https://blog.schoergendorfer.com/post/meta-learning-where-to-allocate-experts-task-conditioned-layer-wise-compressionSecFeedde2026-08-28T10:34:01.282705+00:00Meta-Learning Where to Allocate Experts: Task-Conditioned Layer-Wise Compression for MoEshttps://blog.schoergendorfer.com/post/information-guided-frontier-decoding-contextual-utility-driven-commitment-in-dmlSecFeedde2026-08-28T10:34:01.256387+00:00Information-Guided Frontier Decoding: Contextual Utility-Driven Commitment in dMLLMshttps://blog.schoergendorfer.com/post/not-just-reason-not-just-scan-reinforcement-learning-for-proactive-scientific-erSecFeedde2026-08-28T10:34:01.204615+00:00Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paperhttps://blog.schoergendorfer.com/post/surgical-alignment-in-knowledge-graph-training-for-clinical-diagnosis-with-largeSecFeedde2026-08-28T10:34:01.152663+00:00Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Modelshttps://blog.schoergendorfer.com/post/double-trouble-bilingual-pretraining-leaves-language-conditioned-effects-in-sharSecFeedde2026-08-28T10:34:01.119826+00:00Double Trouble: Bilingual Pretraining Leaves Language-Conditioned Effects in Shared-Language Representationshttps://blog.schoergendorfer.com/post/dependency-aware-revocable-decoding-for-efficient-diffusion-large-language-modelSecFeedde2026-08-28T10:34:01.090406+00:00Dependency-Aware Revocable Decoding for Efficient Diffusion Large Language Model Inferencehttps://blog.schoergendorfer.com/post/spt-skills-as-pre-training-data-for-agentic-language-modelsSecFeedde2026-08-28T10:34:01.062125+00:00SPT: Skills as Pre-Training Data for Agentic Language Modelshttps://blog.schoergendorfer.com/post/spear-distilling-domain-adaptive-reasoning-skeletons-via-sequential-symbolic-aliSecFeedde2026-08-28T10:34:01.033045+00:00SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learninghttps://blog.schoergendorfer.com/post/multi-expert-conformal-risk-control-for-pairwise-llm-judging-in-open-ended-dialoSecFeedde2026-08-28T10:34:01.004332+00:00Multi-Expert Conformal Risk Control for Pairwise LLM Judging in Open-Ended Dialoguehttps://blog.schoergendorfer.com/post/sycophancy-suppression-can-impair-rational-updating-anti-sycophancy-should-preseSecFeedde2026-08-28T10:34:00.976200+00:00Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Updatehttps://blog.schoergendorfer.com/post/case2flow-bridging-patient-cases-and-guideline-flowcharts-through-multimodal-retSecFeedde2026-08-28T10:34:00.888076+00:00Case2Flow: Bridging Patient Cases and Guideline Flowcharts through Multimodal Retrievalhttps://blog.schoergendorfer.com/post/mogancolbert-tr-a-late-interaction-multi-vector-retrieval-model-for-turkishSecFeedde2026-08-28T10:34:00.790532+00:00MoganColBERT-TR: A Late-Interaction Multi-Vector Retrieval Model for Turkishhttps://blog.schoergendorfer.com/post/neuro-symbolic-prm-enhancing-scientific-reasoning-via-structured-traces-and-symbSecFeedde2026-08-28T10:34:00.760547+00:00Neuro-symbolic PRM: Enhancing Scientific Reasoning via Structured Traces and Symbolic Verificationhttps://blog.schoergendorfer.com/post/care-causally-aligned-reasoning-exploration-for-medical-large-language-modelsSecFeedde2026-08-28T10:18:31.488216+00:00CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Modelshttps://blog.schoergendorfer.com/post/vagdhenu-a-vrutta-meter-aware-shloka-to-chant-tts-system-for-sanskritSecFeedde2026-08-28T10:18:31.457440+00:00Vagdhenu: A Vrutta (Meter) Aware Shloka-to-Chant (TTS) System for Sanskrithttps://blog.schoergendorfer.com/post/why-current-xai-is-not-enough-for-arabic-nlp-a-critical-survey-of-the-explainabiSecFeedde2026-08-28T10:18:31.429022+00:00Why Current XAI Is Not Enough for Arabic NLP: A Critical Survey of the Explainability Gaphttps://blog.schoergendorfer.com/post/reward-informed-sparse-autoencoders-and-the-solution-completeness-confoundSecFeedde2026-08-28T10:18:31.403786+00:00Reward-Informed Sparse Autoencoders and the Solution-Completeness Confoundhttps://blog.schoergendorfer.com/post/agent-seer-synthesizing-scenarios-from-specification-understandingSecFeedde2026-08-28T10:18:31.350945+00:00Agent Seer: Synthesizing Scenarios from Specification Understandinghttps://blog.schoergendorfer.com/post/evaluating-language-models-in-realistic-conversational-contextsSecFeedde2026-08-28T10:18:31.327774+00:00Evaluating Language Models in Realistic Conversational Contextshttps://blog.schoergendorfer.com/post/agents-dont-paginate-first-chunk-selection-for-llm-tool-responsesSecFeedde2026-08-28T10:18:31.299393+00:00Agents Don't Paginate: First-Chunk Selection for LLM Tool Responseshttps://blog.schoergendorfer.com/post/telecomgpt-r1-a-unified-open-source-reasoner-for-the-telecom-stackSecFeedde2026-08-28T10:18:31.271779+00:00TelecomGPT-R1: A Unified Open-Source Reasoner for the Telecom Stackhttps://blog.schoergendorfer.com/post/natural-language-policies-to-executable-decisions-an-interpretable-large-languagSecFeedde2026-08-28T10:18:31.245534+00:00Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Frameworkhttps://blog.schoergendorfer.com/post/which-india-survives-translation-narrative-homogenisation-across-indian-oral-traSecFeedde2026-08-28T10:18:31.220754+00:00Which India Survives Translation? Narrative Homogenisation Across Indian Oral Traditions in LLMshttps://blog.schoergendorfer.com/post/deflectbench-a-benchmark-for-evaluating-rhetorical-fallacy-generation-in-llmsSecFeedde2026-08-28T10:18:31.193233+00:00DeflectBench: A Benchmark for Evaluating Rhetorical Fallacy Generation in LLMshttps://blog.schoergendorfer.com/post/elementcheck-complexity-aware-long-form-text-factuality-evaluation-via-sentenceSecFeedde2026-08-28T10:18:31.161937+00:00ElementCheck: Complexity-Aware Long-Form Text Factuality Evaluation via Sentence Elementshttps://blog.schoergendorfer.com/post/treegraft-adaptive-multi-drafter-grafting-for-tree-based-speculative-decodingSecFeedde2026-08-28T10:18:31.135017+00:00TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decodinghttps://blog.schoergendorfer.com/post/lm-x-explainable-action-modeling-with-progress-event-and-uncertainty-prediction-2SecFeedde2026-08-28T10:18:31.109256+00:00LM-X: Explainable Action Modeling with Progress, Event, and Uncertainty Prediction for Generalist Robot Manipulationhttps://blog.schoergendorfer.com/post/keeping-the-index-open-the-recommendation-side-cost-of-shared-search-and-recommeSecFeedde2026-08-28T10:18:31.060683+00:00Keeping the Index Open: The Recommendation-Side Cost of Shared Search and Recommendationhttps://blog.schoergendorfer.com/post/vqc-zti-variational-quantum-control-for-zero-trust-protection-of-the-tactile-int-2SecFeedde2026-08-28T10:18:31.037623+00:00VQC-ZTI: Variational Quantum Control for Zero Trust Protection of the Tactile Internethttps://blog.schoergendorfer.com/post/gradient-free-learning-of-a-closed-loop-wall-controller-for-turbulent-drag-reduc-2SecFeedde2026-08-28T10:18:31.012861+00:00Gradient-free learning of a closed-loop wall controller for turbulent drag reductionhttps://blog.schoergendorfer.com/post/when-top-k-misses-the-decision-tool-call-drift-in-multi-teacher-on-policy-distil-3SecFeedde2026-08-28T10:04:59.813802+00:00When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillationhttps://blog.schoergendorfer.com/post/clinically-aligned-geometry-constraints-for-robust-ivus-vessel-boundary-segmentaSecFeedde2026-08-28T10:04:59.782908+00:00Clinically Aligned Geometry Constraints for Robust IVUS Vessel Boundary Segmentationhttps://blog.schoergendorfer.com/post/adaptive-inference-for-resource-constrained-dynamic-pricing-2SecFeedde2026-08-28T10:04:59.756784+00:00Adaptive Inference for Resource-Constrained Dynamic Pricinghttps://blog.schoergendorfer.com/post/out-of-sight-not-out-of-mind-unveiling-latent-attack-in-latent-based-multi-agentSecFeedde2026-08-28T10:04:59.730377+00:00Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systemshttps://blog.schoergendorfer.com/post/bayes-with-no-shame-admissibility-geometries-of-predictive-inference-2SecFeedde2026-08-28T10:04:59.655981+00:00Bayes with No Shame: Admissibility Geometries of Predictive Inferencehttps://blog.schoergendorfer.com/post/pacifier-pacing-opinion-depolarization-via-a-unified-graph-learning-frameworkSecFeedde2026-08-28T10:04:59.626087+00:00PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Frameworkhttps://blog.schoergendorfer.com/post/toward-all-optical-unsupervised-hebbian-learning-in-deep-photonic-neuromorphic-nSecFeedde2026-08-28T10:04:59.581460+00:00Toward all-optical unsupervised Hebbian learning in deep photonic neuromorphic networkshttps://blog.schoergendorfer.com/post/a-flexible-empirical-bayes-approach-to-generalized-linear-models-with-applicatioSecFeedde2026-08-28T10:04:59.557709+00:00A Flexible Empirical Bayes Approach to Generalized Linear Models, with Applications to Sparse Logistic Regressionhttps://blog.schoergendorfer.com/post/quantitative-mapping-from-conventional-mri-using-self-supervised-physics-guidedSecFeedde2026-08-28T10:04:59.533744+00:00Quantitative mapping from conventional MRI using self-supervised physics-guided deep learning: applications to a large-scale, clinically heterogeneous datasethttps://blog.schoergendorfer.com/post/ucb-for-large-scale-pure-exploration-beyond-sub-gaussianitySecFeedde2026-08-28T10:04:59.507149+00:00UCB for Large-Scale Pure Exploration: Beyond Sub-Gaussianityhttps://blog.schoergendorfer.com/post/a-framework-for-low-effort-training-data-generation-for-urban-semantic-segmentatSecFeedde2026-08-28T10:04:59.480127+00:00A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentationhttps://blog.schoergendorfer.com/post/llm-analysis-of-150-years-of-german-parliamentary-debates-on-migration-reveals-sSecFeedde2026-08-28T10:04:59.448366+00:00LLM Analysis of 150+ years of German Parliamentary Debates on Migration Reveals Shift from Post-War Solidarity to Anti-Solidarity in the Last Decadehttps://blog.schoergendorfer.com/post/sequential-additivity-in-distributionally-robust-ranking-and-selectionSecFeedde2026-08-28T10:04:59.419284+00:00Sequential Additivity in Distributionally Robust Ranking and Selectionhttps://blog.schoergendorfer.com/post/stack-trace-based-crash-deduplication-with-transformer-adaptationSecFeedde2026-08-28T10:04:59.388112+00:00Stack Trace-Based Crash Deduplication with Transformer Adaptationhttps://blog.schoergendorfer.com/post/stitch-ope-trajectory-stitching-with-guided-diffusion-for-off-policy-evaluationSecFeedde2026-08-28T10:04:59.331545+00:00STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluationhttps://blog.schoergendorfer.com/post/bregman-linearized-augmented-lagrangian-method-for-nonconvex-constrained-stochasSecFeedde2026-08-28T10:04:59.301698+00:00Bregman Linearized Augmented Lagrangian Method for Nonconvex Constrained Stochastic Zeroth-order Optimizationhttps://blog.schoergendorfer.com/post/group-shared-low-rank-approximation-for-mobile-efficient-pointwise-convolutions-2SecFeedde2026-08-28T09:50:18.510541+00:00Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNshttps://blog.schoergendorfer.com/post/a-token-level-analysis-of-sampled-token-reverse-kl-on-policy-distillation-2SecFeedde2026-08-28T09:50:18.477246+00:00A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillationhttps://blog.schoergendorfer.com/post/learning-generalizable-behaviors-for-terminal-agentsSecFeedde2026-08-28T09:50:18.442074+00:00Learning Generalizable Behaviors for Terminal Agentshttps://blog.schoergendorfer.com/post/decoupled-physical-modeling-and-execution-for-physics-reasoning-2SecFeedde2026-08-28T09:50:18.406312+00:00Decoupled Physical Modeling and Execution for Physics Reasoninghttps://blog.schoergendorfer.com/post/rethinking-expressivity-and-efficiency-in-test-time-training-2SecFeedde2026-08-28T09:50:18.377131+00:00Rethinking Expressivity and Efficiency in Test-Time Traininghttps://blog.schoergendorfer.com/post/a-real-time-tsetlin-machine-based-non-intrusive-load-monitoring-system-on-mcus-2SecFeedde2026-08-28T09:50:18.342877+00:00A Real-Time Tsetlin Machine-based Non-intrusive Load Monitoring System on MCUshttps://blog.schoergendorfer.com/post/nrcd-an-open-database-of-collegiate-running-with-unified-performance-standardiza-2SecFeedde2026-08-28T09:50:18.310034+00:00NRCD: An Open Database of Collegiate Running with Unified Performance Standardizationhttps://blog.schoergendorfer.com/post/saga-score-weighted-adaptive-generation-alignment-for-low-resource-nordic-langua-2SecFeedde2026-08-28T09:50:18.278875+00:00SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Modelshttps://blog.schoergendorfer.com/post/neural-non-equilibrium-hamiltonian-monte-carlo-for-corrected-boltzmann-sampling-2SecFeedde2026-08-28T09:50:18.253583+00:00Neural Non-Equilibrium Hamiltonian Monte Carlo for Corrected Boltzmann Samplinghttps://blog.schoergendorfer.com/post/auditing-invisible-weight-updates-with-reference-traces-2SecFeedde2026-08-28T09:50:18.216069+00:00Auditing Invisible Weight Updates with Reference Traceshttps://blog.schoergendorfer.com/post/tensorion-a-tensor-aware-generalization-of-the-muon-optimizerSecFeedde2026-08-28T09:50:18.163084+00:00Tensorion: A Tensor-Aware Generalization of the Muon Optimizerhttps://blog.schoergendorfer.com/post/you-dont-need-to-run-every-evalSecFeedde2026-08-28T09:50:18.135143+00:00You Don't Need to Run Every Evalhttps://blog.schoergendorfer.com/post/when-do-autoregressive-sequence-models-forecast-physical-wavefields-a-controlledSecFeedde2026-08-28T09:50:18.105827+00:00When Do Autoregressive Sequence Models Forecast Physical Wavefields? A Controlled Study on Synthetic Seismogramshttps://blog.schoergendorfer.com/post/beyond-flops-benchmarking-real-inference-acceleration-of-llm-pruning-under-a-gemSecFeedde2026-08-28T09:50:18.079521+00:00Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomyhttps://blog.schoergendorfer.com/post/the-attribution-contract-for-generative-language-modelsSecFeedde2026-08-28T09:50:18.053771+00:00The Attribution Contract for Generative Language Modelshttps://blog.schoergendorfer.com/post/aitchison-embeddings-for-learning-compositional-graph-representationsSecFeedde2026-08-28T09:50:18.025853+00:00Aitchison Embeddings for Learning Compositional Graph Representationshttps://blog.schoergendorfer.com/post/the-rashomon-effect-for-visualizing-high-dimensional-dataSecFeedde2026-08-28T09:50:17.973411+00:00The Rashomon Effect for Visualizing High-Dimensional Datahttps://blog.schoergendorfer.com/post/p1-better-prompt-optimization-with-fewer-promptsSecFeedde2026-08-28T09:50:17.945825+00:00$p1$: Better Prompt Optimization with Fewer Promptshttps://blog.schoergendorfer.com/post/stable-but-wrong-when-learning-stabilizes-away-from-the-truthSecFeedde2026-08-28T09:35:47.699435+00:00Stable but Wrong: When Learning Stabilizes Away from the Truthhttps://blog.schoergendorfer.com/post/learning-to-reason-with-curriculum-i-provable-benefits-of-autocurriculumSecFeedde2026-08-28T09:35:47.673409+00:00Learning to Reason with Curriculum I: Provable Benefits of Autocurriculumhttps://blog.schoergendorfer.com/post/private-and-interpretable-clinical-prediction-with-quantum-inspired-tensor-trainSecFeedde2026-08-28T09:35:47.647852+00:00Private and interpretable clinical prediction with quantum-inspired tensor train modelshttps://blog.schoergendorfer.com/post/cofm-consistent-optimal-transport-flow-matching-via-partially-input-convex-neuraSecFeedde2026-08-28T09:35:47.624504+00:00COFM: Consistent Optimal Transport Flow Matching via Partially Input Convex Neural Networkshttps://blog.schoergendorfer.com/post/absolute-indices-for-determining-compactness-separability-and-number-of-clustersSecFeedde2026-08-28T09:35:47.599162+00:00Absolute indices for determining compactness, separability and number of clustershttps://blog.schoergendorfer.com/post/a-survey-of-llm-prompt-datasets-taxonomy-linguistic-patterns-and-practical-usesSecFeedde2026-08-28T09:35:47.574213+00:00A Survey of LLM Prompt Datasets: Taxonomy, Linguistic Patterns, and Practical Useshttps://blog.schoergendorfer.com/post/leakage-free-evaluation-and-distribution-robust-spatio-temporal-graph-learning-fSecFeedde2026-08-28T09:35:47.547268+00:00Leakage-Free Evaluation and Distribution-Robust Spatio-Temporal Graph Learning for Inductive Kriginghttps://blog.schoergendorfer.com/post/relate-accelerating-tensor-decomposition-via-safe-and-efficient-learning-of-sparSecFeedde2026-08-28T09:35:47.516044+00:00ReLATE: Accelerating Tensor Decomposition via Safe and Efficient Learning of Sparse Encodingshttps://blog.schoergendorfer.com/post/provable-one-poison-backdoor-attacks-on-linear-models-and-relu-neural-networksSecFeedde2026-08-28T09:35:47.491194+00:00Provable one-poison backdoor attacks on linear models and ReLU neural networkshttps://blog.schoergendorfer.com/post/plain-transformers-can-be-powerful-graph-learnersSecFeedde2026-08-28T09:35:47.469874+00:00Plain Transformers Can be Powerful Graph Learnershttps://blog.schoergendorfer.com/post/modis-multi-omics-data-integration-for-small-and-unpaired-datasetsSecFeedde2026-08-28T09:35:47.448154+00:00MODIS: Multi-Omics Data Integration for Small and unpaired datasetshttps://blog.schoergendorfer.com/post/federated-adversarial-training-with-transformersSecFeedde2026-08-28T09:35:47.404995+00:00Federated Adversarial Training with Transformershttps://blog.schoergendorfer.com/post/scaling-graph-neural-networks-for-friend-recommendation-multi-hash-user-embeddinSecFeedde2026-08-28T09:35:47.380882+00:00Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Samplinghttps://blog.schoergendorfer.com/post/puro-2b-poor-labs-qwen2-15b-trained-on-rtx-5090-within-5090SecFeedde2026-08-28T09:35:47.312550+00:00Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090https://blog.schoergendorfer.com/post/recovering-expert-critic-sourced-network-adjacency-between-musical-artists-fromSecFeedde2026-08-28T09:35:47.287710+00:00Recovering Expert Critic-Sourced Network Adjacency between Musical Artists from Acoustic Distributions: A Construct-Validity Approachhttps://blog.schoergendorfer.com/post/enforcing-dirichlet-boundary-conditions-in-operator-learningSecFeedde2026-08-28T09:19:11.583129+00:00Enforcing Dirichlet Boundary Conditions in Operator Learninghttps://blog.schoergendorfer.com/post/a-point-of-prescription-safety-check-system-for-adverse-drug-reactions-in-ruralSecFeedde2026-08-28T09:19:11.552037+00:00A Point-of-Prescription Safety-Check System for Adverse Drug Reactions in Rural Bangladeshi Hospitals: A Feasibility Studyhttps://blog.schoergendorfer.com/post/data-efficient-crack-quantification-in-lithium-ion-cathodes-using-foundation-modSecFeedde2026-08-28T09:19:11.525914+00:00Data-efficient crack quantification in lithium-ion cathodes using foundation model transferhttps://blog.schoergendorfer.com/post/securedrive-fl-joint-differential-privacy-and-gradient-aware-selective-homomorphSecFeedde2026-08-28T09:19:11.436614+00:00SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoringhttps://blog.schoergendorfer.com/post/foldpipe-bounded-remote-streaming-of-native-molecular-shards-with-asynchronous-pSecFeedde2026-08-28T09:19:11.409508+00:00FoldPipe: Bounded Remote Streaming of Native Molecular Shards with Asynchronous Prefetchhttps://blog.schoergendorfer.com/post/representation-measurements-under-function-preserving-reparameterizationsSecFeedde2026-08-28T09:19:11.379447+00:00Representation Measurements Under Function-Preserving Reparameterizationshttps://blog.schoergendorfer.com/post/why-not-to-use-the-gaussian-kernelSecFeedde2026-08-28T09:19:11.341656+00:00Why not to use the Gaussian kernelhttps://blog.schoergendorfer.com/post/squeezing-more-from-limited-data-with-recursive-transformersSecFeedde2026-08-28T09:19:11.309943+00:00Squeezing More from Limited Data with Recursive Transformershttps://blog.schoergendorfer.com/post/data-driven-koopman-mode-approximation-a-neural-power-iteration-algorithmSecFeedde2026-08-28T09:19:11.277401+00:00Data-driven Koopman mode approximation: A neural power iteration algorithmhttps://blog.schoergendorfer.com/post/bridging-short-and-medium-range-weather-forecasting-with-machine-learningSecFeedde2026-08-28T09:19:11.231836+00:00Bridging short- and medium-range weather forecasting with machine learninghttps://blog.schoergendorfer.com/post/incremental-recommendation-via-causal-modelsSecFeedde2026-08-28T09:19:11.206097+00:00Incremental Recommendation via Causal Modelshttps://blog.schoergendorfer.com/post/hyperspectral-diffusion-equivariant-imaging-hydiff-ei-a-self-supervised-frameworSecFeedde2026-08-28T09:19:11.178416+00:00Hyperspectral Diffusion Equivariant Imaging (HyDiff-EI): A Self-supervised Framework for Hyperspectral Image Inpaintinghttps://blog.schoergendorfer.com/post/equal-ranking-quality-different-decisions-training-order-consistent-llm-scorersSecFeedde2026-08-28T09:19:11.123419+00:00Equal Ranking Quality, Different Decisions: Training Order-Consistent LLM Scorershttps://blog.schoergendorfer.com/post/domain-specific-self-supervised-representation-learning-for-retinal-fundus-classSecFeedde2026-08-28T09:19:11.097251+00:00Domain-Specific Self-Supervised Representation Learning for Retinal Fundus Classificationhttps://blog.schoergendorfer.com/post/generative-semantic-scene-completionSecFeedde2026-08-28T09:19:11.068998+00:00Generative Semantic Scene Completionhttps://blog.schoergendorfer.com/post/hierarchical-channel-stacking-a-structured-decision-framework-for-ai-generated-iSecFeedde2026-08-28T09:03:14.155056+00:00Hierarchical Channel Stacking: A Structured Decision Framework for AI-Generated Image Detectionhttps://blog.schoergendorfer.com/post/dynamical-phase-selection-controls-compute-scaling-in-looped-transformersSecFeedde2026-08-28T09:03:14.081343+00:00Dynamical phase selection controls compute scaling in looped transformershttps://blog.schoergendorfer.com/post/hadamard-flattening-and-gaussian-pooling-sketch-for-least-squares-with-coordinatSecFeedde2026-08-28T09:03:14.050519+00:00Hadamard Flattening and Gaussian Pooling Sketch for Least Squares with Coordinate-wise Guaranteehttps://blog.schoergendorfer.com/post/sharp-minimax-regret-for-infinite-memory-logistic-predictionSecFeedde2026-08-28T09:03:14.023809+00:00Sharp Minimax Regret for Infinite-Memory Logistic Predictionhttps://blog.schoergendorfer.com/post/vowel-signs-are-not-letters-a-pre-tokenization-ceiling-on-multilingual-tokenizerSecFeedde2026-08-28T09:03:13.999403+00:00Vowel Signs Are Not Letters: A Pre-tokenization Ceiling on Multilingual Tokenizer Fertilityhttps://blog.schoergendorfer.com/post/systematic-literature-review-of-machine-learning-models-and-applications-for-texSecFeedde2026-08-28T09:03:13.974605+00:00Systematic Literature Review of Machine Learning Models and Applications for Text Recognitionhttps://blog.schoergendorfer.com/post/interpreting-latent-protein-language-model-features-with-geometric-annotationsSecFeedde2026-08-28T09:03:13.947783+00:00Interpreting Latent Protein Language Model Features with Geometric Annotationshttps://blog.schoergendorfer.com/post/towards-a-universal-meta-optics-solver-via-large-language-modelsSecFeedde2026-08-28T09:03:13.922351+00:00Towards a universal meta-optics solver via large language modelshttps://blog.schoergendorfer.com/post/lowrankarena-a-standardized-evaluation-platform-for-svd-based-llm-compressionSecFeedde2026-08-28T09:03:13.897928+00:00LowRankArena: A Standardized Evaluation Platform for SVD-Based LLM Compressionhttps://blog.schoergendorfer.com/post/cross-simulator-transfer-with-foundation-model-summaries-towards-robust-ska-eraSecFeedde2026-08-28T09:03:13.869408+00:00Cross-simulator transfer with foundation model summaries: Towards robust SKA-era reionization inferencehttps://blog.schoergendorfer.com/post/finding-the-right-evidence-factor-guided-coarse-to-fine-reasoning-for-long-videoSecFeedde2026-08-28T09:03:13.841917+00:00Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videoshttps://blog.schoergendorfer.com/post/when-is-noise-response-universal-tokenization-as-the-hidden-variable-in-languageSecFeedde2026-08-28T09:03:13.808470+00:00When Is Noise Response Universal? Tokenization as the Hidden Variable in Language Modelshttps://blog.schoergendorfer.com/post/district-level-food-environment-indicators-and-social-vulnerability-in-sao-pauloSecFeedde2026-08-28T09:03:13.776240+00:00District-Level Food Environment Indicators and Social Vulnerability in S\~ao Paulohttps://blog.schoergendorfer.com/post/multi-dataset-inverse-problem-solving-with-distributed-generative-aiSecFeedde2026-08-28T09:03:13.743525+00:00Multi-Dataset Inverse Problem Solving with Distributed Generative AIhttps://blog.schoergendorfer.com/post/constraint-aware-physics-informed-neural-networks-for-static-shape-estimation-ofSecFeedde2026-08-28T09:03:13.714410+00:00Constraint-Aware Physics-Informed Neural Networks for Static Shape Estimation of Co-Manipulative Continuum Robotshttps://blog.schoergendorfer.com/post/a-causal-graph-informed-temporal-convolution-architecture-for-interpretable-retaSecFeedde2026-08-28T09:03:13.690677+00:00A causal graph-informed temporal convolution architecture for interpretable retail electricity price forecastinghttps://blog.schoergendorfer.com/post/classical-and-hybrid-quantum-machine-learning-for-trigger-like-event-selection-oSecFeedde2026-08-28T09:03:13.663504+00:00Classical and Hybrid Quantum Machine Learning for Trigger-Like Event Selection on CMS Open Data: An Eight-Qubit, PCA-Constrained Benchmarkhttps://blog.schoergendorfer.com/post/trace-retrospective-streaming-generation-of-physical-fields-under-sparse-structuSecFeedde2026-08-28T09:03:13.637598+00:00TRACE: Retrospective Streaming Generation of Physical Fields under Sparse Structured Sensinghttps://blog.schoergendorfer.com/post/real-time-virtual-circuits-for-plasma-shape-control-via-neural-network-emulatorsSecFeedde2026-08-28T08:47:54.556185+00:00Real-time virtual circuits for plasma shape control via neural network emulators: integration and testing in the MAST-U PCShttps://blog.schoergendorfer.com/post/adathinking-e-one-token-entropy-regulation-for-adaptive-thinkingSecFeedde2026-08-28T08:47:54.528943+00:00AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinkinghttps://blog.schoergendorfer.com/post/affix-cache-for-diffusion-large-language-modelsSecFeedde2026-08-28T08:47:54.502512+00:00Affix Cache for Diffusion Large Language Modelshttps://blog.schoergendorfer.com/post/cross-platform-generalisation-failure-in-mental-health-natural-language-processiSecFeedde2026-08-28T08:47:54.478018+00:00Cross-Platform Generalisation Failure in Mental Health Natural Language Processing: A Five-Axis Fairness Audit of Transformer Models on Social Mediahttps://blog.schoergendorfer.com/post/interpretable-fairly-evaluated-automated-l2-speaking-assessment-that-beats-the-sSecFeedde2026-08-28T08:47:54.448949+00:00Interpretable, Fairly Evaluated Automated L2 Speaking Assessment that Beats the Single-Human Ceiling and Why Pause Encoding Does Not Change LLM Fluency Scoreshttps://blog.schoergendorfer.com/post/graph-based-modeling-of-financial-volatility-dynamicsSecFeedde2026-08-28T08:47:54.417593+00:00Graph-Based Modeling of Financial Volatility Dynamicshttps://blog.schoergendorfer.com/post/can-a-model-catch-its-own-hallucinations-for-free-label-free-doubt-signals-holdSecFeedde2026-08-28T08:47:54.389085+00:00Can a Model Catch Its Own Hallucinations for Free?: Label-Free Doubt Signals Hold Their Own Against a Labelled Dataset for Abstentionhttps://blog.schoergendorfer.com/post/generative-monte-carlo-sampling-for-constant-cost-particle-transportSecFeedde2026-08-28T08:47:54.329694+00:00Generative Monte Carlo Sampling for Constant-Cost Particle Transporthttps://blog.schoergendorfer.com/post/a-dynamic-likelihood-approach-to-filtering-for-advection-diffusion-dynamicsSecFeedde2026-08-28T08:47:54.299442+00:00A Dynamic Likelihood Approach to Filtering for Advection-Diffusion Dynamicshttps://blog.schoergendorfer.com/post/understanding-evolution-strategies-for-llm-reasoning-broader-reasoning-coverageSecFeedde2026-08-28T08:47:54.271339+00:00Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPOhttps://blog.schoergendorfer.com/post/beyond-parallel-blindness-information-floors-and-model-gaps-in-block-draftingSecFeedde2026-08-28T08:47:54.236334+00:00Beyond Parallel Blindness: Information Floors and Model Gaps in Block Draftinghttps://blog.schoergendorfer.com/post/quantumboostnet-a-hybrid-classical-quantum-architecture-for-enhanced-accuracy-inSecFeedde2026-08-28T08:47:54.205282+00:00QuantumBoostNet: A Hybrid Classical-Quantum Architecture for Enhanced Accuracy in Cardiac Ultrasound View Identificationhttps://blog.schoergendorfer.com/post/making-latent-evolution-explicit-operator-structured-transitions-for-world-actioSecFeedde2026-08-28T08:47:54.161385+00:00Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Modelshttps://blog.schoergendorfer.com/post/circuit-condensation-post-training-that-concentrates-a-behaviors-causal-circuitSecFeedde2026-08-28T08:47:54.129574+00:00Circuit Condensation: Post-Training that Concentrates a Behavior's Causal Circuithttps://blog.schoergendorfer.com/post/importance-scoring-of-transformer-attention-heads-in-learning-tabular-dataSecFeedde2026-08-28T08:47:54.098005+00:00Importance Scoring of Transformer Attention Heads in Learning Tabular Datahttps://blog.schoergendorfer.com/post/halo-a-heterogeneity-aware-language-aligned-imu-foundation-model-for-open-set-huSecFeedde2026-08-28T08:47:54.066700+00:00HALO: A Heterogeneity-Aware Language-Aligned IMU Foundation Model for Open-Set Human Activity Recognitionhttps://blog.schoergendorfer.com/post/profit-based-evaluation-of-machine-learning-for-nitrogen-recommendations-in-wintSecFeedde2026-08-28T08:47:54.036336+00:00Profit based evaluation of machine learning for nitrogen recommendations in winter wheathttps://blog.schoergendorfer.com/post/common-geodesics-do-not-guarantee-fisher-consistency-of-the-structured-svm-minimSecFeedde2026-08-28T08:47:54.000852+00:00Common Geodesics Do Not Guarantee Fisher Consistency of the Structured SVM: Minimal Counterexamples and a Tree-Metric Classificationhttps://blog.schoergendorfer.com/post/when-interference-graphs-evolve-doubly-robust-estimation-of-dynamic-peer-effectsSecFeedde2026-08-28T08:32:50.699855+00:00When Interference Graphs Evolve: Doubly Robust Estimation of Dynamic Peer Effectshttps://blog.schoergendorfer.com/post/tracebench-controlled-evaluation-of-llm-agents-for-time-series-root-cause-attribSecFeedde2026-08-28T08:32:50.674749+00:00TraceBench: Controlled Evaluation of LLM Agents for Time-Series Root-Cause Attributionhttps://blog.schoergendorfer.com/post/diffusion-policies-for-short-horizon-planning-in-robot-crowd-navigationSecFeedde2026-08-28T08:32:50.650832+00:00Diffusion Policies for Short-Horizon Planning in Robot Crowd Navigationhttps://blog.schoergendorfer.com/post/inductive-correlation-clustering-with-graph-neural-networksSecFeedde2026-08-28T08:32:50.623213+00:00Inductive Correlation Clustering with Graph Neural Networkshttps://blog.schoergendorfer.com/post/ultra-low-power-lightweight-probabilistic-rss-based-path-reconstruction-a-systemSecFeedde2026-08-28T08:32:50.598432+00:00Ultra Low-Power, Lightweight, Probabilistic RSS-Based Path Reconstruction: A System for Landscape-Scale Bee Trackinghttps://blog.schoergendorfer.com/post/cone-extended-rayleigh-quotients-for-directed-graph-learning-minimax-spectral-ceSecFeedde2026-08-28T08:32:50.570500+00:00Cone Extended Rayleigh Quotients for Directed Graph Learning: Minimax Spectral Certificates, Sensitivity, and Adaptive Controlhttps://blog.schoergendorfer.com/post/trace-crc-trajectory-adaptive-conformal-risk-control-for-multi-step-channel-statSecFeedde2026-08-28T08:32:50.544421+00:00TRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Predictionhttps://blog.schoergendorfer.com/post/tabular-deep-learning-for-algorithmic-trading-cross-regime-bayesian-optimisationSecFeedde2026-08-28T08:32:50.513317+00:00Tabular Deep Learning for Algorithmic Trading: Cross-Regime Bayesian Optimisation for Equity Signal Generationhttps://blog.schoergendorfer.com/post/unifying-detection-and-adaptation-in-task-free-continual-learningSecFeedde2026-08-28T08:32:50.488203+00:00Unifying Detection and Adaptation in Task-Free Continual Learninghttps://blog.schoergendorfer.com/post/soft-active-electromyography-interface-for-machine-learning-enabled-silent-speecSecFeedde2026-08-28T08:32:50.462190+00:00Soft Active Electromyography Interface for Machine Learning-Enabled Silent Speech Recognitionhttps://blog.schoergendorfer.com/post/benchmarking_fast_domain_adaptation_for_unsupervised_speech_unitsSecFeedde2026-08-28T08:32:50.435952+00:00Benchmarking_Fast_Domain_Adaptation_for_Unsupervised_Speech_Unitshttps://blog.schoergendorfer.com/post/disentangling-optimization-scale-from-preference-scale-in-dpoSecFeedde2026-08-28T08:32:50.411195+00:00Disentangling Optimization Scale from Preference Scale in DPOhttps://blog.schoergendorfer.com/post/decentralized-multitask-learning-over-learned-task-graphsSecFeedde2026-08-28T08:32:50.386205+00:00Decentralized Multitask Learning over Learned Task Graphshttps://blog.schoergendorfer.com/post/terrain-signatures-in-welsh-settlement-namesSecFeedde2026-08-28T08:32:50.358577+00:00Terrain signatures in Welsh settlement nameshttps://blog.schoergendorfer.com/post/templar-wales-a-georeferenced-environmental-and-toponymic-dataset-of-welsh-settlSecFeedde2026-08-28T08:32:50.329261+00:00TEMPLAR Wales: A georeferenced environmental and toponymic dataset of Welsh settlementshttps://blog.schoergendorfer.com/post/graph-based-pseudo-multimodal-contrastive-learning-for-12-lead-ecg-representatioSecFeedde2026-08-28T08:32:50.300593+00:00Graph-Based Pseudo-multimodal Contrastive Learning for 12-Lead ECG Representationshttps://blog.schoergendorfer.com/post/clusterattention-a-training-free-speedup-of-bidirectional-attentionSecFeedde2026-08-28T08:32:50.270946+00:00ClusterAttention: A training-free speedup of bidirectional attentionhttps://blog.schoergendorfer.com/post/adversarial-training-without-input-gradients-via-low-rank-householder-expansionsSecFeedde2026-08-28T08:32:50.242494+00:00Adversarial Training Without Input Gradients via Low-Rank Householder Expansionshttps://blog.schoergendorfer.com/post/packora-systematic-design-for-generative-molecular-crystal-structure-predictionSecFeedde2026-08-28T08:32:50.214516+00:00Packora: Systematic Design for Generative Molecular Crystal Structure Predictionhttps://blog.schoergendorfer.com/post/gromov-monge-flow-matching-for-equivariant-graph-generationSecFeedde2026-08-28T08:32:50.189807+00:00Gromov-Monge Flow Matching for Equivariant Graph Generationhttps://blog.schoergendorfer.com/post/scaling-model-generated-distillation-data-can-make-latent-teacher-traits-more-reSecFeedde2026-08-28T08:17:56.367927+00:00Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverablehttps://blog.schoergendorfer.com/post/a-layer-importance-metric-for-quantization-accounting-for-the-speed-quality-tradSecFeedde2026-08-28T08:17:56.339826+00:00A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Modelshttps://blog.schoergendorfer.com/post/mitigating-strong-modality-collapse-in-multimodal-learning-via-inverted-asymmetrSecFeedde2026-08-28T08:17:56.309781+00:00Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusionhttps://blog.schoergendorfer.com/post/when-is-the-sharp-covariance-envelope-tight-feature-only-geometry-for-volume-samSecFeedde2026-08-28T08:17:56.281552+00:00When Is the Sharp Covariance Envelope Tight? Feature-Only Geometry for Volume-Sampled Least Squareshttps://blog.schoergendorfer.com/post/sage-variate-wise-semantic-augmentation-for-vision-language-time-series-forecastSecFeedde2026-08-28T08:17:56.257353+00:00SAGE: Variate-Wise Semantic Augmentation for Vision-Language Time Series Forecastinghttps://blog.schoergendorfer.com/post/beyond-client-averaging-a-client-independent-second-order-stationary-bias-componSecFeedde2026-08-28T08:17:56.204181+00:00Beyond Client Averaging: A Client-Independent Second-Order Stationary-Bias Component in Stochastic SCAFFOLDhttps://blog.schoergendorfer.com/post/safety-by-design-realized-cost-constraints-for-contextual-bandits-with-continuouSecFeedde2026-08-28T08:17:56.174775+00:00Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actionshttps://blog.schoergendorfer.com/post/neural-regression-with-embeddings-for-numerical-attribute-prediction-in-knowledgSecFeedde2026-08-28T08:17:56.144835+00:00Neural Regression with Embeddings for Numerical Attribute Prediction in Knowledge Graphshttps://blog.schoergendorfer.com/post/self-augmented-diffusion-guidance-for-physics-informed-generationSecFeedde2026-08-28T08:17:56.117748+00:00Self-Augmented Diffusion Guidance for Physics-Informed Generationhttps://blog.schoergendorfer.com/post/simple-actors-and-deep-critics-for-scalable-reinforcement-learningSecFeedde2026-08-28T08:17:56.092262+00:00Simple Actors and Deep Critics for Scalable Reinforcement Learninghttps://blog.schoergendorfer.com/post/when-privacy-hurts-mergeability-geometry-aware-model-merging-under-differentialSecFeedde2026-08-28T08:17:56.067401+00:00When Privacy Hurts Mergeability: Geometry-Aware Model Merging under Differential Privacyhttps://blog.schoergendorfer.com/post/robust-neural-stimulation-response-modeling-through-meta-learning-and-pretraininSecFeedde2026-08-28T08:17:56.042351+00:00Robust Neural Stimulation Response Modeling Through Meta-Learning and Pretraininghttps://blog.schoergendorfer.com/post/simcast-s2s-an-efficient-generative-model-for-subseasonal-precipitation-forecastSecFeedde2026-08-28T08:17:56.018224+00:00SimCast-S2S: An Efficient Generative Model for Subseasonal Precipitation Forecasting via Transfer Learning from Climate Simulationshttps://blog.schoergendorfer.com/post/technical-comparative-benchmarking-study-advanced-ai-hybrid-methods-for-renewablSecFeedde2026-08-28T08:17:55.987342+00:00Technical Comparative Benchmarking Study: Advanced AI Hybrid Methods for Renewable Energy Farm Optimization and Forecastinghttps://blog.schoergendorfer.com/post/gras-guided-reduced-variance-proposals-and-adaptive-selection-for-training-freeSecFeedde2026-08-28T08:17:55.961871+00:00GRAS: Guided Reduced-Variance Proposals and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusionhttps://blog.schoergendorfer.com/post/activation-outliers-matter-robust-recovery-for-quantized-multimodal-llmsSecFeedde2026-08-28T08:17:55.937161+00:00Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMshttps://blog.schoergendorfer.com/post/arrive-and-survive-scaling-safe-goal-conditioned-policy-learning-from-one-bit-faSecFeedde2026-08-28T08:17:55.912577+00:00Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signalshttps://blog.schoergendorfer.com/post/predicting-quantifiability-from-primary-screens-to-prioritize-dose-response-profSecFeedde2026-08-28T08:17:55.853118+00:00Predicting Quantifiability from Primary Screens to Prioritize Dose-Response Profilinghttps://blog.schoergendorfer.com/post/high-probability-derivative-bounds-for-random-tanh-neural-networks-on-a-hypercubSecFeedde2026-08-28T08:02:38.853073+00:00High Probability Derivative Bounds for Random tanh Neural Networks on a Hypercubehttps://blog.schoergendorfer.com/post/algorithmic-principles-for-multiclass-learning-are-hard-to-come-by-limits-of-regSecFeedde2026-08-28T08:02:38.823837+00:00Algorithmic Principles For Multiclass Learning Are Hard To Come By: Limits of Regularization and Proper Learninghttps://blog.schoergendorfer.com/post/a-single-suffix-to-break-them-all-basin-aware-jailbreaks-for-merged-model-familiSecFeedde2026-08-28T08:02:38.797660+00:00A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Familieshttps://blog.schoergendorfer.com/post/a-unified-framework-for-fair-and-personalized-decentralized-learning-under-commuSecFeedde2026-08-28T08:02:38.773012+00:00A Unified Framework for Fair and Personalized Decentralized Learning under Communication Constraintshttps://blog.schoergendorfer.com/post/shared-actors-need-not-share-critics-effects-of-value-mismatch-in-parallel-reinfSecFeedde2026-08-28T08:02:38.716488+00:00Shared Actors Need Not Share Critics: Effects of Value Mismatch in Parallel Reinforcement Learninghttps://blog.schoergendorfer.com/post/distributed-training-using-an-intelligent-networkSecFeedde2026-08-28T08:02:38.689277+00:00Distributed Training using an Intelligent Networkhttps://blog.schoergendorfer.com/post/toward-equitable-low-carbon-mobility-fairness-aware-demand-prediction-for-expandSecFeedde2026-08-28T08:02:38.636211+00:00Toward Equitable Low-Carbon Mobility: Fairness-Aware Demand Prediction for Expanding Bike-Sharing Systemshttps://blog.schoergendorfer.com/post/subgraph-filtering-for-fair-graph-neural-networksSecFeedde2026-08-28T08:02:38.605566+00:00Subgraph Filtering for Fair Graph Neural Networkshttps://blog.schoergendorfer.com/post/neotrifuse-reliability-aware-multimodal-fusion-under-missingness-heterogeneity-fSecFeedde2026-08-28T08:02:38.575180+00:00NeoTriFuse: Reliability-Aware Multimodal Fusion under Missingness Heterogeneity for Neonatal Mortality Risk Predictionhttps://blog.schoergendorfer.com/post/fedcmapss-a-benchmark-for-federated-learning-in-remaining-useful-life-estimationSecFeedde2026-08-28T08:02:38.543449+00:00FedCMAPSS: A Benchmark for Federated Learning in Remaining Useful Life Estimationhttps://blog.schoergendorfer.com/post/privacy-without-regret-differentially-private-inference-time-alignmentSecFeedde2026-08-28T08:02:38.511351+00:00Privacy Without Regret: Differentially Private Inference-Time Alignmenthttps://blog.schoergendorfer.com/post/algebraic-multigrid-acceleration-for-efficient-label-spreadingSecFeedde2026-08-28T08:02:38.461087+00:00Algebraic Multigrid Acceleration for Efficient Label Spreadinghttps://blog.schoergendorfer.com/post/muon-with-finite-newton-schulz-the-smoothing-benefit-in-nonsmooth-nonconvex-optiSecFeedde2026-08-28T08:02:38.432179+00:00Muon with Finite Newton-Schulz: The Smoothing Benefit in Nonsmooth Nonconvex Optimizationhttps://blog.schoergendorfer.com/post/pruning-binarized-neural-networks-a-dedicated-framework-and-globally-weighted-alSecFeedde2026-08-28T08:02:38.395500+00:00Pruning Binarized Neural Networks: A Dedicated Framework and Globally Weighted Algorithmshttps://blog.schoergendorfer.com/post/slm-conditioned-hierarchical-relation-routing-for-labeled-property-graph-learninSecFeedde2026-08-28T08:02:38.364365+00:00SLM-Conditioned Hierarchical Relation Routing for Labeled Property Graph Learninghttps://blog.schoergendorfer.com/post/learning-new-facts-with-qlora-an-acquisition-retention-frontier-2SecFeedde2026-08-28T08:02:38.335788+00:00Learning New Facts with QLoRA: An Acquisition-Retention Frontierhttps://blog.schoergendorfer.com/post/when-stale-constraints-go-unchecked-budgeted-verification-failures-in-inherited-2SecFeedde2026-08-28T08:02:38.309004+00:00When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memoryhttps://blog.schoergendorfer.com/post/4dstreamctrl-interactive-video-generation-with-online-4d-controlSecFeedde2026-08-28T07:47:45.418200+00:004DStreamCtrl: Interactive Video Generation with Online 4D Controlhttps://blog.schoergendorfer.com/post/macgen-toward-functionally-correct-and-secure-code-generation-via-multi-agent-coSecFeedde2026-08-28T07:47:45.343607+00:00MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaborationhttps://blog.schoergendorfer.com/post/datakernelbench-can-llms-optimize-database-queries-on-gpus-2SecFeedde2026-08-28T07:47:45.313948+00:00DataKernelBench: Can LLMs Optimize Database Queries on GPUs?https://blog.schoergendorfer.com/post/cat-gs-balanced-multimodal-learning-via-calibrated-gating-and-fusion-surgery-2SecFeedde2026-08-28T07:47:45.259736+00:00CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgeryhttps://blog.schoergendorfer.com/post/when-youth-enter-the-chat-an-epistemic-shift-in-the-validation-of-llm-based-meas-2SecFeedde2026-08-28T07:47:45.226819+00:00When Youth Enter The Chat: An Epistemic Shift in the Validation of LLM-Based Measures of Student Talkhttps://blog.schoergendorfer.com/post/exam2-underlineextending-underlineaudio-understanding-in-underlinemultilingual-a-2SecFeedde2026-08-28T07:47:45.195850+00:00EXAM$^2$: $\underline{Ex}tending$ $\underline{A}udio$ $Understanding$ $in$ $\underline{M}ultilingual$ $and$ $\underline{M}ultimodal$ $Analysis$https://blog.schoergendorfer.com/post/the-limits-of-automatic-evaluation-of-creativity-in-large-language-models-2SecFeedde2026-08-28T07:47:45.167288+00:00The Limits of Automatic Evaluation of Creativity in Large Language Modelshttps://blog.schoergendorfer.com/post/language-chain-in-alignment-cross-lingual-ranking-preference-optimization-2SecFeedde2026-08-28T07:47:45.138504+00:00Language Chain in Alignment: Cross-lingual Ranking Preference Optimizationhttps://blog.schoergendorfer.com/post/complexity-induction-compositional-generalization-via-structured-training-distorSecFeedde2026-08-28T07:47:45.081333+00:00Complexity Induction: Compositional Generalization via Structured Training Distortionhttps://blog.schoergendorfer.com/post/x2localizer-cross-grained-alignment-for-progressive-cross-view-video-geo-localiz-2SecFeedde2026-08-28T07:47:45.049867+00:00X$^2$Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localizationhttps://blog.schoergendorfer.com/post/pre-training-visual-dexterity-in-simulation-2SecFeedde2026-08-28T07:47:45.020991+00:00Pre-training Visual Dexterity in Simulationhttps://blog.schoergendorfer.com/post/mllm-routed-heterogeneous-ensembles-for-robust-cross-dataset-image-classificatio-2SecFeedde2026-08-28T07:47:44.993061+00:00MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classificationhttps://blog.schoergendorfer.com/post/m-net-integrating-spectral-features-and-physical-field-operators-into-deep-learn-2SecFeedde2026-08-28T07:47:44.958735+00:00M-Net: Integrating Spectral Features and Physical Field Operators into Deep Learning for Medical Image Segmentationhttps://blog.schoergendorfer.com/post/a-12-cnot-double-qubit-excitation-gateSecFeedde2026-08-28T07:47:44.928588+00:00A 12-CNOT Double Qubit Excitation Gatehttps://blog.schoergendorfer.com/post/reopd-reliability-adaptive-reward-extrapolation-for-on-policy-distillation-3SecFeedde2026-08-28T07:47:44.898883+00:00REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillationhttps://blog.schoergendorfer.com/post/evidence-grounded-trustworthy-multimodal-reasoning-and-evaluation-benchmark-in-c-2SecFeedde2026-08-28T07:47:44.871420+00:00Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Sceneshttps://blog.schoergendorfer.com/post/scalesense-cost-intelligent-scaling-framework-via-learned-resource-estimation-in-2SecFeedde2026-08-28T07:47:44.843232+00:00ScaleSense: Cost-Intelligent Scaling Framework via Learned Resource Estimation in Alibaba AnalyticDBhttps://blog.schoergendorfer.com/post/univvt-a-unified-end-to-end-framework-for-high-fidelity-video-virtual-try-on-2SecFeedde2026-08-28T07:47:44.812345+00:00UniVVT: A Unified End-to-End Framework for High-Fidelity Video Virtual Try-onhttps://blog.schoergendorfer.com/post/when-does-latent-communication-pay-a-causal-audit-of-relayed-kv-caches-in-multi-2SecFeedde2026-08-28T07:32:32.376422+00:00When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMshttps://blog.schoergendorfer.com/post/can-lvlms-uncover-the-truth-behind-visual-illusions-an-analysis-of-perceptual-anSecFeedde2026-08-28T07:32:32.343571+00:00Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning Capabilitieshttps://blog.schoergendorfer.com/post/reprec-representation-driven-parameter-efficient-recommendation-system-2SecFeedde2026-08-28T07:32:32.310803+00:00REPREC: Representation Driven Parameter-Efficient Recommendation Systemhttps://blog.schoergendorfer.com/post/trishieldrag-3-rings-one-blind-spot-in-layered-defenses-for-retrieval-augmentedSecFeedde2026-08-28T07:32:32.277673+00:00TriShieldRAG: 3 Rings, One Blind Spot in Layered Defenses for Retrieval-Augmented Generationhttps://blog.schoergendorfer.com/post/atlas-automated-approximation-of-transformers-for-efficient-homomorphic-inferenc-2SecFeedde2026-08-28T07:32:32.248571+00:00ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hourhttps://blog.schoergendorfer.com/post/drift-adaptive-icu-intervention-prediction-freezing-the-physiological-encoder-fo-2SecFeedde2026-08-28T07:32:32.219427+00:00Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updatinghttps://blog.schoergendorfer.com/post/autoresearch-with-coding-agents-generalizers-and-metric-maximizers-on-quran-reci-2SecFeedde2026-08-28T07:32:32.187106+00:00Autoresearch with Coding Agents: Generalizers and Metric-Maximizers on Quran Recitation Datahttps://blog.schoergendorfer.com/post/ppe-bench-a-benchmark-for-evaluating-mllm-unlearning-under-private-public-entang-2SecFeedde2026-08-28T07:32:32.134061+00:00PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglementhttps://blog.schoergendorfer.com/post/shift-semantic-harmonization-via-index-side-feature-transformation-for-multilingSecFeedde2026-08-28T07:32:32.099904+00:00SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrievalhttps://blog.schoergendorfer.com/post/harnessing-the-collective-intelligence-of-ai-agents-in-the-wild-for-new-discoverSecFeedde2026-08-28T07:32:32.047237+00:00Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoverieshttps://blog.schoergendorfer.com/post/loopmoe-unifying-iterative-computation-with-mixture-of-experts-for-language-modeSecFeedde2026-08-28T07:32:31.985577+00:00LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modelinghttps://blog.schoergendorfer.com/post/do-multimodal-agents-really-benefit-from-tool-use-a-systematic-study-of-capabiliSecFeedde2026-08-28T07:32:31.957129+00:00Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gainshttps://blog.schoergendorfer.com/post/mimo-multilingual-information-retrieval-via-monolingual-objectivesSecFeedde2026-08-28T07:32:31.928917+00:00MIMO: Multilingual Information Retrieval via Monolingual Objectiveshttps://blog.schoergendorfer.com/post/pixel-wised-lesion-prediction-on-covid-19-ct-imagery-a-comparative-analysis-of-aSecFeedde2026-08-28T07:32:31.903657+00:00Pixel Wised Lesion Prediction on COVID-19 CT Imagery: A Comparative Analysis of Automated Image Segmentation Architectureshttps://blog.schoergendorfer.com/post/a-comprehensive-comparison-of-deep-learning-architectures-for-covid-19-classificSecFeedde2026-08-28T07:32:31.876904+00:00A Comprehensive Comparison of Deep Learning Architectures for COVID-19 Classification on CT & X-ray Imageryhttps://blog.schoergendorfer.com/post/gamma-global-bit-allocation-for-mixed-precision-models-under-arbitrary-budgetsSecFeedde2026-08-28T07:32:31.841485+00:00GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgetshttps://blog.schoergendorfer.com/post/hint-sd-targeted-hindsight-self-distillation-for-long-horizon-agentsSecFeedde2026-08-28T07:32:31.813846+00:00HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agentshttps://blog.schoergendorfer.com/post/no-plan-yet-human-a-reactive-robotics-model-predicts-human-planning-failures-onSecFeedde2026-08-28T07:17:51.938602+00:00No Plan, Yet Human: A Reactive Robotics Model Predicts Human Planning Failures on a Clinical Taskhttps://blog.schoergendorfer.com/post/medfabric-gold-evidence-hides-the-difficulty-of-word-level-medical-fabrication-dSecFeedde2026-08-28T07:17:51.913302+00:00MedFabric: Gold Evidence Hides the Difficulty of Word-Level Medical Fabrication Detectionhttps://blog.schoergendorfer.com/post/mambacsp-hybrid-attention-state-space-models-for-hardware-efficient-channel-statSecFeedde2026-08-28T07:17:51.854250+00:00MambaCSP: Hybrid-Attention State Space Models for Hardware-Efficient Channel State Predictionhttps://blog.schoergendorfer.com/post/momo-a-framework-for-seamless-physical-verbal-and-graphical-robot-skill-learningSecFeedde2026-08-28T07:17:51.826300+00:00MOMO: A framework for seamless physical, verbal, and graphical robot skill learning and adaptationhttps://blog.schoergendorfer.com/post/can-llms-accurately-score-medical-diagnoses-and-clinical-reasoningSecFeedde2026-08-28T07:17:51.794518+00:00Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning?https://blog.schoergendorfer.com/post/cpgrec-a-balance-oriented-framework-for-personalized-video-game-recommendations-2SecFeedde2026-08-28T07:17:51.762621+00:00CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendationshttps://blog.schoergendorfer.com/post/a-unified-conditional-flow-for-motion-generation-editing-and-intra-structural-reSecFeedde2026-08-28T07:17:51.735232+00:00A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargetinghttps://blog.schoergendorfer.com/post/grounded-token-initialization-for-new-vocabulary-in-lms-for-generative-recommendSecFeedde2026-08-28T07:17:51.705230+00:00Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendationhttps://blog.schoergendorfer.com/post/high-fidelity-face-content-recovery-via-tamper-resilient-versatile-watermarkingSecFeedde2026-08-28T07:17:51.675757+00:00High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarkinghttps://blog.schoergendorfer.com/post/how-llms-distort-our-written-languageSecFeedde2026-08-28T07:17:51.649947+00:00How LLMs Distort Our Written Languagehttps://blog.schoergendorfer.com/post/frequency-matters-fast-model-agnostic-data-curation-for-pruning-and-quantizationSecFeedde2026-08-28T07:17:51.621674+00:00Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantizationhttps://blog.schoergendorfer.com/post/a-very-big-video-reasoning-suiteSecFeedde2026-08-28T07:17:51.571280+00:00A Very Big Video Reasoning Suitehttps://blog.schoergendorfer.com/post/beyond-factual-qa-mentorship-oriented-question-answering-over-long-form-multilinSecFeedde2026-08-28T07:17:51.538405+00:00Beyond Factual QA: Mentorship-Oriented Question Answering over Long-Form Multilingual Contenthttps://blog.schoergendorfer.com/post/lora-as-oracleSecFeedde2026-08-28T07:17:51.506759+00:00LoRA as Oraclehttps://blog.schoergendorfer.com/post/subspace-alignment-for-vision-language-model-test-time-adaptationSecFeedde2026-08-28T07:17:51.476329+00:00Subspace Alignment for Vision-Language Model Test-time Adaptationhttps://blog.schoergendorfer.com/post/countervid-counterfactual-video-generation-for-mitigating-action-and-temporal-haSecFeedde2026-08-28T07:17:51.449584+00:00CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Modelshttps://blog.schoergendorfer.com/post/diagnosing-conformal-prediction-failures-under-distribution-shift-a-covid-19-casSecFeedde2026-08-28T07:17:51.421182+00:00Diagnosing Conformal Prediction Failures Under Distribution Shift: A COVID-19 Case Studyhttps://blog.schoergendorfer.com/post/multivariate-diffusion-transformer-with-decoupled-attention-for-high-fidelity-maSecFeedde2026-08-28T07:17:51.388691+00:00Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generationhttps://blog.schoergendorfer.com/post/what-the-spotless-mind-remembers-how-knowledge-entanglement-shapes-what-leaks-afSecFeedde2026-08-28T07:02:41.277549+00:00What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMshttps://blog.schoergendorfer.com/post/the-principles-of-diffusion-modelsSecFeedde2026-08-28T07:02:41.250339+00:00The Principles of Diffusion Modelshttps://blog.schoergendorfer.com/post/mentor-reinforcement-learning-via-flexible-teacher-optimized-rewards-for-tool-usSecFeedde2026-08-28T07:02:41.218648+00:00MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillationhttps://blog.schoergendorfer.com/post/llm-specific-utility-for-retrieval-augmented-generation-2SecFeedde2026-08-28T07:02:41.189872+00:00LLM-Specific Utility for Retrieval-Augmented Generationhttps://blog.schoergendorfer.com/post/mcce-a-framework-for-multi-llm-collaborative-search-in-discrete-spaces-with-simiSecFeedde2026-08-28T07:02:41.164131+00:00MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learninghttps://blog.schoergendorfer.com/post/egosurg-arbitrary-view-synthesis-for-egocentric-replay-of-operating-room-workfloSecFeedde2026-08-28T07:02:41.136846+00:00Egosurg: Arbitrary view synthesis for egocentric replay of operating room workflows from ambient camerashttps://blog.schoergendorfer.com/post/gsm8k-v-can-vision-language-models-solve-grade-school-math-word-problems-in-visuSecFeedde2026-08-28T07:02:41.108152+00:00GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contextshttps://blog.schoergendorfer.com/post/recurrence-meets-transformers-for-universal-multimodal-retrieval-2SecFeedde2026-08-28T07:02:41.080634+00:00Recurrence Meets Transformers for Universal Multimodal Retrievalhttps://blog.schoergendorfer.com/post/beyond-the-rosetta-stone-unification-forces-in-generalization-dynamicsSecFeedde2026-08-28T07:02:41.050628+00:00Beyond the Rosetta Stone: Unification Forces in Generalization Dynamicshttps://blog.schoergendorfer.com/post/toward-a-new-science-of-ai-as-cognitive-infrastructureSecFeedde2026-08-28T07:02:41.022725+00:00Toward a New Science of AI as Cognitive Infrastructurehttps://blog.schoergendorfer.com/post/airllm-diffusion-policy-based-adaptive-lora-for-remote-fine-tuning-of-llm-over-tSecFeedde2026-08-28T07:02:40.990097+00:00AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Airhttps://blog.schoergendorfer.com/post/distinct-profiles-of-run-to-run-score-reliability-and-expert-panel-alignment-acrSecFeedde2026-08-28T07:02:40.956558+00:00Distinct Profiles of Run-to-Run Score Reliability and Expert-Panel Alignment Across Four LLM Evaluators of Simulated Japanese-Language AI-to-AI Counselinghttps://blog.schoergendorfer.com/post/residual-reward-models-leveraging-prior-knowledge-for-efficient-preference-basedSecFeedde2026-08-28T07:02:40.925597+00:00Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Roboticshttps://blog.schoergendorfer.com/post/refine-poi-reinforcement-fine-tuned-large-language-models-for-next-point-of-inteSecFeedde2026-08-28T07:02:40.894622+00:00Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendationhttps://blog.schoergendorfer.com/post/from-accuracy-to-robustness-a-study-of-rule-and-model-based-verifiers-in-mathemaSecFeedde2026-08-28T07:02:40.859160+00:00From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoninghttps://blog.schoergendorfer.com/post/hybridprover-augmenting-theorem-proving-with-llm-driven-proof-synthesis-and-refiSecFeedde2026-08-28T07:02:40.822996+00:00HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinementhttps://blog.schoergendorfer.com/post/temporally-grounded-language-generation-towards-real-time-vision-language-modelsSecFeedde2026-08-28T07:02:40.790855+00:00Temporally-Grounded Language Generation: Towards Real-Time Vision-Language Modelshttps://blog.schoergendorfer.com/post/communication-styles-and-reader-preferences-of-llm-and-human-authored-covid-19-iSecFeedde2026-08-28T07:02:40.760275+00:00Communication styles and reader preferences of LLM- and human-authored COVID-19 information explanations: a case studyhttps://blog.schoergendorfer.com/post/unleashing-the-power-of-llms-in-dense-retrieval-with-query-likelihood-modeling-2SecFeedde2026-08-28T07:02:40.731553+00:00Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modelinghttps://blog.schoergendorfer.com/post/the-bs-meter-detecting-politics-and-labour-through-chatgpts-languageSecFeedde2026-08-28T07:02:40.699146+00:00The BS-meter: Detecting Politics and Labour through ChatGPT's Languagehttps://blog.schoergendorfer.com/post/collafuse-collaborative-diffusion-models-2SecFeedde2026-08-28T06:47:32.363682+00:00CollaFuse: Collaborative Diffusion Modelshttps://blog.schoergendorfer.com/post/account-consistency-from-gameplay-traces-same-player-verification-in-counter-strSecFeedde2026-08-28T06:47:32.300696+00:00Account Consistency from Gameplay Traces: Same-Player Verification in Counter-Strike 2https://blog.schoergendorfer.com/post/from-state-to-action-ooda-tool-for-reliable-multi-turn-tool-use-2SecFeedde2026-08-28T06:47:32.263885+00:00From State to Action: OODA-Tool for Reliable Multi-Turn Tool Usehttps://blog.schoergendorfer.com/post/from-inertia-to-objectivity-improving-deep-research-agents-with-noise-isolation-2SecFeedde2026-08-28T06:47:32.164846+00:00From Inertia to Objectivity: Improving Deep Research Agents with Noise Isolationhttps://blog.schoergendorfer.com/post/buried-in-textual-debt-context-pruning-with-visual-evidence-preservation-for-mll-2SecFeedde2026-08-28T06:47:32.141104+00:00Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agentshttps://blog.schoergendorfer.com/post/execrubrics-executable-tool-augmented-rubrics-for-verifiable-and-efficient-long-2SecFeedde2026-08-28T06:47:32.115654+00:00ExecRubrics: Executable Tool-Augmented Rubrics for Verifiable and Efficient Long-Form Evaluationhttps://blog.schoergendorfer.com/post/flavourbench-executable-culinary-reward-maps-for-language-model-evaluation-and-pSecFeedde2026-08-28T06:47:32.033447+00:00FlavourBench: Executable Culinary Reward Maps for Language Model Evaluation and Post-Traininghttps://blog.schoergendorfer.com/post/blast-radius-3SecFeedde2026-08-28T06:47:32.007065+00:00Blast Radiushttps://blog.schoergendorfer.com/post/niyamai-an-intent-bound-ai-agent-with-cryptographically-verifiable-guardrails-us-2SecFeedde2026-08-28T06:47:31.972255+00:00NiyamAI - An Intent-Bound AI Agent with Cryptographically Verifiable Guardrails using Zero-Knowledge Proofshttps://blog.schoergendorfer.com/post/rethinking-modality-reliability-in-multimodal-sentiment-analysis-with-incomplete-2SecFeedde2026-08-28T06:47:31.942556+00:00Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observationshttps://blog.schoergendorfer.com/post/are-the-high-weight-neurons-the-important-ones-in-image-classification-neural-ne-2SecFeedde2026-08-28T06:47:31.915683+00:00Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?https://blog.schoergendorfer.com/post/do-coding-agents-need-executable-world-models-simplification-and-verification-to-2SecFeedde2026-08-28T06:47:31.884471+00:00Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?https://blog.schoergendorfer.com/post/rethinking-the-evaluation-of-harness-evolution-for-agents-2SecFeedde2026-08-28T06:47:31.852519+00:00Rethinking the Evaluation of Harness Evolution for Agentshttps://blog.schoergendorfer.com/post/heaviside-continuity-of-rolling-coefficients-for-eliminating-epistemic-entropy-i-2SecFeedde2026-08-28T06:47:31.820662+00:00Heaviside Continuity of Rolling Coefficients for Eliminating Epistemic Entropy in Large Language Modelshttps://blog.schoergendorfer.com/post/learning-the-arts-of-search-for-automated-discoverySecFeedde2026-08-28T06:32:51.282915+00:00Learning the ARTS of Search for Automated Discoveryhttps://blog.schoergendorfer.com/post/provenanceguard-source-aware-factuality-verification-for-mcp-based-llm-agents-2SecFeedde2026-08-28T06:32:51.255731+00:00ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agentshttps://blog.schoergendorfer.com/post/touchthinker-scaling-tactile-commonsense-reasoning-to-the-open-world-with-large-2SecFeedde2026-08-28T06:32:51.227780+00:00TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representationhttps://blog.schoergendorfer.com/post/from-accuracy-to-auditability-a-survey-of-determinism-in-financial-ai-systems-2SecFeedde2026-08-28T06:32:51.198874+00:00From Accuracy to Auditability: A Survey of Determinism in Financial AI Systemshttps://blog.schoergendorfer.com/post/nomad-autonomous-exploration-and-discoverySecFeedde2026-08-28T06:32:51.167470+00:00Nomad: Autonomous Exploration and Discoveryhttps://blog.schoergendorfer.com/post/learning-to-predict-discover-and-reason-in-high-dimensional-event-sequencesSecFeedde2026-08-28T06:32:51.136112+00:00Learning to Predict, Discover, and Reason in High-Dimensional Event Sequenceshttps://blog.schoergendorfer.com/post/dianoia-diagnostic-decomposition-and-joint-optimization-for-multi-agent-reasoninSecFeedde2026-08-28T06:32:51.106498+00:00DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoninghttps://blog.schoergendorfer.com/post/beyond-linearization-attributed-table-graphs-for-table-reasoningSecFeedde2026-08-28T06:32:51.039603+00:00Beyond Linearization: Attributed Table Graphs for Table Reasoninghttps://blog.schoergendorfer.com/post/deepplanner-scaling-planning-capability-for-deep-research-agents-via-advantage-sSecFeedde2026-08-28T06:32:51.016687+00:00DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shapinghttps://blog.schoergendorfer.com/post/interaction-protocol-shapes-moral-judgment-in-multi-agent-debate-2SecFeedde2026-08-28T06:32:50.993252+00:00Interaction Protocol Shapes Moral Judgment in Multi-Agent Debatehttps://blog.schoergendorfer.com/post/do-language-models-follow-occams-razor-an-evaluation-of-parsimony-in-inductive-aSecFeedde2026-08-28T06:32:50.970595+00:00Do Language Models Follow Occam's Razor? An Evaluation of Parsimony in Inductive and Abductive Reasoninghttps://blog.schoergendorfer.com/post/pushing-the-envelope-of-llm-inference-with-ultra-low-bit-quantized-modelsSecFeedde2026-08-28T06:32:50.947462+00:00Pushing the Envelope of LLM Inference with Ultra-Low-Bit Quantized Modelshttps://blog.schoergendorfer.com/post/swe-prime-fewer-trajectories-better-performanceSecFeedde2026-08-28T06:32:50.897908+00:00SWE-Prime: Fewer Trajectories, Better Performancehttps://blog.schoergendorfer.com/post/designing-cellular-manufacturing-systems-in-the-presence-of-alternative-processSecFeedde2026-08-28T06:32:50.872490+00:00Designing Cellular Manufacturing Systems in the Presence of Alternative Process Planshttps://blog.schoergendorfer.com/post/from-static-to-dynamic-benchmarking-real-world-code-review-with-mcr-benchSecFeedde2026-08-28T06:32:50.842067+00:00From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Benchhttps://blog.schoergendorfer.com/post/redevoagent-automatic-red-teaming-agent-with-experience-driven-skill-evolutionSecFeedde2026-08-28T06:32:50.816893+00:00RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolutionhttps://blog.schoergendorfer.com/post/beyond-f1-evaluating-coverage-and-failure-recovery-in-ai-model-security-scannersSecFeedde2026-08-28T06:32:50.791782+00:00Beyond F1: Evaluating Coverage and Failure Recovery in AI Model Security Scannershttps://blog.schoergendorfer.com/post/persona-execution-separation-an-architecture-pattern-for-evolving-llm-agents-undSecFeedde2026-08-28T06:32:50.764688+00:00Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audithttps://blog.schoergendorfer.com/post/clap-cross-embodiment-video-world-models-are-zero-shot-physical-simulatorsSecFeedde2026-08-28T06:32:50.740138+00:00CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulatorshttps://blog.schoergendorfer.com/post/how-language-models-organize-and-structure-moral-knowledgeSecFeedde2026-08-28T06:17:41.535112+00:00How Language Models Organize and Structure Moral Knowledgehttps://blog.schoergendorfer.com/post/levjepa-efficient-scalable-video-pretraining-without-the-heuristicsSecFeedde2026-08-28T06:17:41.487378+00:00LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristicshttps://blog.schoergendorfer.com/post/property-specific-recoverability-from-contact-ppg-to-camera-rppg-under-heterogenSecFeedde2026-08-28T06:17:41.462338+00:00Property-Specific Recoverability from Contact PPG to Camera rPPG under Heterogeneous Observation Conditionshttps://blog.schoergendorfer.com/post/successive-capacity-growth-task-complexity-driven-width-and-depth-expansion-forSecFeedde2026-08-28T06:17:41.437006+00:00Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Modelshttps://blog.schoergendorfer.com/post/knockgsinteraction-grounded-calibrationof-physical-gaussian-representationsSecFeedde2026-08-28T06:17:41.412233+00:00KnockGS:interaction-Grounded Calibrationof Physical Gaussian Representationshttps://blog.schoergendorfer.com/post/rcmn-understanding-misleadingness-in-influential-public-discourseSecFeedde2026-08-28T06:17:41.365051+00:00RCMN: Understanding Misleadingness in Influential Public Discoursehttps://blog.schoergendorfer.com/post/pawbench-how-far-are-we-from-probabilistically-aligned-world-modelingSecFeedde2026-08-28T06:17:41.340788+00:00PAWBench: How Far Are We from Probabilistically Aligned World Modeling?https://blog.schoergendorfer.com/post/difference-in-differences-on-a-censored-rating-scale-can-manufacture-an-effect-eSecFeedde2026-08-28T06:17:41.313049+00:00Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audithttps://blog.schoergendorfer.com/post/tadp-task-aware-deformable-prediction-for-single-stage-3d-object-detectionSecFeedde2026-08-28T06:17:41.283355+00:00TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detectionhttps://blog.schoergendorfer.com/post/compositional-online-learning-for-semantic-data-processing-systemsSecFeedde2026-08-28T06:17:41.258589+00:00Compositional Online Learning for Semantic Data Processing Systemshttps://blog.schoergendorfer.com/post/step-state-aware-task-estimation-and-planning-with-multi-modal-llms-for-human-roSecFeedde2026-08-28T06:17:41.235273+00:00STEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot Collaborationhttps://blog.schoergendorfer.com/post/pace-a-unified-condense-and-extract-paradigm-for-fast-vlm-inferenceSecFeedde2026-08-28T06:17:41.210894+00:00PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inferencehttps://blog.schoergendorfer.com/post/when-text-misleads-inconsistent-aware-reasoning-for-audio-grounded-dialogueSecFeedde2026-08-28T06:17:41.188808+00:00When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialoguehttps://blog.schoergendorfer.com/post/llms-in-digital-eda-a-perspective-on-shifting-roles-from-generation-to-orchestraSecFeedde2026-08-28T06:17:41.167185+00:00LLMs in Digital EDA: A perspective on shifting roles from Generation to Orchestrationhttps://blog.schoergendorfer.com/post/antshapes-benchmarking-datasets-for-event-based-neuromorphic-object-classificatiSecFeedde2026-08-28T06:17:41.143465+00:00ANTShapes Benchmarking Datasets for Event-Based Neuromorphic Object Classificationhttps://blog.schoergendorfer.com/post/safety-does-not-compose-non-decaying-loop-state-for-autonomous-llm-agentsSecFeedde2026-08-28T06:17:41.115712+00:00Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agentshttps://blog.schoergendorfer.com/post/active-sensing-to-characterize-the-heterogeneity-of-plant-stressSecFeedde2026-08-28T06:17:41.069209+00:00Active sensing to characterize the heterogeneity of plant stresshttps://blog.schoergendorfer.com/post/emotional-preferences-as-goal-priority-regulationSecFeedde2026-08-28T06:03:40.405904+00:00Emotional Preferences as Goal-Priority Regulationhttps://blog.schoergendorfer.com/post/performance-foundations-of-parallel-distributed-reasoning-language-modelsSecFeedde2026-08-28T06:03:40.376286+00:00Performance Foundations of Parallel & Distributed Reasoning Language Modelshttps://blog.schoergendorfer.com/post/beyond-classification-task-dependent-learnability-under-privacy-motivated-imageSecFeedde2026-08-28T06:03:40.342010+00:00Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformationshttps://blog.schoergendorfer.com/post/multi-person-human-motion-forecasting-in-complex-scenesSecFeedde2026-08-28T06:03:40.309577+00:00Multi-Person Human Motion Forecasting in Complex Sceneshttps://blog.schoergendorfer.com/post/fault-bench-towards-benchmarking-network-troubleshooting-llm-agents-under-unreliSecFeedde2026-08-28T06:03:40.274066+00:00FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Ticketshttps://blog.schoergendorfer.com/post/per-view-gaussian-predictions-enable-training-free-distractor-filtering-in-feedSecFeedde2026-08-28T06:03:40.240023+00:00Per-View Gaussian Predictions Enable Training-Free Distractor Filtering in Feed-Forward 3DGShttps://blog.schoergendorfer.com/post/when-memory-takes-gradients-collaborative-vector-memory-for-agentic-recommenderSecFeedde2026-08-28T06:03:40.175405+00:00When Memory Takes Gradients: Collaborative Vector Memory for Agentic Recommender Systemshttps://blog.schoergendorfer.com/post/plcbench-can-autonomous-llm-agents-turn-plc-access-into-sustained-physical-impacSecFeedde2026-08-28T06:03:40.141041+00:00PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact?https://blog.schoergendorfer.com/post/from-reasoning-to-pixels-grounded-medical-multimodal-llms-for-vqa-and-segmentatiSecFeedde2026-08-28T06:03:40.089762+00:00From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentationhttps://blog.schoergendorfer.com/post/reinforcement-learning-based-control-of-cav-platoon-joining-maneuvers-in-mixed-tSecFeedde2026-08-28T06:03:40.048768+00:00Reinforcement Learning-Based Control of CAV Platoon Joining Maneuvers in Mixed Traffichttps://blog.schoergendorfer.com/post/medfg-vqa-low-frequency-memory-and-graph-attention-for-lightweight-medical-vqaSecFeedde2026-08-28T06:03:40.021856+00:00MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQAhttps://blog.schoergendorfer.com/post/evaluating-confidence-gated-retrieval-with-matched-trajectory-replaySecFeedde2026-08-28T06:03:39.987441+00:00Evaluating Confidence-Gated Retrieval with Matched Trajectory Replayhttps://blog.schoergendorfer.com/post/behavior2trip-towards-personalized-travel-planning-via-user-behavior-trajectorySecFeedde2026-08-28T06:03:39.960631+00:00Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectoryhttps://blog.schoergendorfer.com/post/beyond-execution-auditing-experimental-fidelity-in-llm-driven-scientific-researcSecFeedde2026-08-28T06:03:39.931560+00:00Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Researchhttps://blog.schoergendorfer.com/post/faultlens-learning-compact-behavioral-test-suites-for-generated-operational-progSecFeedde2026-08-28T06:03:39.900664+00:00FaultLens: Learning Compact Behavioral Test Suites for Generated Operational Programshttps://blog.schoergendorfer.com/post/daydreaming-stealing-hidden-agent-skills-through-black-box-task-interactionSecFeedde2026-08-28T06:03:39.871053+00:00Daydreaming: Stealing Hidden Agent Skills through Black-Box Task Interactionhttps://blog.schoergendorfer.com/post/livevvt-high-fidelity-video-virtual-try-on-in-real-timeSecFeedde2026-08-28T06:03:39.822850+00:00LiveVVT: High-Fidelity Video Virtual Try-On in Real Timehttps://blog.schoergendorfer.com/post/aescanvas-a-large-scale-dataset-and-benchmark-for-aesthetic-critique-and-contextSecFeedde2026-08-28T05:47:28.073164+00:00AesCanvas: A Large-Scale Dataset and Benchmark for Aesthetic Critique and Contextual Suitabilityhttps://blog.schoergendorfer.com/post/focus-repair-mitigating-text-degeneration-via-token-level-guidance-for-pruned-laSecFeedde2026-08-28T05:47:28.044951+00:00FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance for Pruned Large Language Modelshttps://blog.schoergendorfer.com/post/do-llms-understand-personality-rethinking-persona-fidelity-evaluation-through-stSecFeedde2026-08-28T05:47:28.012910+00:00Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inferencehttps://blog.schoergendorfer.com/post/pailitaogr-latent-think-with-images-for-generative-image-retrievalSecFeedde2026-08-28T05:47:27.980047+00:00PailitaoGR: Latent Think-with-Images for Generative Image Retrievalhttps://blog.schoergendorfer.com/post/risks-and-controls-for-multi-agent-systems-an-analytical-framework-for-deploymenSecFeedde2026-08-28T05:47:27.928302+00:00Risks and Controls for Multi-Agent Systems: an analytical framework for deployment of AI agents across organisational boundarieshttps://blog.schoergendorfer.com/post/j-zero-unified-challenger-solver-judge-co-evolution-from-zero-dataSecFeedde2026-08-28T05:47:27.898949+00:00J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Datahttps://blog.schoergendorfer.com/post/physics-informed-stochastic-configuration-machine-a-backpropagation-free-neuralSecFeedde2026-08-28T05:47:27.868990+00:00Physics-Informed Stochastic Configuration Machine: A Backpropagation-Free Neural Network with Fast Training for Nonlinear Differential Equationshttps://blog.schoergendorfer.com/post/rtnav-towards-real-time-zero-shot-object-navigationSecFeedde2026-08-28T05:47:27.840735+00:00RTNav: Towards Real-Time Zero-Shot Object Navigationhttps://blog.schoergendorfer.com/post/zero-shot-self-orchestration-with-ledger-based-control-for-improved-llm-coding-pSecFeedde2026-08-28T05:47:27.813845+00:00Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performancehttps://blog.schoergendorfer.com/post/diff-mining-logit-differences-reveal-finetuning-objectivesSecFeedde2026-08-28T05:47:27.786983+00:00Diff Mining: Logit Differences Reveal Finetuning Objectiveshttps://blog.schoergendorfer.com/post/speechgym-an-audio-native-gym-for-training-voice-agents-via-reinforcement-learniSecFeedde2026-08-28T05:47:27.760746+00:00SpeechGym: An Audio-Native Gym for Training Voice Agents via Reinforcement Learninghttps://blog.schoergendorfer.com/post/the-latent-diagnostic-taxonomy-a-framework-for-constructing-classifiers-and-diagSecFeedde2026-08-28T05:47:27.729795+00:00The Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection Detectionhttps://blog.schoergendorfer.com/post/redwood-a-frontier-ai-accelerator-designed-verified-and-deployed-from-scratch-inSecFeedde2026-08-28T05:47:27.703462+00:00Redwood: A Frontier AI Accelerator Designed, Verified, and Deployed from Scratch in 2 Weeks by AIhttps://blog.schoergendorfer.com/post/why-rags-hallucinate-penalty-aware-evaluation-of-retrieval-augmented-generationSecFeedde2026-08-28T05:47:27.617576+00:00Why RAGs Hallucinate: Penalty-Aware Evaluation of Retrieval-Augmented Generation Systems with Knowledge-Gap Canarieshttps://blog.schoergendorfer.com/post/cg4ai-a-column-generation-framework-for-training-ai-models-under-constraintsSecFeedde2026-08-28T05:47:27.592549+00:00CG4AI: A Column Generation Framework for Training AI Models Under Constraintshttps://blog.schoergendorfer.com/post/knowledge-verified-emergent-deception-in-llm-agents-under-conflicting-incentivesSecFeedde2026-08-28T05:47:27.563186+00:00Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentiveshttps://blog.schoergendorfer.com/post/decay-region-group-delay-as-a-forensic-cue-for-ai-generated-impulsive-soundsSecFeedde2026-08-28T05:47:27.532221+00:00Decay-Region Group Delay as a Forensic Cue for AI-Generated Impulsive Soundshttps://blog.schoergendorfer.com/post/how-unlikely-is-unlikely-assessing-verbal-probability-perception-across-large-laSecFeedde2026-08-28T05:32:39.847043+00:00How Unlikely Is "Unlikely"? Assessing Verbal Probability Perception Across Large Language Modelshttps://blog.schoergendorfer.com/post/modality-maturity-index-a-benchmark-for-assessing-multimodal-capabilities-of-omnSecFeedde2026-08-28T05:32:39.824474+00:00Modality Maturity Index: A benchmark for assessing multimodal capabilities of omni modelshttps://blog.schoergendorfer.com/post/memtoc-benchmarking-memory-tool-conflict-resolution-in-large-language-modelsSecFeedde2026-08-28T05:32:39.799938+00:00MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Modelshttps://blog.schoergendorfer.com/post/on-scope-classification-and-current-knowledge-editing-benchmarks-a-negative-resuSecFeedde2026-08-28T05:32:39.771169+00:00On Scope Classification and Current Knowledge-Editing Benchmarks: A Negative Result, with INLAY as a Gradient-Free Case Studyhttps://blog.schoergendorfer.com/post/how-do-llm-agents-actually-get-the-flag-trace-level-provenance-for-agentic-offenSecFeedde2026-08-28T05:32:39.740008+00:00How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluationhttps://blog.schoergendorfer.com/post/neuronfuzz-safety-neuron-guided-fuzzing-for-llm-safety-evaluationSecFeedde2026-08-28T05:32:39.712901+00:00NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluationhttps://blog.schoergendorfer.com/post/adepts-bench-measuring-the-trustworthiness-of-computer-use-agents-across-devicesSecFeedde2026-08-28T05:32:39.665310+00:00ADeptS-Bench: Measuring the Trustworthiness of Computer Use Agents Across Deviceshttps://blog.schoergendorfer.com/post/fairness-invariants-a-relational-approach-to-explaining-and-mitigating-fairnessSecFeedde2026-08-28T05:32:39.639387+00:00Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugshttps://blog.schoergendorfer.com/post/comparing-chunking-and-embedding-strategies-for-turkish-rag-systemsSecFeedde2026-08-28T05:32:39.596430+00:00Comparing Chunking and Embedding Strategies for Turkish RAG Systemshttps://blog.schoergendorfer.com/post/investigating-the-influence-of-prompt-and-response-languages-on-llm-content-geneSecFeedde2026-08-28T05:32:39.569755+00:00Investigating the Influence of Prompt and Response Languages on LLM Content Generationhttps://blog.schoergendorfer.com/post/when-the-canonical-completion-is-wrong-formalizing-and-measuring-the-jump-in-larSecFeedde2026-08-28T05:32:39.544864+00:00When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in Large Language Modelshttps://blog.schoergendorfer.com/post/paceshop-evaluating-personalized-actionable-compositional-and-evidence-groundedSecFeedde2026-08-28T05:32:39.517520+00:00PACEShop: Evaluating Personalized, Actionable, Compositional, and Evidence-grounded Shopping Assistantshttps://blog.schoergendorfer.com/post/a-multi-framework-comparison-of-outline-stages-in-long-form-generation-with-llmsSecFeedde2026-08-28T05:32:39.490169+00:00A Multi-Framework Comparison of Outline Stages in Long-Form Generation with LLMshttps://blog.schoergendorfer.com/post/lost-in-compression-a-controlled-cross-lingual-audit-of-extractive-prompt-compreSecFeedde2026-08-28T05:32:39.434342+00:00Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressorshttps://blog.schoergendorfer.com/post/drl-a-deterministic-relational-middleware-layer-for-transaction-safe-enterpriseSecFeedde2026-08-28T05:32:39.383089+00:00DRL: A Deterministic Relational Middleware Layer for Transaction-Safe Enterprise NL2SQL Under Schema-Graph Scalinghttps://blog.schoergendorfer.com/post/hallucinations-in-llms-a-lifecycle-based-survey-of-causes-detection-mitigation-aSecFeedde2026-08-28T05:32:39.351503+00:00Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Preventionhttps://blog.schoergendorfer.com/post/using-poly-encoders-for-computationally-efficient-automated-creativity-assessmenSecFeedde2026-08-28T05:17:34.674812+00:00Using Poly-Encoders for Computationally Efficient Automated Creativity Assessmenthttps://blog.schoergendorfer.com/post/from-sound-to-symptom-real-time-respiratory-signal-understanding-for-conversatioSecFeedde2026-08-28T05:17:34.650436+00:00From Sound to Symptom: Real-Time Respiratory Signal Understanding for Conversational Healthcare Agentshttps://blog.schoergendorfer.com/post/self-generated-text-recognition-quality-heuristics-cross-task-transfer-and-downsSecFeedde2026-08-28T05:17:34.601318+00:00Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluationhttps://blog.schoergendorfer.com/post/artificial-intelligence-models-can-predict-and-collaboratively-modulate-human-meSecFeedde2026-08-28T05:17:34.533105+00:00Artificial Intelligence Models Can Predict and Collaboratively Modulate Human Memory Searchhttps://blog.schoergendorfer.com/post/position-is-all-you-need-a-free-lunch-token-compression-strategy-for-mllm-basedSecFeedde2026-08-28T05:17:34.510233+00:00Position Is All You Need: A Free Lunch Token Compression Strategy for MLLM-based Referring Expression Segmentationhttps://blog.schoergendorfer.com/post/beyond-accuracy-a-qualitative-analysis-of-vision-language-models-for-hate-speechSecFeedde2026-08-28T05:17:34.484629+00:00Beyond Accuracy: A Qualitative Analysis of Vision-Language Models for Hate Speech Detection in Memeshttps://blog.schoergendorfer.com/post/syntax-vs-semantics-how-transformers-learn-deep-dependenciesSecFeedde2026-08-28T05:17:34.456865+00:00Syntax vs. Semantics: How Transformers Learn Deep Dependencieshttps://blog.schoergendorfer.com/post/firstpass-a-multi-domain-multi-round-peer-review-dataset-grounded-in-real-editorSecFeedde2026-08-28T05:17:34.427065+00:00FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomeshttps://blog.schoergendorfer.com/post/from-sql-to-knowledge-graphs-an-llm-driven-multi-agent-approach-with-data-schemaSecFeedde2026-08-28T05:17:34.397197+00:00From SQL to Knowledge Graphs: An LLM-Driven Multi-Agent Approach with Data Schema Improvementhttps://blog.schoergendorfer.com/post/exploring-the-role-of-llms-in-hpc-programming-a-surveySecFeedde2026-08-28T05:17:34.342930+00:00Exploring the Role of LLMs in HPC Programming: A Surveyhttps://blog.schoergendorfer.com/post/wikiskill-compiling-agent-experience-into-persistent-knowledge-for-skill-evolutiSecFeedde2026-08-28T05:17:34.317435+00:00WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolutionhttps://blog.schoergendorfer.com/post/mechanistic-reaction-prediction-via-discrete-flow-matching-on-graph-structured-eSecFeedde2026-08-28T05:17:34.285494+00:00Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupationhttps://blog.schoergendorfer.com/post/learning-a-continuous-sepsis-severity-score-without-hour-by-hour-supervision-a-tSecFeedde2026-08-28T05:17:34.258916+00:00Learning a Continuous Sepsis Severity Score Without Hour-by-Hour Supervision: A Two-Site Retrospective Studyhttps://blog.schoergendorfer.com/post/sophistication-in-genai-use-field-evidence-from-a-large-firmSecFeedde2026-08-28T05:17:34.203943+00:00Sophistication in GenAI Use: Field Evidence from a Large Firmhttps://blog.schoergendorfer.com/post/llms-can-design-near-optimal-or-algorithmsSecFeedde2026-08-28T05:02:31.814191+00:00LLMs Can Design Near-Optimal OR Algorithmshttps://blog.schoergendorfer.com/post/braillebench-investigating-multi-criteria-braille-comprehension-in-large-languagSecFeedde2026-08-28T05:02:31.788982+00:00BrailleBench: Investigating Multi-Criteria Braille Comprehension in Large Language Modelshttps://blog.schoergendorfer.com/post/naive-prompt-optimization-rethinking-the-need-for-complex-prompt-searchSecFeedde2026-08-28T05:02:31.759364+00:00Naive Prompt Optimization: Rethinking the Need for Complex Prompt Searchhttps://blog.schoergendorfer.com/post/what-makes-good-agentic-data-an-ace-lens-on-data-generation-for-llm-agentsSecFeedde2026-08-28T05:02:31.723644+00:00What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agentshttps://blog.schoergendorfer.com/post/calibrated-enough-to-know-not-calibrated-to-act-fabricated-evidence-makes-llm-agSecFeedde2026-08-28T05:02:31.691950+00:00Calibrated Enough to Know, Not Calibrated to Act: Fabricated Evidence Makes LLM Agents Commit to the Unknowablehttps://blog.schoergendorfer.com/post/thomson-continual-learning-of-frontier-models-for-sovereignaiSecFeedde2026-08-28T05:02:31.632922+00:00Thomson: Continual Learning of Frontier Models for SovereignAIhttps://blog.schoergendorfer.com/post/when-tool-outputs-become-commands-separating-action-induction-from-runtime-authoSecFeedde2026-08-28T05:02:31.600708+00:00When Tool Outputs Become Commands: Separating Action Induction from Runtime Authorization in Tool-Augmented LLM Agentshttps://blog.schoergendorfer.com/post/feature-transformation-enhanced-jacobi-polynomial-graph-filtering-for-graph-anomSecFeedde2026-08-28T05:02:31.573895+00:00Feature Transformation Enhanced Jacobi Polynomial Graph Filtering for Graph Anomaly Detectionhttps://blog.schoergendorfer.com/post/grain-bridging-name-and-narrative-shifts-in-real-world-graph-reasoning-through-iSecFeedde2026-08-28T05:02:31.540576+00:00GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RLhttps://blog.schoergendorfer.com/post/transmeme-a-multi-agent-framework-for-cross-cultural-meme-transcreationSecFeedde2026-08-28T05:02:31.503524+00:00TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreationhttps://blog.schoergendorfer.com/post/laaf-a-layered-accountability-architecture-framework-for-llm-applicationsSecFeedde2026-08-28T05:02:31.472110+00:00LAAF: A Layered Accountability Architecture Framework for LLM Applicationshttps://blog.schoergendorfer.com/post/pro-team-at-llms4ol-2026-tasks-flagship-and-reuse-retrieval-augmented-generationSecFeedde2026-08-28T05:02:31.436498+00:00pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learninghttps://blog.schoergendorfer.com/post/a-contract-centered-architecture-for-scalable-and-manageable-agentic-runtimesSecFeedde2026-08-28T05:02:31.402353+00:00A Contract-Centered Architecture for Scalable and Manageable Agentic Runtimeshttps://blog.schoergendorfer.com/post/omni-interactive-universal-embedderSecFeedde2026-08-28T05:02:31.372493+00:00Omni-Interactive Universal Embedderhttps://blog.schoergendorfer.com/post/asil-replacing-screenshot-and-click-with-structured-state-and-semantic-actionsSecFeedde2026-08-28T05:02:31.341131+00:00ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actionshttps://blog.schoergendorfer.com/post/a-multi-modal-ai-framework-for-real-time-queue-prediction-management-and-optimisSecFeedde2026-08-28T05:02:31.307700+00:00A Multi-Modal AI Framework for Real-Time Queue Prediction, Management and Optimisation in Intelligent Border Control Systemshttps://blog.schoergendorfer.com/post/dsa-evidence-aware-llm-agent-orchestration-for-multi-market-stock-researchSecFeedde2026-08-28T05:02:31.252114+00:00DSA: Evidence-Aware LLM-Agent Orchestration for Multi-Market Stock Researchhttps://blog.schoergendorfer.com/post/graphmemix-query-aware-evidence-forests-for-long-term-multimodal-agent-memorySecFeedde2026-08-28T05:02:31.218059+00:00GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memoryhttps://blog.schoergendorfer.com/post/from-atomic-to-agentic-towards-interpretable-evaluation-of-llms-agentic-mathematSecFeedde2026-08-28T04:47:46.901241+00:00From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilitieshttps://blog.schoergendorfer.com/post/a-table-is-worth-64-tokens-pixel-level-compression-for-multi-table-document-quesSecFeedde2026-08-28T04:47:46.869315+00:00A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answeringhttps://blog.schoergendorfer.com/post/counterfactual-bias-testing-for-application-tracking-systemSecFeedde2026-08-28T04:47:46.839743+00:00Counterfactual Bias Testing for Application Tracking Systemhttps://blog.schoergendorfer.com/post/ai-agents-in-algorithmic-electricity-markets-on-the-emergence-of-tacit-collusionSecFeedde2026-08-28T04:47:46.808759+00:00AI agents in Algorithmic Electricity Markets: On the Emergence of Tacit Collusionhttps://blog.schoergendorfer.com/post/evaluating-human-and-llm-screening-workflows-in-a-conceptually-complex-scoping-rSecFeedde2026-08-28T04:47:46.725100+00:00Evaluating human and LLM screening workflows in a conceptually complex scoping review: Recall--workload trade-offs and run-to-run consistencyhttps://blog.schoergendorfer.com/post/bekchiai-measuring-observing-and-controlling-llm-agents-in-one-clickSecFeedde2026-08-28T04:47:46.692324+00:00BekchiAI: Measuring, Observing, and Controlling LLM Agents in One Clickhttps://blog.schoergendorfer.com/post/decoupling-planning-and-control-for-instructable-agentsSecFeedde2026-08-28T04:47:46.596265+00:00Decoupling Planning and Control for Instructable Agentshttps://blog.schoergendorfer.com/post/categorizer-automata-for-discounted-sum-payoffsSecFeedde2026-08-28T04:47:46.561159+00:00Categorizer Automata for Discounted-Sum Payoffshttps://blog.schoergendorfer.com/post/ai-control-scientist-llm-driven-agentic-system-for-automated-control-designSecFeedde2026-08-28T04:47:46.532518+00:00AI Control Scientist: LLM-driven Agentic System for Automated Control Designhttps://blog.schoergendorfer.com/post/agentfold-closed-loop-agentic-search-for-protein-folding-model-designSecFeedde2026-08-28T04:47:46.456782+00:00AgentFold: Closed-Loop Agentic Search for Protein Folding Model Designhttps://blog.schoergendorfer.com/post/graph-guided-selective-unlearning-for-language-models-controlling-support-routesSecFeedde2026-08-28T04:47:46.426621+00:00Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seedshttps://blog.schoergendorfer.com/post/knowing-when-not-to-reuse-conditional-experience-transfer-in-autonomous-llm-postSecFeedde2026-08-28T04:47:46.392692+00:00Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Traininghttps://blog.schoergendorfer.com/post/style-as-a-confound-false-positives-in-ai-detection-of-non-native-academic-writiSecFeedde2026-08-28T04:47:46.363709+00:00Style as a Confound: False Positives in AI Detection of Non-Native Academic Writinghttps://blog.schoergendorfer.com/post/accelerating-scientific-research-with-gemini-in-the-real-worldSecFeedde2026-08-28T04:47:46.331181+00:00Accelerating Scientific Research with Gemini in the Real-Worldhttps://blog.schoergendorfer.com/post/five-primitives-for-governing-autonomous-ai-agents-at-runtimeSecFeedde2026-08-28T04:32:29.254444+00:00Five Primitives for Governing Autonomous AI Agents at Runtimehttps://blog.schoergendorfer.com/post/relational-over-regularization-graph-based-ai-generated-text-detection-via-senteSecFeedde2026-08-28T04:32:29.223357+00:00Relational Over-Regularization: Graph-Based AI-Generated Text Detection via Sentence Transition Deviationhttps://blog.schoergendorfer.com/post/sigma-structured-noise-effect-aware-grouped-multi-agent-aggregationSecFeedde2026-08-28T04:32:29.184148+00:00SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregationhttps://blog.schoergendorfer.com/post/agentjudgebench-a-multi-difficulty-benchmark-for-evaluating-llm-judges-on-agentiSecFeedde2026-08-28T04:32:29.150062+00:00AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Callinghttps://blog.schoergendorfer.com/post/dumatebench-evaluating-autonomous-agents-in-complex-real-world-workflowsSecFeedde2026-08-28T04:32:29.116764+00:00DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflowshttps://blog.schoergendorfer.com/post/multi2av-safety-benchmarking-safety-in-multimodal-to-audio-video-generationSecFeedde2026-08-28T04:32:29.089998+00:00Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generationhttps://blog.schoergendorfer.com/post/pilot-in-the-loop-live-self-improvement-for-long-horizon-agentsSecFeedde2026-08-28T04:32:29.057942+00:00PILOT in the Loop: Live Self-Improvement for Long-Horizon Agentshttps://blog.schoergendorfer.com/post/dont-overthink-dont-underthink-toward-adaptive-reasoning-in-agentic-aiSecFeedde2026-08-28T04:32:29.029536+00:00Don't Overthink, Don't Underthink: Toward Adaptive Reasoning in Agentic AIhttps://blog.schoergendorfer.com/post/fine-tuning-of-transformer-models-with-framesSecFeedde2026-08-28T04:32:28.998605+00:00Fine-Tuning of Transformer models with Frameshttps://blog.schoergendorfer.com/post/proofevolve-neuro-symbolic-evolution-for-formal-automated-theorem-provingSecFeedde2026-08-28T04:32:28.971671+00:00ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Provinghttps://blog.schoergendorfer.com/post/faithsieve-fine-grained-evaluation-of-math-proofs-with-faithful-formal-evidenceSecFeedde2026-08-28T04:32:28.940425+00:00FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidencehttps://blog.schoergendorfer.com/post/approved-too-late-verdict-staleness-in-llm-guarded-self-adaptive-systemsSecFeedde2026-08-28T04:32:28.914283+00:00Approved Too Late: Verdict Staleness in LLM-Guarded Self-Adaptive Systemshttps://blog.schoergendorfer.com/post/assessing-mentalization-in-humans-and-large-language-modelsSecFeedde2026-08-28T04:32:28.888425+00:00Assessing mentalization in humans and large language modelshttps://blog.schoergendorfer.com/post/65-of-the-neuro-symbolic-literature-can-be-reproduced-from-its-published-artifacSecFeedde2026-08-28T04:32:28.834630+00:006.5% of the Neuro-Symbolic Literature Can Be Reproduced from Its Published Artifacts, a Six-Stage Audit Framework and First Instantiationhttps://blog.schoergendorfer.com/post/the-reasoning-tax-token-economics-of-llm-reasoning-across-task-types-and-deploymSecFeedde2026-08-28T04:32:28.804878+00:00The Reasoning Tax: Token Economics of LLM Reasoning Across Task Types and Deployment Contextshttps://blog.schoergendorfer.com/post/agent-mesh-reliability-primitives-for-non-idempotent-agent-delegation-identity-aSecFeedde2026-08-28T04:32:28.748583+00:00Agent Mesh: Reliability Primitives for Non-Idempotent Agent Delegation - Identity Adequacy and Evidence Adequacyhttps://blog.schoergendorfer.com/post/same-model-different-harness-different-coding-agent-resultsSecFeedde2026-08-28T04:32:28.716589+00:00Same Model, Different Harness: Different Coding-Agent Resultshttps://blog.schoergendorfer.com/post/gamewam-a-world-action-model-for-video-gamesSecFeedde2026-08-28T04:32:28.672142+00:00GameWAM: A World Action Model for Video Gameshttps://blog.schoergendorfer.com/post/benchmarking-ai-agents-for-hardware-design-automation-via-mcp-tool-callingSecFeedde2026-08-28T04:17:30.648029+00:00Benchmarking AI Agents for Hardware Design Automation via MCP Tool Callinghttps://blog.schoergendorfer.com/post/agentic-ai-for-operating-scientific-instruments-for-nanoscale-characterizationSecFeedde2026-08-28T04:17:30.615919+00:00Agentic AI for operating scientific instruments for nanoscale characterizationhttps://blog.schoergendorfer.com/post/affectomni-rl-verifiable-people-centric-grounded-affective-reasoning-for-socialSecFeedde2026-08-28T04:17:30.579752+00:00AffectOmni: RL-Verifiable People-Centric Grounded Affective Reasoning for Social and Art-Related Sceneshttps://blog.schoergendorfer.com/post/predicting-consequences-and-reinforcing-navigation-policies-with-latent-world-moSecFeedde2026-08-28T04:17:30.520472+00:00Predicting Consequences and Reinforcing Navigation Policies with Latent World Modelshttps://blog.schoergendorfer.com/post/invocation-level-reliability-of-tool-using-agentsSecFeedde2026-08-28T04:17:30.487295+00:00Invocation-Level Reliability of Tool-Using Agentshttps://blog.schoergendorfer.com/post/is-your-neighborhood-safe-place-based-stigma-in-large-language-models-urban-safeSecFeedde2026-08-28T04:17:30.452879+00:00Is Your Neighborhood Safe? Place-based Stigma in Large Language Models' Urban Safety Judgmentshttps://blog.schoergendorfer.com/post/can-you-say-this-for-me-speaking-up-by-proxy-in-co-located-discussionSecFeedde2026-08-28T04:17:30.423234+00:00Can You Say This for Me? Speaking Up by Proxy in Co-Located Discussionhttps://blog.schoergendorfer.com/post/tutortrace-a-dataset-and-taxonomy-for-classifying-learner-behavioral-states-duriSecFeedde2026-08-28T04:17:30.393723+00:00TutorTrace: A Dataset and Taxonomy for Classifying Learner Behavioral States during AI-Assisted Programming Educationhttps://blog.schoergendorfer.com/post/why-did-my-robot-just-change-personality-prompting-guidelines-for-a-grounded-robSecFeedde2026-08-28T04:17:30.367111+00:00Why did My Robot Just Change Personality? Prompting Guidelines for a Grounded Robot Persona in LLM-Based HRIhttps://blog.schoergendorfer.com/post/ai-revealed-preferencesSecFeedde2026-08-28T04:17:30.336441+00:00AI Revealed Preferenceshttps://blog.schoergendorfer.com/post/knowledge-cards-structured-knowledge-for-ai-systemsSecFeedde2026-08-28T04:17:30.306796+00:00Knowledge Cards: Structured Knowledge for AI Systemshttps://blog.schoergendorfer.com/post/refusal-is-not-robustness-auditing-confident-fabrication-in-large-language-modelSecFeedde2026-08-28T04:17:30.273874+00:00Refusal Is Not Robustness: Auditing Confident Fabrication in Large Language Models on a Provably Uninformative Clinical Pain Speech Transcripthttps://blog.schoergendorfer.com/post/a-task-centric-ontology-and-deterministic-domain-rules-as-a-verifiable-core-forSecFeedde2026-08-28T04:17:30.242766+00:00A Task-Centric Ontology and Deterministic Domain Rules as a Verifiable Core for AI-Assisted Chemistry Problem Solvinghttps://blog.schoergendorfer.com/post/a-safety-gated-multimodal-ai-backend-for-mental-health-support-hierarchical-statSecFeedde2026-08-28T04:17:30.213621+00:00A Safety-Gated Multimodal AI Backend for Mental-Health Support: Hierarchical State Representation, Conservative Risk Fusion, and Controlled Generation in Anianhttps://blog.schoergendorfer.com/post/saref-based-ontology-for-distributed-ai-workflows-across-the-edge-fog-cloud-contSecFeedde2026-08-28T04:17:30.186264+00:00SAREF-based Ontology for Distributed AI Workflows across the Edge-Fog-Cloud Continuumhttps://blog.schoergendorfer.com/post/ground-reducing-hallucinations-in-llm-based-enterprise-analytics-through-governeSecFeedde2026-08-28T04:17:30.157727+00:00GROUND: Reducing Hallucinations in LLM-Based Enterprise Analytics Through Governed Semantic Definitionshttps://blog.schoergendorfer.com/post/selection-bias-correction-in-retail-intelligenceSecFeedde2026-08-28T04:17:30.129827+00:00Selection Bias Correction in Retail Intelligencehttps://blog.schoergendorfer.com/post/eeg-to-report-an-annotation-and-feature-text-framework-for-training-language-modSecFeedde2026-08-28T04:17:30.100404+00:00EEG-to-Report: An Annotation and Feature-Text Framework for Training Language Models on Clinical EEGhttps://blog.schoergendorfer.com/post/explainable-artificial-intelligence-for-customer-churn-prediction-in-telecommuniSecFeedde2026-08-28T04:17:30.065824+00:00Explainable Artificial Intelligence for Customer Churn Prediction in Telecommunications: A Framework for CRM Integrationhttps://blog.schoergendorfer.com/post/leveraging-large-language-models-for-systematic-literature-review-of-disease-sprSecFeedde2026-08-28T04:02:27.847671+00:00Leveraging Large Language Models for Systematic Literature Review of Disease Spread Modelshttps://blog.schoergendorfer.com/post/methodological-and-conceptual-framework-for-5d-multi-table-analysis-a-unified-apSecFeedde2026-08-28T04:02:27.819242+00:00Methodological and Conceptual Framework for 5D Multi-Table Analysis: A Unified Approach for Complex Data Reusehttps://blog.schoergendorfer.com/post/llms-for-academic-workflows-an-evaluation-of-literature-reviews-generated-with-sSecFeedde2026-08-28T04:02:27.759456+00:00LLMs for Academic Workflows: An Evaluation of Literature Reviews Generated with Short and Long Context Windows of LLMshttps://blog.schoergendorfer.com/post/the-artificial-experimentalist-discovery-and-control-of-self-organizing-phenomenSecFeedde2026-08-28T04:02:27.698534+00:00The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement Learninghttps://blog.schoergendorfer.com/post/cifqa-a-deterministic-tool-grounded-multi-agent-llm-framework-for-financial-querSecFeedde2026-08-28T04:02:27.671708+00:00CIFQA: A Deterministic Tool-Grounded Multi-Agent LLM Framework for Financial Query Answeringhttps://blog.schoergendorfer.com/post/picasso-an-ai-enabled-design-framework-for-autonomous-optimization-of-silicon-phSecFeedde2026-08-28T04:02:27.641984+00:00PICasso: An AI-Enabled Design Framework for Autonomous Optimization of Silicon Photonic Deviceshttps://blog.schoergendorfer.com/post/large-models-for-battery-prognostics-and-health-management-a-review-and-future-rSecFeedde2026-08-28T04:02:27.612419+00:00Large Models for Battery Prognostics and Health Management: A Review and Future Roadmaphttps://blog.schoergendorfer.com/post/standalone-llm-and-a-pre-specified-agentic-pipeline-for-explaining-icu-mortalitySecFeedde2026-08-28T04:02:27.582750+00:00Standalone LLM and a Pre-specified Agentic Pipeline for Explaining ICU Mortality Predictions: a Feasibility Study on the eICU Demo Datasethttps://blog.schoergendorfer.com/post/eduriskx-a-neuro-symbolic-framework-with-f-logic-reasoning-for-early-academic-riSecFeedde2026-08-28T04:02:27.552046+00:00EduRiskX: A Neuro-Symbolic Framework with F-Logic Reasoning for Early Academic Risk Predictionhttps://blog.schoergendorfer.com/post/kubernetes-v137-metrics-api-graduates-to-stableSecFeedde2026-08-28T03:32:36.037743+00:00Kubernetes v1.37: Metrics API graduates to stablehttps://blog.schoergendorfer.com/post/muse-glimmer-30b-and-qwen-38-27b-models-now-available-on-amazon-sagemaker-jumpstSecFeedde2026-08-28T00:17:31.865945+00:00Muse-Glimmer-30B and Qwen 3.8-27B models now available on Amazon SageMaker JumpStarthttps://blog.schoergendorfer.com/post/cosmos3-edge-cosmos3-nano-and-cosmos3-super-models-now-available-on-amazon-sagemSecFeedde2026-08-28T00:17:31.830903+00:00Cosmos3-Edge, Cosmos3-Nano, and Cosmos3-Super models now available on Amazon SageMaker JumpStarthttps://blog.schoergendorfer.com/post/how-to-measure-and-improve-instrumentation-quality-for-better-full-stack-observaSecFeedde2026-08-27T23:17:24.827556+00:00How to measure and improve instrumentation quality for better full-stack observabilityhttps://blog.schoergendorfer.com/post/aws-backup-adds-cross-region-and-cross-account-backup-support-for-amazon-fsx-forSecFeedde2026-08-27T23:17:24.792901+00:00AWS Backup adds cross-Region and cross-account backup support for Amazon FSx for NetApp ONTAPhttps://blog.schoergendorfer.com/post/build-agentic-creative-workflows-with-amazon-quick-and-falSecFeedde2026-08-27T23:17:24.708117+00:00Build agentic creative workflows with Amazon Quick and falhttps://blog.schoergendorfer.com/post/breaking-claude-code-opus-5-auto-modeSecFeedde2026-08-27T23:02:39.830185+00:00Breaking Claude Code Opus 5 Auto Modehttps://blog.schoergendorfer.com/post/amazon-evs-now-supports-i7imetal-48xl-amazon-ec2-instance-typeSecFeedde2026-08-27T22:17:58.522183+00:00Amazon EVS now supports i7i.metal-48xl Amazon EC2 instance typehttps://blog.schoergendorfer.com/post/usn-8666-3-linux-kernel-gcp-fips-vulnerabilitiesSecFeedde2026-08-27T22:02:27.817629+00:00USN-8666-3: Linux kernel (GCP FIPS) vulnerabilitieshttps://blog.schoergendorfer.com/post/amazon-connect-customer-expands-conversational-analytics-capabilities-in-the-afrSecFeedde2026-08-27T21:17:39.145656+00:00Amazon Connect Customer expands conversational analytics capabilities in the Africa (Cape Town) Regionhttps://blog.schoergendorfer.com/post/amazon-redshift-integrates-with-agent-toolkit-for-aws-for-ai-assisted-data-warehSecFeedde2026-08-27T21:17:39.106462+00:00Amazon Redshift integrates with Agent Toolkit for AWS for AI-assisted data warehouse managementhttps://blog.schoergendorfer.com/post/introducing-openai-models-on-amazon-bedrock-for-in-country-inferencing-in-india-2SecFeedde2026-08-27T21:17:39.039298+00:00Introducing OpenAI models on Amazon Bedrock for in-country inferencing in Indiahttps://blog.schoergendorfer.com/post/google-found-a-way-to-test-gemini-without-seeing-the-questionsSecFeedde2026-08-27T21:03:05.897404+00:00Google found a way to test Gemini without seeing the questionshttps://blog.schoergendorfer.com/post/introducing-openai-models-on-amazon-bedrock-for-in-country-inferencing-in-indiaSecFeedde2026-08-27T21:03:05.830332+00:00Introducing OpenAI models on Amazon Bedrock for in-country inferencing in Indiahttps://blog.schoergendorfer.com/post/how-to-recognize-your-team-with-gitlab-achievementsSecFeedde2026-08-27T20:17:41.644608+00:00How to recognize your team with GitLab Achievementshttps://blog.schoergendorfer.com/post/amazon-fsx-for-netapp-ontap-now-supports-copying-backups-across-aws-regions-andSecFeedde2026-08-27T20:17:41.609837+00:00Amazon FSx for NetApp ONTAP now supports copying backups across AWS Regions and accountshttps://blog.schoergendorfer.com/post/amazon-ec2-x8i-instances-are-now-available-in-additional-regions-2SecFeedde2026-08-27T20:17:41.571840+00:00Amazon EC2 X8i instances are now available in additional regionshttps://blog.schoergendorfer.com/post/cohere-releases-parse-5-parse-v50-a-23b-vision-language-model-that-turns-enterprSecFeedde2026-08-27T20:17:41.536136+00:00Cohere Releases Parse 5 (parse-v5.0): A 2.3B Vision Language Model That Turns Enterprise Documents Into Markdownhttps://blog.schoergendorfer.com/post/sonar-ai-agent-discovers-vulnerabilities-hidden-in-business-logic-workflowsSecFeedde2026-08-27T19:47:49.784225+00:00Sonar AI Agent Discovers Vulnerabilities Hidden in Business Logic Workflowshttps://blog.schoergendorfer.com/post/ai-coded-it-ai-shipped-it-who-owns-it-by-ralph-birdSecFeedde2026-08-27T19:47:49.745572+00:00AI Coded It, AI Shipped It, Who Owns It? by Ralph Birdhttps://blog.schoergendorfer.com/post/aws-elastic-disaster-recovery-introduces-recovery-plans-for-orchestrated-applicaSecFeedde2026-08-27T19:17:52.488633+00:00AWS Elastic Disaster Recovery introduces Recovery Plans for orchestrated application recoveryhttps://blog.schoergendorfer.com/post/introducing-india-cross-region-inference-for-openai-gpt-56-models-on-amazon-bedrSecFeedde2026-08-27T18:47:37.997650+00:00Introducing India cross-Region inference for OpenAI GPT-5.6 models on Amazon Bedrockhttps://blog.schoergendorfer.com/post/cisa-adds-three-known-exploited-vulnerabilities-to-catalog-5SecFeedde2026-08-27T18:33:57.034563+00:00CISA Adds Three Known Exploited Vulnerabilities to Cataloghttps://blog.schoergendorfer.com/post/aider-claude-code-and-openclaw-ran-an-identical-model-token-use-varied-70-foldSecFeedde2026-08-27T18:03:44.796783+00:00Aider, Claude Code, and OpenClaw ran an identical model. Token use varied 70-fold.https://blog.schoergendorfer.com/post/when-ai-coding-agents-become-malware-delivery-systemsSecFeedde2026-08-27T18:03:44.763641+00:00When AI Coding Agents Become Malware Delivery Systemshttps://blog.schoergendorfer.com/post/sorry-i-cant-help-with-that-how-your-guardrails-might-become-the-attackers-bestSecFeedde2026-08-27T18:03:44.731983+00:00“Sorry, I can’t help with that”: How your guardrails might become the attacker’s best friendhttps://blog.schoergendorfer.com/post/gitlab-compliance-frameworks-adhere-to-soc-2-in-minutesSecFeedde2026-08-27T17:47:49.908249+00:00GitLab compliance frameworks: Adhere to SOC 2 in minuteshttps://blog.schoergendorfer.com/post/why-specterops-signed-openais-call-for-collective-cyber-defenseSecFeedde2026-08-27T17:47:49.870268+00:00Why SpecterOps Signed OpenAI’s Call for Collective Cyber Defensehttps://blog.schoergendorfer.com/post/sharepoint-framework-spfx-roadmap-update-august-2026SecFeedde2026-08-27T17:47:49.836119+00:00SharePoint Framework (SPFx) roadmap update – August 2026https://blog.schoergendorfer.com/post/whats-new-in-microsoft-security-august-2026SecFeedde2026-08-27T17:18:00.304258+00:00​​​​​​What’s new in Microsoft Security: August 2026https://blog.schoergendorfer.com/post/best-agent-sandboxes-in-2026-cold-start-per-second-pricing-and-network-policy-acSecFeedde2026-08-27T17:18:00.266568+00:00Best Agent Sandboxes in 2026: Cold Start, Per-Second Pricing, and Network Policy Across E2B, Daytona, Modal, Cloudflare, and Vercelhttps://blog.schoergendorfer.com/post/how-we-saved-100-terabytes-of-memory-by-optimizing-1111s-dns-cacheSecFeedde2026-08-27T17:03:46.504654+00:00How we saved 100 terabytes of memory by optimizing 1.1.1.1’s DNS cachehttps://blog.schoergendorfer.com/post/nvidias-129b-hugging-face-deal-has-an-open-source-problemSecFeedde2026-08-27T16:48:15.866631+00:00Nvidia’s $12.9B Hugging Face deal has an open-source problemhttps://blog.schoergendorfer.com/post/this-duck-will-teach-you-reinforcement-learning-and-pick-up-your-socksSecFeedde2026-08-27T16:34:11.641909+00:00This duck will teach you reinforcement learning — and pick up your sockshttps://blog.schoergendorfer.com/post/extend-amazon-bedrock-guardrails-to-tool-interactions-using-the-strands-agents-sSecFeedde2026-08-27T16:34:11.582077+00:00Extend Amazon Bedrock Guardrails to Tool Interactions Using the Strands Agents SDKhttps://blog.schoergendorfer.com/post/replits-new-default-auto-mode-picks-the-best-model-for-each-taskSecFeedde2026-08-27T16:18:20.569179+00:00Replit’s new default: Auto mode picks the best model for each taskhttps://blog.schoergendorfer.com/post/harness-unfurls-source-code-repository-alternative-to-githubSecFeedde2026-08-27T16:18:20.538400+00:00Harness Unfurls Source Code Repository Alternative to GitHubhttps://blog.schoergendorfer.com/post/reduce-asr-inference-costs-by-75-with-nvidia-mps-on-amazon-ec2SecFeedde2026-08-27T16:18:20.483291+00:00Reduce ASR inference costs by 75% with NVIDIA MPS on Amazon EC2https://blog.schoergendorfer.com/post/deepgram-deepens-amazon-sagemaker-ai-observability-with-enhanced-metricsSecFeedde2026-08-27T16:18:20.449768+00:00Deepgram deepens Amazon SageMaker AI observability with Enhanced Metricshttps://blog.schoergendorfer.com/post/openclaw-went-viral-meet-the-maintainers-building-and-securing-itSecFeedde2026-08-27T16:18:20.414066+00:00OpenClaw went viral. Meet the maintainers building and securing it.https://blog.schoergendorfer.com/post/deploy-personal-ai-agents-with-cloud-run-instancesSecFeedde2026-08-27T16:18:20.376392+00:00Deploy personal AI agents with Cloud Run instanceshttps://blog.schoergendorfer.com/post/reimagining-work-how-pythians-internal-ai-playbook-delivers-customer-roiSecFeedde2026-08-27T16:18:20.338065+00:00Reimagining work: How Pythian’s internal AI playbook delivers customer ROIhttps://blog.schoergendorfer.com/post/cleartext-credential-recovery-in-servicenowSecFeedde2026-08-27T16:02:54.595484+00:00Cleartext Credential Recovery in ServiceNowhttps://blog.schoergendorfer.com/post/posterity-will-find-it-ludicrous-sai-agent-hits-73-on-osworld-20-performing-routSecFeedde2026-08-27T15:48:24.068817+00:00“Posterity will find it ludicrous”: Sai agent hits 73% on OSWorld 2.0 performing routine (but necessary) workhttps://blog.schoergendorfer.com/post/mitsubishi-electric-cnc-series-update-aSecFeedde2026-08-27T15:48:24.032563+00:00Mitsubishi Electric CNC Series (Update A)https://blog.schoergendorfer.com/post/xiiaozet-lk100wSecFeedde2026-08-27T15:48:23.995713+00:00Xiiaozet LK100Whttps://blog.schoergendorfer.com/post/rockwell-automation-otto-fleet-managerSecFeedde2026-08-27T15:48:23.960205+00:00Rockwell Automation OTTO Fleet Managerhttps://blog.schoergendorfer.com/post/ebyte-na111-mSecFeedde2026-08-27T15:48:23.926510+00:00Ebyte NA111-Mhttps://blog.schoergendorfer.com/post/all-line-equipment-company-fuel-bossSecFeedde2026-08-27T15:48:23.887607+00:00All-Line Equipment Company Fuel-Bosshttps://blog.schoergendorfer.com/post/applied-systems-engineering-ase2000-v2-communications-test-setSecFeedde2026-08-27T15:48:23.852214+00:00Applied Systems Engineering ASE2000 V2 Communications Test Sethttps://blog.schoergendorfer.com/post/from-in-silico-to-wet-lab-evaluating-ai-protein-design-performanceSecFeedde2026-08-27T15:48:23.808397+00:00From In-Silico to Wet-Lab: Evaluating AI Protein Design Performancehttps://blog.schoergendorfer.com/post/mitsubishi-electric-multiple-fa-products-update-dSecFeedde2026-08-27T15:33:00.645326+00:00Mitsubishi Electric Multiple FA Products (Update D)https://blog.schoergendorfer.com/post/nvidia-doesnt-need-to-block-rival-chips-on-hugging-face-it-just-needs-the-defaulSecFeedde2026-08-27T15:17:57.284415+00:00Nvidia doesn’t need to block rival chips on Hugging Face. It just needs the defaults.https://blog.schoergendorfer.com/post/lsn-0121-1-kernel-live-patch-security-noticeSecFeedde2026-08-27T14:47:51.711147+00:00LSN-0121-1: Kernel Live Patch Security Noticehttps://blog.schoergendorfer.com/post/how-to-build-an-exposure-management-program-the-business-trusts-lessons-from-tenSecFeedde2026-08-27T14:47:51.666919+00:00How to build an exposure management program the business trusts: Lessons from Tenable’s CSOhttps://blog.schoergendorfer.com/post/enterprise-ais-real-risk-isnt-autonomous-agents-its-the-complexity-between-themSecFeedde2026-08-27T14:47:51.632698+00:00Enterprise AI's real risk isn't autonomous agents. It's the complexity between them.https://blog.schoergendorfer.com/post/identity-as-a-service-uncovering-dark-web-marketplaces-trading-executive-ssnsSecFeedde2026-08-27T14:17:43.390105+00:00Identity-as-a-Service: Uncovering Dark Web Marketplaces Trading Executive SSNshttps://blog.schoergendorfer.com/post/why-basic-rag-fails-at-multi-hop-reasoning-and-how-graphrag-fixes-itSecFeedde2026-08-27T14:02:53.328640+00:00Why basic RAG fails at multi-hop reasoning (and how GraphRAG fixes it)https://blog.schoergendorfer.com/post/when-agents-act-on-their-own-governance-has-to-live-in-the-data-layerSecFeedde2026-08-27T13:17:40.147493+00:00When agents act on their own, governance has to live in the data layerhttps://blog.schoergendorfer.com/post/anthropics-new-files-api-vs-pasting-it-will-save-you-time-but-it-wont-save-you-mSecFeedde2026-08-27T13:02:50.348876+00:00Anthropic’s new Files API vs. pasting: It will save you time, but it won’t save you money.https://blog.schoergendorfer.com/post/advance-zero-trust-for-ai-new-tools-and-guidance-to-secure-ai-agents-and-devseco-2SecFeedde2026-08-27T13:02:50.299712+00:00Advance Zero Trust for AI: New tools and guidance to secure AI agents and DevSecOpshttps://blog.schoergendorfer.com/post/microsoft-named-a-leader-in-the-kuppingercole-leadership-compass-for-cloud-nativ-2SecFeedde2026-08-27T13:02:50.262765+00:00​​Microsoft named a Leader in the KuppingerCole Leadership Compass for Cloud Native Application Protection Platforms (CNAPP)https://blog.schoergendorfer.com/post/how-to-build-a-durable-change-control-gate-for-ai-agentsSecFeedde2026-08-27T11:47:41.878922+00:00How to Build a Durable Change-Control Gate for AI Agentshttps://blog.schoergendorfer.com/post/building-an-ai-factory-on-kubernetesSecFeedde2026-08-27T11:47:41.849469+00:00Building an AI factory on Kuberneteshttps://blog.schoergendorfer.com/post/azure-devops-in-the-github-copilot-appSecFeedde2026-08-27T11:47:40.408954+00:00Azure DevOps in the GitHub Copilot Apphttps://blog.schoergendorfer.com/post/production-validation-the-missing-layer-in-enterprise-releasesSecFeedde2026-08-27T11:47:40.302892+00:00Production Validation: The Missing Layer in Enterprise Releaseshttps://blog.schoergendorfer.com/post/two-alleged-teampcp-hackers-arrested-in-australiaSecFeedde2026-08-27T11:32:48.391346+00:00Two Alleged ‘TeamPCP’ Hackers Arrested in Australiahttps://blog.schoergendorfer.com/post/a-polymorphic-phishing-page-that-occasionally-breaks-itself-thu-aug-27thSecFeedde2026-08-27T11:17:40.912535+00:00A polymorphic phishing page (that occasionally breaks itself), (Thu, Aug 27th)https://blog.schoergendorfer.com/post/threat-landscape-for-industrial-automation-systems-q2-2026SecFeedde2026-08-27T11:17:40.870207+00:00Threat landscape for industrial automation systems. Q2 2026https://blog.schoergendorfer.com/post/javascript-obfuscation-from-party-trick-to-phishing-kitSecFeedde2026-08-27T11:17:40.806024+00:00JavaScript obfuscation: From party trick to phishing kithttps://blog.schoergendorfer.com/post/google-research-introduces-glucofm-a-072m-parameter-dual-stream-foundation-modelSecFeedde2026-08-27T09:32:47.487415+00:00Google Research Introduces GlucoFM: A 0.72M-Parameter Dual-Stream Foundation Model for Continuous Glucose Monitoringhttps://blog.schoergendorfer.com/post/cutetts-efficient-and-high-quality-speech-synthesis-via-autoregressive-modeling-2SecFeedde2026-08-27T09:32:47.419075+00:00CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latentshttps://blog.schoergendorfer.com/post/schedbench-a-benchmark-for-evaluating-llm-constraint-faithfulness-in-natural-lan-2SecFeedde2026-08-27T09:32:47.387383+00:00SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Schedulinghttps://blog.schoergendorfer.com/post/corpus2skill-distilling-enterprise-knowledge-into-navigable-agent-skills-for-qaSecFeedde2026-08-27T09:32:47.327302+00:00Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAGhttps://blog.schoergendorfer.com/post/a-layered-security-framework-against-prompt-injection-in-rag-based-chatbotsSecFeedde2026-08-27T09:32:47.299620+00:00A Layered Security Framework Against Prompt Injection in RAG-Based Chatbotshttps://blog.schoergendorfer.com/post/mmemb-r1-reasoning-enhanced-multimodal-embedding-with-pair-aware-selection-and-aSecFeedde2026-08-27T09:32:47.262798+00:00MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Controlhttps://blog.schoergendorfer.com/post/mitigating-llm-biases-toward-spurious-social-contexts-using-direct-preference-opSecFeedde2026-08-27T09:32:47.207704+00:00Mitigating LLM biases toward spurious social contexts using direct preference optimizationhttps://blog.schoergendorfer.com/post/tool-verification-for-test-time-reinforcement-learningSecFeedde2026-08-27T09:32:47.174507+00:00Tool Verification for Test-Time Reinforcement Learninghttps://blog.schoergendorfer.com/post/reasoning-or-rambling-exploring-the-effect-of-thinking-on-agent-persuasionSecFeedde2026-08-27T09:32:47.143366+00:00Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasionhttps://blog.schoergendorfer.com/post/eduagentqg-multi-agent-personalized-mathematics-question-generation-with-expliciSecFeedde2026-08-27T09:32:47.102657+00:00EduAgentQG: Multi-Agent Personalized Mathematics Question Generation with Explicit Diversity and Objective-Aware Evaluationhttps://blog.schoergendorfer.com/post/recurrence-meets-transformers-for-universal-multimodal-retrievalSecFeedde2026-08-27T09:32:47.069492+00:00Recurrence Meets Transformers for Universal Multimodal Retrievalhttps://blog.schoergendorfer.com/post/memory-augmentation-unlocks-efficient-chain-of-thought-reasoning-2SecFeedde2026-08-27T09:32:47.007049+00:00Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoninghttps://blog.schoergendorfer.com/post/literarybigfive-author-personalized-text-generation-in-a-unified-interpretable-s-2SecFeedde2026-08-27T09:32:46.971046+00:00LITERARYBIGFIVE: Author-Personalized Text Generation in a Unified Interpretable Spacehttps://blog.schoergendorfer.com/post/reliable-financial-named-entity-recognition-under-domain-shift-confidence-estimaSecFeedde2026-08-27T09:17:48.400506+00:00Reliable Financial Named Entity Recognition Under Domain Shift: Confidence Estimation and Selective Predictionhttps://blog.schoergendorfer.com/post/style-wins-substance-loses-a-diagnosis-of-llm-as-judge-in-idea-generation-3SecFeedde2026-08-27T09:17:48.343977+00:00Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generationhttps://blog.schoergendorfer.com/post/when-retrieval-helps-and-distracts-evaluating-evidence-generating-llms-for-biome-2SecFeedde2026-08-27T09:17:48.305195+00:00When Retrieval Helps and Distracts: Evaluating Evidence-Generating LLMs for Biomedical Claim Verificationhttps://blog.schoergendorfer.com/post/vdar-router-adaptive-llms-routing-via-verbalized-query-difficulty-analysis-retri-2SecFeedde2026-08-27T09:17:48.260500+00:00VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrievalhttps://blog.schoergendorfer.com/post/lower-resource-higher-scores-language-bias-in-llm-evaluators-2SecFeedde2026-08-27T09:17:48.220733+00:00Lower-Resource, Higher Scores: Language Bias in LLM Evaluatorshttps://blog.schoergendorfer.com/post/pigeonholing-how-bad-prompts-hurt-models-causing-collapse-and-mistakes-2SecFeedde2026-08-27T09:17:48.174423+00:00Pigeonholing: how bad prompts hurt models, causing collapse and mistakeshttps://blog.schoergendorfer.com/post/sag-sql-retrieval-augmented-generation-with-query-time-dynamic-hyperedges-3SecFeedde2026-08-27T09:17:48.130381+00:00SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedgeshttps://blog.schoergendorfer.com/post/clinically-grounded-privacy-evaluation-of-medical-lms-2SecFeedde2026-08-27T09:17:48.096921+00:00Clinically Grounded Privacy Evaluation of Medical LMshttps://blog.schoergendorfer.com/post/latentskill-from-in-context-textual-skills-to-in-weight-latent-skills-for-llm-ag-2SecFeedde2026-08-27T09:17:48.063115+00:00LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agentshttps://blog.schoergendorfer.com/post/from-layers-to-submodules-rethinking-granularity-in-replacement-based-llm-compreSecFeedde2026-08-27T09:17:48.029629+00:00From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compressionhttps://blog.schoergendorfer.com/post/resmerge-residual-based-spectral-merging-of-large-language-modelsSecFeedde2026-08-27T09:17:47.997107+00:00ResMerge: Residual-based Spectral Merging of Large Language Modelshttps://blog.schoergendorfer.com/post/rethinking-the-multilingual-reasoning-gap-with-layer-swapSecFeedde2026-08-27T09:17:47.954982+00:00Rethinking the Multilingual Reasoning Gap with Layer Swaphttps://blog.schoergendorfer.com/post/agentdiff-meaning-bearing-rewrites-trigger-deeper-divergence-than-presentation-cSecFeedde2026-08-27T09:17:47.923648+00:00AgentDiff: Meaning-Bearing Rewrites Trigger Deeper Divergence than Presentation Changes in LLM Agentshttps://blog.schoergendorfer.com/post/macro-enhancing-multilingual-counterfactual-explanations-through-alignment-as-prSecFeedde2026-08-27T09:17:47.898159+00:00Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimizationhttps://blog.schoergendorfer.com/post/when-emotion-becomes-trigger-emotion-style-dynamic-backdoor-attack-parasitisingSecFeedde2026-08-27T09:17:47.868751+00:00When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Modelshttps://blog.schoergendorfer.com/post/ael-evolving-agent-harness-in-open-ended-environmentsSecFeedde2026-08-27T09:17:47.839246+00:00AEL: Evolving Agent Harness in Open-Ended Environmentshttps://blog.schoergendorfer.com/post/synthesizing-instruction-tuning-datasets-with-contrastive-decodingSecFeedde2026-08-27T09:17:47.801867+00:00Synthesizing Instruction-Tuning Datasets with Contrastive Decodinghttps://blog.schoergendorfer.com/post/time-is-not-a-label-continuous-phase-rotation-for-temporal-knowledge-graphs-andSecFeedde2026-08-27T09:17:47.759793+00:00Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memoryhttps://blog.schoergendorfer.com/post/sell-more-play-less-benchmarking-llm-realistic-selling-skillSecFeedde2026-08-27T09:17:47.725929+00:00Sell More, Play Less: Benchmarking LLM Realistic Selling Skillhttps://blog.schoergendorfer.com/post/addressing-the-reasoning-gap-mechanistic-circuit-based-knowledge-editing-in-largSecFeedde2026-08-27T09:02:56.441900+00:00Addressing the Reasoning Gap: Mechanistic Circuit-Based Knowledge Editing in Large Language Modelshttps://blog.schoergendorfer.com/post/just-pass-twice-efficient-token-classification-with-llms-for-zero-shot-nerSecFeedde2026-08-27T09:02:56.410008+00:00Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NERhttps://blog.schoergendorfer.com/post/retrieval-augmented-agentic-rubric-generation-for-reliable-medical-response-evalSecFeedde2026-08-27T09:02:56.356772+00:00Retrieval-Augmented Agentic Rubric Generation for Reliable Medical Response Evaluationhttps://blog.schoergendorfer.com/post/mind2report-expert-level-commercial-report-synthesis-via-cognitive-deep-researchSecFeedde2026-08-27T09:02:56.329185+00:00Mind2Report: Expert-Level Commercial Report Synthesis via Cognitive Deep Research Agenthttps://blog.schoergendorfer.com/post/gavel-agent-meets-checklist-for-evaluating-llms-on-long-context-legal-summarizat-2SecFeedde2026-08-27T09:02:56.270578+00:00Gavel: Agent Meets Checklist for Evaluating LLMs on Long-Context Legal Summarizationhttps://blog.schoergendorfer.com/post/scalable-supervision-for-software-agents-via-patch-reasoningSecFeedde2026-08-27T09:02:56.219231+00:00Scalable Supervision for Software Agents via Patch Reasoninghttps://blog.schoergendorfer.com/post/edudial-constructing-a-large-scale-multi-turn-teacher-student-dialogue-corpusSecFeedde2026-08-27T09:02:56.159137+00:00EduDial: Constructing a Large-scale Multi-turn Teacher-Student Dialogue Corpushttps://blog.schoergendorfer.com/post/refine-a-framework-for-trustworthy-large-reasoning-models-with-reliability-faithSecFeedde2026-08-27T09:02:56.129115+00:00ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretabilityhttps://blog.schoergendorfer.com/post/llmtrace-a-corpus-for-classification-and-fine-grained-localization-of-ai-writtenSecFeedde2026-08-27T09:02:56.095608+00:00LLMTrace: A Corpus for Classification and Fine-Grained Localization of AI-Written Texthttps://blog.schoergendorfer.com/post/idealign-comparing-ideas-of-large-language-models-to-domain-expertSecFeedde2026-08-27T09:02:56.067139+00:00IDEAlign: Comparing Ideas of Large Language Models to Domain Experthttps://blog.schoergendorfer.com/post/internbootcamp-boosting-llm-reasoning-with-verifiable-task-scalingSecFeedde2026-08-27T09:02:56.036782+00:00InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scalinghttps://blog.schoergendorfer.com/post/simlens-for-early-exit-in-large-language-models-eliciting-accurate-latent-predicSecFeedde2026-08-27T09:02:56.006410+00:00SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Tokenhttps://blog.schoergendorfer.com/post/kesa-a-knowledge-enhanced-approach-for-sentiment-analysisSecFeedde2026-08-27T09:02:55.972761+00:00KESA: A Knowledge Enhanced Approach For Sentiment Analysishttps://blog.schoergendorfer.com/post/on-the-idiosyncrasies-of-the-mandarin-chinese-classifier-systemSecFeedde2026-08-27T09:02:55.942437+00:00On the Idiosyncrasies of the Mandarin Chinese Classifier Systemhttps://blog.schoergendorfer.com/post/recurrent-neural-networks-in-linguistic-theory-revisiting-pinker-and-prince-1988SecFeedde2026-08-27T09:02:55.913034+00:00Recurrent Neural Networks in Linguistic Theory: Revisiting Pinker and Prince (1988) and the Past Tense Debatehttps://blog.schoergendorfer.com/post/plansightrag-a-visual-first-multimodal-rag-for-automating-question-answering-andSecFeedde2026-08-27T09:02:55.880303+00:00PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard Planshttps://blog.schoergendorfer.com/post/swarmworld-stigmergic-technological-evolution-in-societies-of-language-model-ageSecFeedde2026-08-27T09:02:55.844459+00:00SwarmWorld: Stigmergic technological evolution in societies of language-model agentshttps://blog.schoergendorfer.com/post/trace-integrity-for-llm-data-agents-a-vision-for-auditable-structured-reasoningSecFeedde2026-08-27T08:47:36.496721+00:00Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systemshttps://blog.schoergendorfer.com/post/a-self-evolving-multi-agent-framework-defense-against-llm-jailbreak-attacksSecFeedde2026-08-27T08:47:36.451386+00:00A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attackshttps://blog.schoergendorfer.com/post/asymspec-context-asymmetric-speculative-decoding-for-agentic-llmsSecFeedde2026-08-27T08:47:36.421225+00:00AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMshttps://blog.schoergendorfer.com/post/code-world-model-coding-agent-as-world-brainSecFeedde2026-08-27T08:47:36.389061+00:00Code World Model: Coding Agent as World Brainhttps://blog.schoergendorfer.com/post/formal-executable-and-explainable-runtime-monitoring-of-spoken-air-traffic-contrSecFeedde2026-08-27T08:47:36.357567+00:00Formal, Executable and Explainable Runtime Monitoring of Spoken Air Traffic Control Operational Procedureshttps://blog.schoergendorfer.com/post/plans-you-can-check-verifier-grounded-learning-of-an-open-weight-planner-for-exeSecFeedde2026-08-27T08:47:36.325715+00:00Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editinghttps://blog.schoergendorfer.com/post/when-stale-constraints-go-unchecked-budgeted-verification-failures-in-inheritedSecFeedde2026-08-27T08:47:36.293929+00:00When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memoryhttps://blog.schoergendorfer.com/post/conditional-total-correlation-and-the-serial-depth-of-adaptive-parallel-samplingSecFeedde2026-08-27T08:47:36.261720+00:00Conditional Total Correlation and the Serial Depth of Adaptive Parallel Samplinghttps://blog.schoergendorfer.com/post/caskg-counterfactual-causal-skill-graphs-for-scalable-agent-skill-retrievalSecFeedde2026-08-27T08:47:36.228019+00:00CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrievalhttps://blog.schoergendorfer.com/post/ggss-geodesic-gated-spherical-steering-for-inference-time-debiasing-of-generativSecFeedde2026-08-27T08:47:36.159768+00:00GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language Modelshttps://blog.schoergendorfer.com/post/learning-what-to-share-and-what-to-personalize-hierarchical-strategy-co-evolutioSecFeedde2026-08-27T08:47:36.127737+00:00Learning What to Share and What to Personalize: Hierarchical Strategy Co-Evolution for Agent Memoryhttps://blog.schoergendorfer.com/post/finriskatlas-decision-aligned-evaluation-of-large-language-models-for-financialSecFeedde2026-08-27T08:47:36.090172+00:00FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk Reviewhttps://blog.schoergendorfer.com/post/the-curse-of-knowledge-in-llm-query-simulation-concept-provenance-for-tracing-anSecFeedde2026-08-27T08:47:36.055513+00:00The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusionhttps://blog.schoergendorfer.com/post/rare-diseases-common-dilemmas-llms-prioritize-equal-resource-distribution-over-pSecFeedde2026-08-27T08:47:36.025855+00:00Rare Diseases, Common Dilemmas: LLMs Prioritize Equal Resource Distribution over Patient Benefit in Decision-Makinghttps://blog.schoergendorfer.com/post/turnbench-a-multi-domain-benchmark-for-turn-taking-dynamics-in-spoken-dialogueSecFeedde2026-08-27T08:47:35.997421+00:00TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialoguehttps://blog.schoergendorfer.com/post/reflam-a-reference-grounded-line-annotation-pipeline-for-historical-arabic-manusSecFeedde2026-08-27T08:47:35.968145+00:00RefLAM: A Reference-Grounded Line Annotation Pipeline for Historical Arabic Manuscriptshttps://blog.schoergendorfer.com/post/retrieve-match-escalate-accurate-and-scalable-product-linking-with-vlm-distilledSecFeedde2026-08-27T08:47:35.940809+00:00Retrieve, Match, Escalate: Accurate and Scalable Product Linking with VLM-Distilled Cross-Encoders and Agentic VLMshttps://blog.schoergendorfer.com/post/frontierchallenge-evaluating-scientific-workflow-completionSecFeedde2026-08-27T08:47:35.913749+00:00FrontierChallenge: Evaluating Scientific Workflow Completionhttps://blog.schoergendorfer.com/post/can-we-read-the-mind-of-an-audio-llm-a-verbalizable-multilingual-middle-layer-woSecFeedde2026-08-27T08:47:35.880089+00:00Can We Read the Mind of an Audio LLM? A Verbalizable, Multilingual Middle-Layer Workspacehttps://blog.schoergendorfer.com/post/natural-language-input-semantic-track-representation-and-llm-inference-making-thSecFeedde2026-08-27T08:32:59.297043+00:00Natural Language Input, Semantic Track Representation, and LLM Inference: Making the Maritime Information Exchange Model Tractablehttps://blog.schoergendorfer.com/post/fine-tuning-whisper-for-automatic-speech-recognition-in-baniwa-a-preliminary-stuSecFeedde2026-08-27T08:32:59.263759+00:00Fine-Tuning Whisper for Automatic Speech Recognition in Baniwa: A Preliminary Studyhttps://blog.schoergendorfer.com/post/beyond-local-surprise-grounded-dialogue-as-selective-belief-revision-under-referSecFeedde2026-08-27T08:32:59.228319+00:00Beyond Local Surprise: Grounded Dialogue as Selective Belief Revision under Referential Uncertaintyhttps://blog.schoergendorfer.com/post/visa-agentic-self-evolving-data-synthesis-for-multimodal-instruction-followingSecFeedde2026-08-27T08:32:59.192098+00:00VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Followinghttps://blog.schoergendorfer.com/post/distinct-dynamics-of-conceptual-and-referential-disruptions-in-human-reading-andSecFeedde2026-08-27T08:32:59.157363+00:00Distinct dynamics of conceptual and referential disruptions in human reading and large language model processinghttps://blog.schoergendorfer.com/post/when-personality-meets-quantization-a-layer-wise-mbti-analysis-of-quantized-llmsSecFeedde2026-08-27T08:32:59.125844+00:00When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMshttps://blog.schoergendorfer.com/post/unveiling-spectral-mechanisms-in-training-free-llm-text-detectionSecFeedde2026-08-27T08:32:59.094207+00:00Unveiling Spectral Mechanisms in Training-Free LLM Text Detectionhttps://blog.schoergendorfer.com/post/query-side-attacks-on-gnn-based-kgqa-tracing-failures-from-entity-linking-to-ansSecFeedde2026-08-27T08:32:59.058880+00:00Query-Side Attacks on GNN-Based KGQA: Tracing Failures from Entity Linking to Answer Generationhttps://blog.schoergendorfer.com/post/one-form-to-transfer-them-all-pretraining-multilingual-language-models-beyond-naSecFeedde2026-08-27T08:32:59.029716+00:00One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthographyhttps://blog.schoergendorfer.com/post/from-passive-response-to-proactive-correction-enhancing-llm-robustness-against-iSecFeedde2026-08-27T08:32:59.000295+00:00From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbationshttps://blog.schoergendorfer.com/post/loss-based-active-learning-for-neural-abstractive-summarizationSecFeedde2026-08-27T08:32:58.961663+00:00Loss-Based Active Learning for Neural Abstractive Summarizationhttps://blog.schoergendorfer.com/post/anchoring-bias-in-llm-as-a-judge-systems-prior-scores-compromise-evaluation-indeSecFeedde2026-08-27T08:32:58.931356+00:00Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independencehttps://blog.schoergendorfer.com/post/localize-then-decide-guarantees-for-llm-judgmentsSecFeedde2026-08-27T08:32:58.899181+00:00Localize-Then-Decide Guarantees for LLM Judgmentshttps://blog.schoergendorfer.com/post/moganbert-tr-a-turkish-encoder-foundation-model-trained-from-scratch-with-a-clmSecFeedde2026-08-27T08:32:58.870787+00:00MoganBert-TR: A Turkish Encoder Foundation Model Trained from Scratch with a CLM-to-MLM Curriculumhttps://blog.schoergendorfer.com/post/beam-search-self-consistency-and-the-limits-of-inference-time-scaling-for-grammaSecFeedde2026-08-27T08:32:58.834765+00:00Beam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language Modelshttps://blog.schoergendorfer.com/post/when-rag-fails-to-equalize-geo-bias-in-factual-question-answering-over-public-coSecFeedde2026-08-27T08:32:58.801766+00:00When RAG Fails to Equalize: Geo-bias in Factual Question Answering over Public Companieshttps://blog.schoergendorfer.com/post/overview-of-shroom-visions-2026-a-shared-task-on-hallucination-detection-in-largSecFeedde2026-08-27T08:32:58.765512+00:00Overview of SHROOM-Visions 2026: A Shared Task on Hallucination Detection in Large Vision-Language Modelshttps://blog.schoergendorfer.com/post/reconstructing-the-right-episode-evaluating-interleaved-conversational-memory-beSecFeedde2026-08-27T08:32:58.705176+00:00Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Contexthttps://blog.schoergendorfer.com/post/unmatched-does-not-mean-false-incomplete-reference-sets-can-reverse-calibrationSecFeedde2026-08-27T08:32:58.670885+00:00Unmatched Does Not Mean False: Incomplete Reference Sets Can Reverse Calibration Rankings in Open-Ended Theory-of-Mind Trackinghttps://blog.schoergendorfer.com/post/awm-answerable-working-memory-for-long-document-vqa-agentsSecFeedde2026-08-27T08:17:49.348252+00:00AWM: Answerable Working Memory for Long-Document VQA Agentshttps://blog.schoergendorfer.com/post/grip-granular-reward-guided-parameter-interpolation-for-efficient-reasoningSecFeedde2026-08-27T08:17:49.291616+00:00GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoninghttps://blog.schoergendorfer.com/post/cross-dataset-stability-of-expert-informed-skill-prompting-and-fine-tuning-for-cSecFeedde2026-08-27T08:17:49.258254+00:00Cross-Dataset Stability of Expert-Informed Skill Prompting and Fine-Tuning for Chinese Metaphor Identificationhttps://blog.schoergendorfer.com/post/clueweaver-reward-guided-dual-agent-evidence-reasoning-for-compact-llms-on-literSecFeedde2026-08-27T08:17:49.138667+00:00ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narrativeshttps://blog.schoergendorfer.com/post/topas-workflow-aware-prefix-state-scheduling-for-multi-agent-llm-servingSecFeedde2026-08-27T08:17:49.106015+00:00TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Servinghttps://blog.schoergendorfer.com/post/reliablerag-combating-misinformation-in-retrieval-augmented-generation-via-reliaSecFeedde2026-08-27T08:17:49.071779+00:00ReliableRAG: Combating Misinformation in Retrieval-Augmented Generation via Reliability-Guided Reasoning Chainshttps://blog.schoergendorfer.com/post/vietaidetector-an-open-source-zero-shot-detector-for-vietnamese-ai-generated-texSecFeedde2026-08-27T08:17:49.040912+00:00VietAIDetector: An Open-Source Zero-Shot Detector for Vietnamese AI-Generated Texthttps://blog.schoergendorfer.com/post/mathadv-what-theorem-provers-know-reason-formalize-and-generalizeSecFeedde2026-08-27T08:17:49.008298+00:00MathAdv: What Theorem Provers Know, Reason, Formalize, and Generalizehttps://blog.schoergendorfer.com/post/omniphys-a-unified-multimodal-benchmark-for-physics-understanding-and-generationSecFeedde2026-08-27T08:17:48.943637+00:00OmniPhys: A Unified Multimodal Benchmark for Physics Understanding and Generation from Chinese Educational Corporahttps://blog.schoergendorfer.com/post/adaptive-triggering-for-bias-correction-in-llm-reasoningSecFeedde2026-08-27T08:17:48.913460+00:00Adaptive Triggering for Bias Correction in LLM Reasoninghttps://blog.schoergendorfer.com/post/short-horizons-and-sparse-concepts-a-mathematical-view-of-the-readout-in-the-j-lSecFeedde2026-08-27T08:17:48.857107+00:00Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lenshttps://blog.schoergendorfer.com/post/provenance-before-prose-claim-locked-reportingSecFeedde2026-08-27T08:17:48.799796+00:00Provenance Before Prose: Claim-Locked Reportinghttps://blog.schoergendorfer.com/post/groundhog-bit-flip-attack-seeding-infinite-generation-loops-in-mixture-of-expertSecFeedde2026-08-27T08:03:07.940219+00:00Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flipshttps://blog.schoergendorfer.com/post/the-changing-geometry-of-grammar-dimensionality-and-neighborhood-reorganizationSecFeedde2026-08-27T08:03:07.912119+00:00The Changing Geometry of Grammar: Dimensionality and Neighborhood Reorganization across Transformer Layershttps://blog.schoergendorfer.com/post/belief-cascades-drive-persuasion-in-llm-agent-networksSecFeedde2026-08-27T08:03:07.882808+00:00Belief Cascades Drive Persuasion in LLM Agent Networkshttps://blog.schoergendorfer.com/post/less-can-be-more-relieving-rag-bottlenecks-via-evidence-frontloading-and-pressurSecFeedde2026-08-27T08:03:07.823125+00:00Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgetinghttps://blog.schoergendorfer.com/post/mtdiag-a-multi-turn-diagnostic-dataset-towards-clinically-meaningful-llm-evaluatSecFeedde2026-08-27T08:03:07.771395+00:00MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluationhttps://blog.schoergendorfer.com/post/healthbench-psych-a-mental-health-subset-of-openais-healthbenchSecFeedde2026-08-27T08:03:07.740951+00:00HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBenchhttps://blog.schoergendorfer.com/post/learning-to-act-while-waiting-rl-finetuning-of-generalist-robot-policies-under-i-2SecFeedde2026-08-27T08:03:07.620800+00:00Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latencyhttps://blog.schoergendorfer.com/post/tailsieve-partial-rollout-guided-tail-routing-for-llm-rollouts-2SecFeedde2026-08-27T08:03:07.590033+00:00TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rolloutshttps://blog.schoergendorfer.com/post/autonomous-cyber-defense-real-time-attack-detection-and-mitigation-in-software-d-2SecFeedde2026-08-27T08:03:07.561723+00:00Autonomous Cyber Defense: Real-Time Attack Detection and Mitigation in Software-Defined Networks Using Machine Learninghttps://blog.schoergendorfer.com/post/edge-experience-distillation-for-guided-exploration-in-agentic-reinforcement-lea-2SecFeedde2026-08-27T08:03:07.532542+00:00EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learninghttps://blog.schoergendorfer.com/post/tokeval-a-tokenizer-evaluation-suite-2SecFeedde2026-08-27T08:03:07.499534+00:00TokEval: A Tokenizer Evaluation Suitehttps://blog.schoergendorfer.com/post/offline-reinforcement-learning-for-hemodynamic-management-of-sepsis-in-the-icu-a-2SecFeedde2026-08-27T08:03:07.470314+00:00Offline Reinforcement Learning for Hemodynamic Management of Sepsis in the ICU: a MIMIC-IV Study with Dual Off-Policy Evaluationhttps://blog.schoergendorfer.com/post/gated-recurrent-transformers-expressive-depth-through-recurrent-modulationSecFeedde2026-08-27T08:03:07.441786+00:00Gated Recurrent Transformers: Expressive Depth through Recurrent Modulationhttps://blog.schoergendorfer.com/post/privileged-likelihood-is-not-automatically-value-three-checks-for-token-credit-i-2SecFeedde2026-08-27T08:03:07.410263+00:00Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillationhttps://blog.schoergendorfer.com/post/analytical-and-bootstrap-confidence-intervals-of-double-machine-learning-simulat-2SecFeedde2026-08-27T07:48:47.538577+00:00Analytical and Bootstrap Confidence Intervals of Double Machine Learning: Simulation studies and an application to rural-urban difference in obesity prevalencehttps://blog.schoergendorfer.com/post/think-short-defer-smart-act-and-repeat-calibrated-reasoning-and-uncertainty-awar-2SecFeedde2026-08-27T07:48:47.503694+00:00Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agentshttps://blog.schoergendorfer.com/post/smooth-minmax-a-differentiable-relaxation-for-codon-harmonization-2SecFeedde2026-08-27T07:48:47.470461+00:00Smooth $\%$MinMax: A Differentiable Relaxation for Codon Harmonizationhttps://blog.schoergendorfer.com/post/from-idea-to-prototype-in-an-afternoon-scaffolded-ai-assisted-rapid-va-prototypiSecFeedde2026-08-27T07:48:47.436266+00:00From Idea to Prototype in an Afternoon: Scaffolded, AI-Assisted Rapid VA Prototypinghttps://blog.schoergendorfer.com/post/robomme-interference-benchmarking-robot-memory-under-interference-2SecFeedde2026-08-27T07:48:47.403891+00:00RoboMME-Interference: Benchmarking Robot Memory Under Interferencehttps://blog.schoergendorfer.com/post/learning-to-prompt-improving-student-engagement-with-adaptive-llm-based-high-schSecFeedde2026-08-27T07:48:47.375898+00:00Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoringhttps://blog.schoergendorfer.com/post/claybuddy-a-framework-evaluation-mitigation-of-coding-agent-failures-2SecFeedde2026-08-27T07:48:47.350813+00:00ClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent Failureshttps://blog.schoergendorfer.com/post/when-probing-accuracy-saturates-fragility-resolves-a-complementary-metric-for-llSecFeedde2026-08-27T07:48:47.320441+00:00When Probing Accuracy Saturates, Fragility Resolves: A Complementary Metric for LLM Pre-Training Analysishttps://blog.schoergendorfer.com/post/online-pandoras-box-for-contextual-llm-cascadingSecFeedde2026-08-27T07:48:47.286703+00:00Online Pandora's Box for Contextual LLM Cascadinghttps://blog.schoergendorfer.com/post/send-a-scout-first-pre-hoc-reasoning-for-adaptive-detector-allocation-in-promptSecFeedde2026-08-27T07:48:47.254827+00:00Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defensehttps://blog.schoergendorfer.com/post/functional-entropy-predicting-functional-correctness-in-llm-generated-code-withSecFeedde2026-08-27T07:48:47.224852+00:00Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantificationhttps://blog.schoergendorfer.com/post/optimal-design-for-multinomial-logit-model-with-applications-to-best-assortmentSecFeedde2026-08-27T07:48:47.196410+00:00Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identificationhttps://blog.schoergendorfer.com/post/minimalist-visual-inertial-odometrySecFeedde2026-08-27T07:48:47.164133+00:00Minimalist Visual Inertial Odometryhttps://blog.schoergendorfer.com/post/reconstruction-of-personally-identifiable-information-from-proprietary-data-in-sSecFeedde2026-08-27T07:48:47.133467+00:00Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Modelshttps://blog.schoergendorfer.com/post/cross-domain-transfer-with-particle-physics-foundation-models-from-jets-to-neutrSecFeedde2026-08-27T07:48:47.100741+00:00Cross-Domain Transfer with Particle Physics Foundation Models: From Jets to Neutrino Interactionshttps://blog.schoergendorfer.com/post/decomposing-gradient-suppression-in-barren-plateaus-activity-sign-organization-aSecFeedde2026-08-27T07:48:47.062663+00:00Decomposing Gradient Suppression in Barren Plateaus: Activity, Sign Organization, and Couplinghttps://blog.schoergendorfer.com/post/regularized-latent-dynamics-prediction-is-a-strong-baseline-for-behavioral-foundSecFeedde2026-08-27T07:48:46.977624+00:00Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Modelshttps://blog.schoergendorfer.com/post/opensanctions-pairs-large-scale-entity-matching-with-llmsSecFeedde2026-08-27T07:48:46.935273+00:00OpenSanctions Pairs: Large-Scale Entity Matching with LLMshttps://blog.schoergendorfer.com/post/ttsr-test-time-self-evolving-via-reflectionSecFeedde2026-08-27T07:35:11.136298+00:00TTSR: Test-Time Self-Evolving via Reflectionhttps://blog.schoergendorfer.com/post/edge-local-and-qubit-efficient-quantum-graph-learning-for-the-nisq-era-2SecFeedde2026-08-27T07:35:11.091349+00:00Edge-Local and Qubit-Efficient Quantum Graph Learning for the NISQ Erahttps://blog.schoergendorfer.com/post/performance-uncertainty-in-medical-image-analysis-a-large-scale-investigation-ofSecFeedde2026-08-27T07:35:11.065589+00:00Performance uncertainty in medical image analysis: a large-scale investigation of confidence intervalshttps://blog.schoergendorfer.com/post/generalized-riesz-regression-a-unified-framework-for-debiased-machine-learning-wSecFeedde2026-08-27T07:35:11.017756+00:00Generalized Riesz Regression: A Unified Framework for Debiased Machine Learning with Riesz Representer Fitting under Bregman Divergencehttps://blog.schoergendorfer.com/post/iflip-iterative-feedback-driven-counterfactual-example-refinementSecFeedde2026-08-27T07:35:10.987672+00:00iFlip: Iterative Feedback-driven Counterfactual Example Refinementhttps://blog.schoergendorfer.com/post/ladder-up-memory-down-low-cost-fine-tuning-with-side-netsSecFeedde2026-08-27T07:35:10.960231+00:00Ladder Up, Memory Down: Low-Cost Fine-Tuning With Side Netshttps://blog.schoergendorfer.com/post/three-way-open-set-detection-for-robust-autonomous-navigationSecFeedde2026-08-27T07:35:10.935427+00:00Three-Way Open-Set Detection for Robust Autonomous Navigationhttps://blog.schoergendorfer.com/post/model-agnostic-open-set-air-to-air-visual-object-detection-for-reliable-uav-percSecFeedde2026-08-27T07:35:10.903577+00:00Model-Agnostic Open-Set Air-to-Air Visual Object Detection for Reliable UAV Perceptionhttps://blog.schoergendorfer.com/post/aiml-life-cycle-management-for-interoperable-ai-native-ranSecFeedde2026-08-27T07:35:10.874642+00:00AI/ML Life Cycle Management for Interoperable AI Native RANhttps://blog.schoergendorfer.com/post/evolutionary-chemical-learning-in-dimerization-networksSecFeedde2026-08-27T07:35:10.847149+00:00Evolutionary chemical learning in dimerization networkshttps://blog.schoergendorfer.com/post/gradient-based-sample-selection-for-faster-bayesian-optimizationSecFeedde2026-08-27T07:35:10.822515+00:00Gradient-based Sample Selection for Faster Bayesian Optimizationhttps://blog.schoergendorfer.com/post/thermodynamic-cost-of-inference-and-learning-in-physical-neural-networksSecFeedde2026-08-27T07:35:10.798909+00:00Thermodynamic cost of inference and learning in physical neural networkshttps://blog.schoergendorfer.com/post/generative-modeling-a-reviewSecFeedde2026-08-27T07:35:10.748488+00:00Generative Modeling: A Reviewhttps://blog.schoergendorfer.com/post/infer-humans-intentions-before-following-natural-language-instructionsSecFeedde2026-08-27T07:35:10.723361+00:00Infer Human's Intentions Before Following Natural Language Instructionshttps://blog.schoergendorfer.com/post/advancements-in-content-based-image-retrieval-a-comprehensive-survey-of-relevancSecFeedde2026-08-27T07:35:10.676173+00:00Advancements in Content-Based Image Retrieval: A Comprehensive Survey of Relevance Feedback Techniqueshttps://blog.schoergendorfer.com/post/iapo-influence-aware-policy-optimization-for-credit-assignment-in-multi-turn-ser-2SecFeedde2026-08-27T07:35:10.646113+00:00IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agentshttps://blog.schoergendorfer.com/post/jepa-x-cross-predictive-physics-grounding-for-forecastable-latent-dynamicsSecFeedde2026-08-27T07:17:49.793347+00:00JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamicshttps://blog.schoergendorfer.com/post/a-theory-of-speciation-in-generative-diffusion-models-on-compact-riemannian-mani-2SecFeedde2026-08-27T07:17:49.757819+00:00A Theory of Speciation in Generative Diffusion Models on Compact Riemannian Manifoldshttps://blog.schoergendorfer.com/post/beyond-point-predictions-uncertainty-aware-satellite-poverty-mapping-for-publicSecFeedde2026-08-27T07:17:49.718936+00:00Beyond Point Predictions: Uncertainty-Aware Satellite Poverty Mapping for Public Policyhttps://blog.schoergendorfer.com/post/fedcc-towards-addressing-label-distribution-skews-in-distillation-based-federate-2SecFeedde2026-08-27T07:17:49.688812+00:00FedCC: Towards Addressing Label Distribution Skews in Distillation-Based Federated Learninghttps://blog.schoergendorfer.com/post/clinical-graph-jepa-predictive-patient-state-knowledge-graphs-for-cognitive-deci-2SecFeedde2026-08-27T07:17:49.658316+00:00Clinical Graph-JEPA: Predictive Patient-State Knowledge Graphs for Cognitive Decision Supporthttps://blog.schoergendorfer.com/post/beyond-dense-adam-states-adaptive-log-space-quantization-for-memory-efficient-opSecFeedde2026-08-27T07:17:49.623521+00:00Beyond Dense Adam States: Adaptive Log-Space Quantization for Memory-Efficient Optimizershttps://blog.schoergendorfer.com/post/daw-dynamics-aware-weighting-for-deep-learning-forecasts-of-chaotic-systemsSecFeedde2026-08-27T07:17:49.593787+00:00DAW: Dynamics-Aware Weighting for Deep Learning Forecasts of Chaotic Systemshttps://blog.schoergendorfer.com/post/reinforcement-learning-on-benign-facts-amplifies-leakage-of-memorized-private-da-2SecFeedde2026-08-27T07:17:49.555283+00:00Reinforcement Learning on Benign Facts Amplifies Leakage of Memorized Private Datahttps://blog.schoergendorfer.com/post/trojaning-the-alignment-stealthy-backdoor-attacks-against-graph-foundation-model-2SecFeedde2026-08-27T07:17:49.515038+00:00Trojaning the Alignment: Stealthy Backdoor Attacks against Graph Foundation Modelshttps://blog.schoergendorfer.com/post/uncovering-the-limits-of-proof-sharing-for-neural-networks-2SecFeedde2026-08-27T07:17:49.480319+00:00Uncovering the Limits of Proof Sharing for Neural Networkshttps://blog.schoergendorfer.com/post/multi-source-complex-network-reconstruction-via-wasserstein-distributionally-rob-2SecFeedde2026-08-27T07:17:49.450599+00:00Multi-Source Complex Network Reconstruction via Wasserstein Distributionally Robust Optimization and Algorithm Unrollinghttps://blog.schoergendorfer.com/post/motosafety-edge-ai-with-learned-temporal-importance-for-two-wheeler-collision-ri-3SecFeedde2026-08-27T07:17:49.416653+00:00MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressurehttps://blog.schoergendorfer.com/post/scale-state-calibrated-latent-embeddings-for-jepa-planning-in-the-right-geometry-2SecFeedde2026-08-27T07:17:49.385938+00:00SCALE: State-Calibrated Latent Embeddings for JEPA Planning in the Right Geometryhttps://blog.schoergendorfer.com/post/towards-a-theory-of-inference-time-alignment-with-unknown-rewards-2SecFeedde2026-08-27T07:17:49.357388+00:00Towards a theory of inference-time alignment with unknown rewardshttps://blog.schoergendorfer.com/post/mitigating-rubric-interference-in-llm-judges-via-on-policy-self-distillation-2SecFeedde2026-08-27T07:17:49.328800+00:00Mitigating Rubric Interference in LLM Judges via On-Policy Self-Distillationhttps://blog.schoergendorfer.com/post/contrastive-learning-for-interpretable-anomaly-detection-at-collider-experiments-2SecFeedde2026-08-27T07:17:49.291315+00:00Contrastive Learning for Interpretable Anomaly Detection at Collider Experimentshttps://blog.schoergendorfer.com/post/riemannian-attention-mechanisms-for-transformers-a-theoretical-framework-and-arc-2SecFeedde2026-08-27T07:17:49.256733+00:00Riemannian Attention Mechanisms for Transformers: A Theoretical Framework and Architecture Designhttps://blog.schoergendorfer.com/post/adaptivity-via-a-parallel-architecture-for-stochastic-gradient-methodsSecFeedde2026-08-27T07:17:49.223415+00:00Adaptivity via a Parallel Architecture for Stochastic Gradient Methodshttps://blog.schoergendorfer.com/post/temporally-centered-sigreg-improves-leworldmodel-representations-for-robot-policSecFeedde2026-08-27T07:17:49.190135+00:00Temporally Centered SIGReg Improves LeWorldModel Representations for Robot Policy Learninghttps://blog.schoergendorfer.com/post/measuring-the-dependency-gap-diagnosing-inter-column-fidelity-in-tabular-generat-5SecFeedde2026-08-27T07:17:49.148139+00:00Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Modelshttps://blog.schoergendorfer.com/post/activation-steering-transfer-to-agents-one-gain-ratio-does-not-identify-potencySecFeedde2026-08-27T07:02:36.348253+00:00Activation Steering Transfer to Agents: One Gain Ratio Does Not Identify Potency and Efficacyhttps://blog.schoergendorfer.com/post/adaptive-bayes-exactly-tracks-information-over-intrinsic-time-2SecFeedde2026-08-27T07:02:36.317185+00:00Adaptive Bayes exactly tracks information over intrinsic timehttps://blog.schoergendorfer.com/post/emyx-fast-and-efficient-all-atom-protein-generationSecFeedde2026-08-27T07:02:36.252487+00:00Emyx: Fast and efficient all-atom protein generationhttps://blog.schoergendorfer.com/post/mode-modality-decomposed-expert-level-mixed-precision-quantization-for-moe-multiSecFeedde2026-08-27T07:02:36.217862+00:00MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMshttps://blog.schoergendorfer.com/post/mitigating-false-credit-propagation-probabilistic-graphical-reward-aggregation-fSecFeedde2026-08-27T07:02:36.180361+00:00Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learninghttps://blog.schoergendorfer.com/post/glucofm-a-dual-stream-foundation-model-for-continuous-glucose-monitoringSecFeedde2026-08-27T07:02:36.144858+00:00GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoringhttps://blog.schoergendorfer.com/post/amplifying-not-learning-the-price-of-out-of-distribution-generalization-in-ai-teSecFeedde2026-08-27T07:02:36.102911+00:00Amplifying, Not Learning: The Price of Out-of-Distribution Generalization in AI-Text Detectionhttps://blog.schoergendorfer.com/post/cubit-token-mixer-with-kernel-ridge-regressionSecFeedde2026-08-27T07:02:36.072363+00:00Cubit: Token Mixer with Kernel Ridge Regressionhttps://blog.schoergendorfer.com/post/jepamatch-geometric-representation-shaping-for-semi-supervised-learningSecFeedde2026-08-27T07:02:36.014656+00:00JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learninghttps://blog.schoergendorfer.com/post/reward-score-matching-unifying-reward-based-fine-tuning-for-flow-and-diffusion-mSecFeedde2026-08-27T07:02:35.982532+00:00Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Modelshttps://blog.schoergendorfer.com/post/stosignsgd-unbiased-structural-stochasticity-fixes-signsgd-for-training-large-laSecFeedde2026-08-27T07:02:35.952954+00:00StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Modelshttps://blog.schoergendorfer.com/post/loop-corrections-in-random-feature-models-training-error-and-generalization-gapSecFeedde2026-08-27T07:02:35.924511+00:00Loop Corrections in Random Feature Models: Training Error and Generalization Gaphttps://blog.schoergendorfer.com/post/multi-turn-reasoning-llms-for-task-offloading-in-mobile-edge-computingSecFeedde2026-08-27T07:02:35.845918+00:00Multi-Turn Reasoning LLMs for Task Offloading in Mobile Edge Computinghttps://blog.schoergendorfer.com/post/phase-consistent-magnetic-spectral-learning-for-multi-view-clusteringSecFeedde2026-08-27T07:02:35.817680+00:00Phase-Consistent Magnetic Spectral Learning for Multi-View Clusteringhttps://blog.schoergendorfer.com/post/spatio-temporal-dual-stage-hypergraph-marl-for-human-centric-multimodal-corridorSecFeedde2026-08-27T07:02:35.788896+00:00Spatio-temporal dual-stage hypergraph MARL for human-centric multimodal corridor traffic signal controlhttps://blog.schoergendorfer.com/post/maximum-volume-nonnegative-matrix-factorizationSecFeedde2026-08-27T07:02:35.759809+00:00Maximum-Volume Nonnegative Matrix Factorizationhttps://blog.schoergendorfer.com/post/same-stabilized-mixture-of-experts-for-multimodal-continual-instruction-tuningSecFeedde2026-08-27T06:48:02.512001+00:00SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuninghttps://blog.schoergendorfer.com/post/grip-algorithm-agnostic-machine-unlearning-for-mixture-of-experts-via-geometricSecFeedde2026-08-27T06:48:02.443525+00:00GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraintshttps://blog.schoergendorfer.com/post/stablepdenet-enhancing-neural-operator-stability-through-physics-informed-residuSecFeedde2026-08-27T06:48:02.409225+00:00StablePDENet: Enhancing Neural Operator Stability through Physics-Informed Residual-Sensitivity Regularizationhttps://blog.schoergendorfer.com/post/predicting-time-pressure-of-powered-two-wheeler-riders-for-proactive-safety-inteSecFeedde2026-08-27T06:48:02.374109+00:00Predicting Time Pressure of Powered Two-Wheeler Riders for Proactive Safety Interventionshttps://blog.schoergendorfer.com/post/a-comedy-of-estimators-on-kl-regularization-in-rl-training-of-llmsSecFeedde2026-08-27T06:48:02.339571+00:00A Comedy of Estimators: On KL Regularization in RL Training of LLMshttps://blog.schoergendorfer.com/post/epistemic-memory-a-validity-layer-for-self-maintaining-intelligent-systemsSecFeedde2026-08-27T06:48:02.275376+00:00Epistemic Memory: A Validity Layer for Self-Maintaining Intelligent Systemshttps://blog.schoergendorfer.com/post/algotrace-algorithmic-primitives-and-compositional-geometry-of-reasoning-in-langSecFeedde2026-08-27T06:48:02.242129+00:00AlgoTrace: Algorithmic Primitives and Compositional Geometry of Reasoning in Language Modelshttps://blog.schoergendorfer.com/post/onnx-net-towards-universal-representations-and-instant-performance-prediction-foSecFeedde2026-08-27T06:48:02.204750+00:00ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectureshttps://blog.schoergendorfer.com/post/banpick-enhancing-performance-and-efficiency-of-moe-llms-via-smarter-routingSecFeedde2026-08-27T06:48:02.113411+00:00Ban&Pick: Enhancing Performance and Efficiency of MoE-LLMs via Smarter Routinghttps://blog.schoergendorfer.com/post/learning-to-summarize-user-information-for-personalized-reinforcement-learning-fSecFeedde2026-08-27T06:48:02.076544+00:00Learning to summarize user information for personalized reinforcement learning from human feedbackhttps://blog.schoergendorfer.com/post/airl-s-unifying-reinforcement-learning-and-search-based-test-time-scaling-via-ad-2SecFeedde2026-08-27T06:48:02.037221+00:00AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learninghttps://blog.schoergendorfer.com/post/sample-margin-aware-recalibration-of-temperature-scalingSecFeedde2026-08-27T06:48:01.989625+00:00Sample Margin-Aware Recalibration of Temperature Scalinghttps://blog.schoergendorfer.com/post/scorpio-serving-right-requests-at-the-right-time-for-heterogeneous-slos-in-llm-iSecFeedde2026-08-27T06:48:01.946186+00:00Scorpio: Serving Right Requests at the Right Time for Heterogeneous SLOs in LLM Inferencehttps://blog.schoergendorfer.com/post/deep-greedy-unfolding-sorting-out-argsorting-in-greedy-sparse-recovery-algorithmSecFeedde2026-08-27T06:48:01.887511+00:00Deep greedy unfolding: Sorting out argsorting in greedy sparse recovery algorithmshttps://blog.schoergendorfer.com/post/emergent-abilities-in-large-language-models-a-surveySecFeedde2026-08-27T06:48:01.822637+00:00Emergent Abilities in Large Language Models: A Surveyhttps://blog.schoergendorfer.com/post/bridle-generalized-self-supervised-learning-with-quantizationSecFeedde2026-08-27T06:32:56.507881+00:00BRIDLE: Generalized Self-supervised Learning with Quantizationhttps://blog.schoergendorfer.com/post/deltagnn-graph-neural-network-with-information-flow-controlSecFeedde2026-08-27T06:32:56.474941+00:00DeltaGNN: Graph Neural Network with Information Flow Controlhttps://blog.schoergendorfer.com/post/a-general-purpose-framework-for-chemical-reaction-representation-with-atomic-corSecFeedde2026-08-27T06:32:56.443949+00:00A General-Purpose Framework for Chemical Reaction Representation with Atomic Correspondence and Flexible Condition Adaptationhttps://blog.schoergendorfer.com/post/optimal-time-complexity-algorithms-for-computing-general-random-walk-graph-kerneSecFeedde2026-08-27T06:32:56.412279+00:00Optimal Time Complexity Algorithms for Computing General Random Walk Graph Kernels on Sparse Graphshttps://blog.schoergendorfer.com/post/differentiated-aggregation-to-improve-generalization-in-federated-learningSecFeedde2026-08-27T06:32:56.343333+00:00Differentiated Aggregation to Improve Generalization in Federated Learninghttps://blog.schoergendorfer.com/post/noise-contrastive-estimation-based-matching-framework-for-low-resource-securitySecFeedde2026-08-27T06:32:56.308296+00:00Noise Contrastive Estimation-based Matching Framework for Low-Resource Security Attack Pattern Recognitionhttps://blog.schoergendorfer.com/post/theoretically-principled-federated-learning-for-balancing-privacy-and-utilitySecFeedde2026-08-27T06:32:56.274783+00:00Theoretically Principled Federated Learning for Balancing Privacy and Utilityhttps://blog.schoergendorfer.com/post/vbvr-pro-a-scalable-and-verifiable-suite-for-native-visual-reasoningSecFeedde2026-08-27T06:32:56.245990+00:00VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoninghttps://blog.schoergendorfer.com/post/myomechanix-biomechanically-grounded-compositional-skilled-activity-understandinSecFeedde2026-08-27T06:32:56.215412+00:00MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coachinghttps://blog.schoergendorfer.com/post/finding-and-using-interpretable-latents-in-a-neutrino-foundation-model-with-sparSecFeedde2026-08-27T06:32:56.183724+00:00Finding and using interpretable latents in a neutrino foundation model with sparse autoencodershttps://blog.schoergendorfer.com/post/planetary-prediction-engine-autonomous-geospatial-prediction-via-intelligent-datSecFeedde2026-08-27T06:32:56.148137+00:00Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddingshttps://blog.schoergendorfer.com/post/prefix-sliding-for-efficient-test-time-scalingSecFeedde2026-08-27T06:32:56.113658+00:00Prefix Sliding for efficient test-time scalinghttps://blog.schoergendorfer.com/post/r3-training-robots-to-reason-in-natural-language-via-reinforcement-learningSecFeedde2026-08-27T06:32:56.077500+00:00$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learninghttps://blog.schoergendorfer.com/post/cardiofusion-ai-robust-ecg-ppg-fusion-for-multimodal-physiological-monitoring-unSecFeedde2026-08-27T06:32:56.010466+00:00CardioFusion-AI: Robust ECG--PPG Fusion for Multimodal Physiological Monitoring Under Signal Degradationhttps://blog.schoergendorfer.com/post/frame-separating-sampling-variation-from-representational-cause-in-medical-imagiSecFeedde2026-08-27T06:32:55.973121+00:00FRAME: separating sampling variation from representational cause in medical imaging fairnesshttps://blog.schoergendorfer.com/post/lost-but-not-erased-finding-traces-of-a-forgotten-language-in-neural-speech-modeSecFeedde2026-08-27T06:32:55.933608+00:00Lost but not erased: Finding traces of a forgotten language in neural speech modelshttps://blog.schoergendorfer.com/post/scimif-understanding-multimodal-instruction-following-in-scientific-domainsSecFeedde2026-08-27T06:32:55.899765+00:00SciMIF: Understanding Multimodal Instruction Following in Scientific Domainshttps://blog.schoergendorfer.com/post/how-robust-are-automated-fact-checking-systems-a-cross-benchmark-evaluationSecFeedde2026-08-27T06:32:55.865949+00:00How Robust Are Automated Fact-Checking Systems? A Cross-Benchmark Evaluationhttps://blog.schoergendorfer.com/post/continually-learning-neural-operator-surrogate-for-three-dimensional-airborne-elSecFeedde2026-08-27T06:17:49.362459+00:00Continually learning neural-operator surrogate for three-dimensional airborne electromagnetic Bayesian inversionhttps://blog.schoergendorfer.com/post/controlling-for-omitted-variable-bias-in-deep-neural-networksSecFeedde2026-08-27T06:17:49.333949+00:00Controlling for Omitted Variable Bias in Deep Neural Networkshttps://blog.schoergendorfer.com/post/sample-a-systemc-ams-machine-learning-based-framework-for-virtual-prototypingSecFeedde2026-08-27T06:17:49.297345+00:00SAMpLE: A SystemC-AMS Machine LEarning-based Framework for Virtual Prototypinghttps://blog.schoergendorfer.com/post/metasieve-faster-relational-deep-learning-through-sql-based-metapath-selectionSecFeedde2026-08-27T06:17:49.259502+00:00MetaSieve: Faster Relational Deep Learning through SQL-Based Metapath Selectionhttps://blog.schoergendorfer.com/post/scalable-multi-gpu-simulation-of-3d-multicellular-growth-with-rnn-based-workloadSecFeedde2026-08-27T06:17:49.226356+00:00Scalable Multi-GPU Simulation of 3D Multicellular Growth with RNN-Based Workload Balancinghttps://blog.schoergendorfer.com/post/efficient-estimation-of-high-information-projections-using-nearest-neighboursSecFeedde2026-08-27T06:17:49.185307+00:00Efficient Estimation of High Information Projections using Nearest Neighbourshttps://blog.schoergendorfer.com/post/precipitation-downscaling-using-foundation-model-conditioned-diffusionSecFeedde2026-08-27T06:17:49.147076+00:00Precipitation Downscaling Using Foundation Model-Conditioned Diffusionhttps://blog.schoergendorfer.com/post/key-point-analysis-needs-structure-recovery-task-definition-dataset-diagnosis-anSecFeedde2026-08-27T06:17:49.117484+00:00Key Point Analysis Needs Structure Recovery: Task Definition, Dataset Diagnosis, and a Structure-Aware Benchmarkhttps://blog.schoergendorfer.com/post/why-ml-based-cough-models-do-not-generalize-a-systematic-cross-dataset-evaluatioSecFeedde2026-08-27T06:17:49.089117+00:00Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screeninghttps://blog.schoergendorfer.com/post/skill-issue-are-skills-language-invariant-in-llmsSecFeedde2026-08-27T06:17:49.060156+00:00Skill Issue: Are Skills Language-Invariant in LLMs?https://blog.schoergendorfer.com/post/flowmodl-model-based-deep-learning-with-conjugate-gradient-data-consistency-forSecFeedde2026-08-27T06:17:49.022687+00:00FlowMoDL: Model-Based Deep Learning with Conjugate-Gradient Data Consistency for Highly Accelerated 4D Flow MRI Reconstructionhttps://blog.schoergendorfer.com/post/unfolding-scientific-papers-into-multi-turn-generation-trajectories-for-continueSecFeedde2026-08-27T06:17:48.990926+00:00Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Traininghttps://blog.schoergendorfer.com/post/tacforcing-streaming-action-generation-with-execution-time-tactile-feedbackSecFeedde2026-08-27T06:17:48.959823+00:00TacForcing: Streaming Action Generation with Execution-Time Tactile Feedbackhttps://blog.schoergendorfer.com/post/large-language-model-few-shot-prompting-with-dilemma-training-outperforms-humanSecFeedde2026-08-27T06:17:48.930385+00:00Large Language Model Few-Shot Prompting with Dilemma Training Outperforms Human Surrogates in Predicting Patient Preferenceshttps://blog.schoergendorfer.com/post/lm-x-explainable-action-modeling-with-progress-event-and-uncertainty-predictionSecFeedde2026-08-27T06:17:48.899549+00:00LM-X: Explainable Action Modeling with Progress, Event, and Uncertainty Prediction for Generalist Robot Manipulationhttps://blog.schoergendorfer.com/post/memark-membrane-space-watermarking-for-spiking-neural-networksSecFeedde2026-08-27T06:17:48.861787+00:00MeMark: Membrane-Space Watermarking for Spiking Neural Networkshttps://blog.schoergendorfer.com/post/pointing-the-way-hiding-the-destination-practical-private-dense-retrieval-at-scaSecFeedde2026-08-27T06:17:48.819499+00:00Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scalehttps://blog.schoergendorfer.com/post/multi-output-gaussian-process-prediction-of-physical-fields-under-linear-equalitSecFeedde2026-08-27T06:17:48.779596+00:00Multi-output Gaussian process prediction of physical fields under linear equality constraintshttps://blog.schoergendorfer.com/post/unsupervised-anatomical-feature-learning-via-diffusion-models-enhanced-medical-iSecFeedde2026-08-27T06:17:48.751616+00:00Unsupervised Anatomical Feature Learning via Diffusion Models: Enhanced Medical Image Segmentation with Denoising Diffusion Probabilistic Modelshttps://blog.schoergendorfer.com/post/fast-rates-in-bayesian-online-learning-with-approximate-posteriorsSecFeedde2026-08-27T06:17:48.722099+00:00Fast rates in Bayesian online learning with approximate posteriorshttps://blog.schoergendorfer.com/post/learning-new-facts-with-qlora-an-acquisition-retention-frontierSecFeedde2026-08-27T06:02:42.935905+00:00Learning New Facts with QLoRA: An Acquisition-Retention Frontierhttps://blog.schoergendorfer.com/post/narcissus-program-synthesis-using-context-aware-llm-approximationsSecFeedde2026-08-27T06:02:42.903651+00:00Narcissus: Program Synthesis Using Context-Aware LLM Approximationshttps://blog.schoergendorfer.com/post/jit-agent-scaling-harness-intelligence-via-just-in-time-harness-evolutionSecFeedde2026-08-27T06:02:42.871102+00:00JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolutionhttps://blog.schoergendorfer.com/post/a-hierarchical-synergistic-deep-learning-framework-integrating-composition-strucSecFeedde2026-08-27T06:02:42.806056+00:00A Hierarchical Synergistic Deep Learning Framework Integrating Composition, Structure, and Ionic Transport for Solid-State Electrolyte Discoveryhttps://blog.schoergendorfer.com/post/cropcop-an-auditable-120-class-plant-health-model-from-benchmark-reconstructionSecFeedde2026-08-27T06:02:42.769521+00:00CropCop: An Auditable 120-Class Plant-Health Model from Benchmark Reconstruction to a Quantised Runtime Artifacthttps://blog.schoergendorfer.com/post/adaptive-hybrid-subspace-levenberg-marquardt-algorithm-with-adequacy-monitor-forSecFeedde2026-08-27T06:02:42.732111+00:00Adaptive Hybrid Subspace Levenberg Marquardt Algorithm with Adequacy Monitor for Large Scale Least Squares Problemshttps://blog.schoergendorfer.com/post/adaptive-regularization-for-random-features-a-neighboring-early-stopping-rule-wiSecFeedde2026-08-27T06:02:42.698411+00:00Adaptive Regularization for Random Features: A Neighboring Early-Stopping Rule with Oracle-Rate Guaranteeshttps://blog.schoergendorfer.com/post/a-multi-view-coupled-tensor-decomposition-for-lightweight-online-adaptive-traffiSecFeedde2026-08-27T06:02:42.662304+00:00A Multi-View Coupled Tensor Decomposition for Lightweight Online Adaptive Traffic Predictionhttps://blog.schoergendorfer.com/post/aeris-offline-policy-improvement-for-multi-uav-integrated-sensing-and-communicatSecFeedde2026-08-27T06:02:42.628748+00:00AERIS: Offline Policy Improvement for Multi-UAV Integrated Sensing and Communicationhttps://blog.schoergendorfer.com/post/functional-linear-regression-from-sparse-to-dense-designs-a-pooling-ridge-methodSecFeedde2026-08-27T06:02:42.595543+00:00Functional linear regression from sparse to dense designs: a pooling-ridge method and minimax optimalityhttps://blog.schoergendorfer.com/post/training-alignment-auditors-via-reinforcement-learningSecFeedde2026-08-27T06:02:42.564339+00:00Training Alignment Auditors via Reinforcement Learninghttps://blog.schoergendorfer.com/post/energy-yield-and-lifetime-climate-classification-via-machine-learning-for-optimiSecFeedde2026-08-27T06:02:42.528633+00:00Energy Yield and Lifetime Climate Classification via Machine Learning for Optimizing Photovoltaic Module Design and Materialshttps://blog.schoergendorfer.com/post/bvr-sim-an-open-and-high-throughput-environment-for-heterogeneous-air-combat-reiSecFeedde2026-08-27T06:02:42.429687+00:00BVR Sim: An Open and High-Throughput Environment for Heterogeneous Air-Combat Reinforcement Learninghttps://blog.schoergendorfer.com/post/token-oriented-semantic-communication-with-pretrained-vision-transformersSecFeedde2026-08-27T06:02:42.391258+00:00Token-Oriented Semantic Communication with Pretrained Vision Transformershttps://blog.schoergendorfer.com/post/cramer-control-via-request-aware-masking-for-editing-recommendersSecFeedde2026-08-27T06:02:42.333540+00:00CRAMER: Control via Request-Aware Masking for Editing Recommendershttps://blog.schoergendorfer.com/post/sauss-stochastic-approximation-with-unbiased-simulated-scores-for-limited-dependSecFeedde2026-08-27T06:02:42.301733+00:00SAUSS: Stochastic Approximation with Unbiased Simulated Scores for Limited Dependent Variable Modelshttps://blog.schoergendorfer.com/post/wave-reversing-the-guidance-hierarchy-for-coarse-to-fine-guided-depth-super-resoSecFeedde2026-08-27T05:47:36.162093+00:00WAVE: Reversing the Guidance Hierarchy for Coarse-to-Fine Guided Depth Super-Resolutionhttps://blog.schoergendorfer.com/post/generative-action-chunk-sampling-for-adaptive-stiffness-control-in-physical-humaSecFeedde2026-08-27T05:47:36.119216+00:00Generative Action-Chunk Sampling for Adaptive Stiffness Control in Physical Human-Robot Collaborationhttps://blog.schoergendorfer.com/post/from-memorization-to-absorption-mixed-policy-rl-for-continual-knowledge-injectioSecFeedde2026-08-27T05:47:36.091367+00:00From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injectionhttps://blog.schoergendorfer.com/post/trustformer-cross-temporal-and-cross-dimensional-transformer-for-task-specific-mSecFeedde2026-08-27T05:47:36.063752+00:00TrustFormer: Cross-Temporal and Cross- Dimensional Transformer for Task-Specific Multi-Dimensional Trust Evaluationhttps://blog.schoergendorfer.com/post/multi-view-trust-evaluation-for-collaborator-selection-via-evidential-deep-learnSecFeedde2026-08-27T05:47:36.037665+00:00Multi-View Trust Evaluation for Collaborator Selection via Evidential Deep Learninghttps://blog.schoergendorfer.com/post/simulating-cognitive-smart-freight-corridors-with-agent-based-models-and-reinforSecFeedde2026-08-27T05:47:36.008237+00:00Simulating Cognitive Smart Freight Corridors with Agent-Based Models and Reinforcement Learninghttps://blog.schoergendorfer.com/post/banglamamba-exploring-state-space-models-for-bangla-fake-news-detectionSecFeedde2026-08-27T05:47:35.976397+00:00BanglaMamba: Exploring State Space Models for Bangla Fake News Detectionhttps://blog.schoergendorfer.com/post/minimax-alternating-regret-for-the-experts-problem-and-online-convex-optimizatioSecFeedde2026-08-27T05:47:35.939064+00:00Minimax Alternating Regret for the Experts Problem and Online Convex Optimizationhttps://blog.schoergendorfer.com/post/lowering-the-barrier-to-ai-driven-inspection-a-no-code-workflow-for-automated-stSecFeedde2026-08-27T05:47:35.908647+00:00Lowering the Barrier to AI-Driven Inspection: A No-Code Workflow for Automated Structural Defect Detectionhttps://blog.schoergendorfer.com/post/romnet-a-hybrid-reduced-order-modeling-and-machine-learning-approach-to-waveformSecFeedde2026-08-27T05:47:35.877418+00:00ROMNet: a hybrid reduced order modeling and machine learning approach to waveform inversionhttps://blog.schoergendorfer.com/post/fuzzingbrain-bench-v1-evaluating-open-ended-bug-discovery-by-llmsSecFeedde2026-08-27T05:47:35.849571+00:00FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMshttps://blog.schoergendorfer.com/post/towards-reliable-generalizable-and-specific-in-context-knowledge-editing-via-mulSecFeedde2026-08-27T05:47:35.821211+00:00Towards Reliable, Generalizable, and Specific In-Context Knowledge Editing via Multi-Objective Reinforcement Learninghttps://blog.schoergendorfer.com/post/scalable-self-supervised-learning-for-multiphase-ac-opf-in-distribution-systemsSecFeedde2026-08-27T05:47:35.792761+00:00Scalable Self-Supervised Learning for Multiphase AC-OPF in Distribution Systems with Topology Reconfigurationhttps://blog.schoergendorfer.com/post/improved-analysis-for-hessian-free-high-resolution-monte-carlo-samplingSecFeedde2026-08-27T05:47:35.740165+00:00Improved Analysis for Hessian-free High-resolution Monte Carlo Samplinghttps://blog.schoergendorfer.com/post/encotess-age-sensitive-encodings-from-raw-tess-light-curvesSecFeedde2026-08-27T05:47:35.691933+00:00EncoTESS: Age-Sensitive Encodings from Raw TESS Light Curveshttps://blog.schoergendorfer.com/post/the-imperfective-paradox-is-not-necessarily-in-large-language-models-a-benchmarkSecFeedde2026-08-27T05:47:35.661268+00:00The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failurehttps://blog.schoergendorfer.com/post/does-fine-tuning-undo-activation-steering-behavioural-recovery-without-weight-edSecFeedde2026-08-27T05:47:35.625642+00:00Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversalhttps://blog.schoergendorfer.com/post/common-center-geometry-and-certified-radial-reconstruction-for-energy-form-fullSecFeedde2026-08-27T05:32:42.414111+00:00Common-Center Geometry and Certified Radial Reconstruction for Energy-Form Full Conformal Regionshttps://blog.schoergendorfer.com/post/beyond-tokens-probing-higher-order-epistasis-in-learned-protein-representationsSecFeedde2026-08-27T05:32:42.382231+00:00Beyond Tokens: Probing Higher-Order Epistasis in Learned Protein Representationshttps://blog.schoergendorfer.com/post/the-dialect-tax-dialectal-biases-persist-throughout-the-language-modeling-pipeliSecFeedde2026-08-27T05:32:42.353870+00:00The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipelinehttps://blog.schoergendorfer.com/post/modality-contribution-score-a-per-patient-framework-for-quantifying-the-relativeSecFeedde2026-08-27T05:32:42.329611+00:00Modality Contribution Score - A Per-Patient Framework for Quantifying the Relative Diagnostic Contribution of Structural MRI and Amyloid PET in Alzheimer's Diseasehttps://blog.schoergendorfer.com/post/pa-cot-profile-adaptive-chain-of-thought-for-personalized-nutritional-consultingSecFeedde2026-08-27T05:32:42.300656+00:00PA-CoT: Profile-Adaptive Chain-of-Thought for Personalized Nutritional Consultinghttps://blog.schoergendorfer.com/post/evidence-grounded-mapping-of-multimodal-human-sensing-psychological-transdiagnosSecFeedde2026-08-27T05:32:42.271149+00:00Evidence-Grounded Mapping of Multimodal Human Sensing Psychological Transdiagnostic Dimensionshttps://blog.schoergendorfer.com/post/detection-reliable-control-decodable-empathy-directions-yield-at-most-partial-shSecFeedde2026-08-27T05:32:42.239784+00:00Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scoreshttps://blog.schoergendorfer.com/post/forecasting-weather-driven-price-dynamics-across-sri-lankan-tea-market-catalogueSecFeedde2026-08-27T05:32:42.209253+00:00Forecasting Weather-Driven Price Dynamics Across Sri Lankan Tea Market Catalogueshttps://blog.schoergendorfer.com/post/same-player-verification-for-account-consistency-in-counter-strike-2SecFeedde2026-08-27T05:32:42.181423+00:00Same-Player Verification for Account Consistency in Counter-Strike 2https://blog.schoergendorfer.com/post/agentic-autoresearch-for-cell-edge-power-control-radically-redefining-the-researSecFeedde2026-08-27T05:32:42.148105+00:00Agentic Autoresearch for Cell-Edge Power Control: Radically Redefining the Researcher's Rolehttps://blog.schoergendorfer.com/post/traceml-an-empirical-analysis-of-human-agent-planning-in-machine-learning-develoSecFeedde2026-08-27T05:32:42.116907+00:00TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Developmenthttps://blog.schoergendorfer.com/post/group-shared-low-rank-approximation-for-mobile-efficient-pointwise-convolutionsSecFeedde2026-08-27T05:32:42.057421+00:00Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNshttps://blog.schoergendorfer.com/post/how-much-rank-does-lora-need-rank-error-bounds-for-transformer-attentionSecFeedde2026-08-27T05:32:42.030117+00:00How Much Rank Does LoRA Need? Rank-Error Bounds for Transformer Attentionhttps://blog.schoergendorfer.com/post/robust-curvemoe-multi-norm-adversarial-defense-for-mixture-of-experts-models-viaSecFeedde2026-08-27T05:32:42.002150+00:00Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivityhttps://blog.schoergendorfer.com/post/spectral-allocation-why-muon-outperforms-adam-and-how-to-improve-muonSecFeedde2026-08-27T05:32:41.941468+00:00Spectral Allocation: Why Muon Outperforms Adam, and How to Improve Muonhttps://blog.schoergendorfer.com/post/when-pruning-meets-interpretability-preserving-sparse-autoencoder-robustness-inSecFeedde2026-08-27T05:32:41.908904+00:00When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMshttps://blog.schoergendorfer.com/post/one-symptom-three-levers-a-critical-review-of-on-policy-self-distillationSecFeedde2026-08-27T05:17:39.067557+00:00One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillationhttps://blog.schoergendorfer.com/post/quantum-inspired-modeling-of-driving-behaviorSecFeedde2026-08-27T05:17:39.032417+00:00Quantum-Inspired Modeling of Driving Behaviorhttps://blog.schoergendorfer.com/post/forecasting-multiple-observables-with-scroll-score-trained-uncertainty-for-stochSecFeedde2026-08-27T05:17:39.001995+00:00Forecasting Multiple Observables with SCROLL: Score-Trained Uncertainty for Stochastic Dynamicshttps://blog.schoergendorfer.com/post/towards-a-unified-information-bottleneck-framework-for-time-series-explanationsSecFeedde2026-08-27T05:17:38.973414+00:00Towards A Unified Information Bottleneck Framework for Time Series Explanationshttps://blog.schoergendorfer.com/post/a-general-purpose-molecular-foundation-model-transfers-across-diverse-olfactorySecFeedde2026-08-27T05:17:38.944563+00:00A General-Purpose Molecular Foundation Model Transfers Across Diverse Olfactory Taskshttps://blog.schoergendorfer.com/post/how-edge-of-stability-hinders-scaffold-in-federated-optimizationSecFeedde2026-08-27T05:17:38.901758+00:00How Edge of Stability Hinders SCAFFOLD in Federated Optimizationhttps://blog.schoergendorfer.com/post/cedar-controlled-and-event-driven-demand-forecasting-via-residual-decompositionSecFeedde2026-08-27T05:17:38.870038+00:00CEDAR: Controlled and Event-Driven Demand Forecasting via Residual Decompositionhttps://blog.schoergendorfer.com/post/vincent-validated-interaction-network-for-cross-drug-explanation-of-therapeuticsSecFeedde2026-08-27T05:17:38.826711+00:00VINCENT: Validated Interaction Network for Cross-drug Explanation of Therapeuticshttps://blog.schoergendorfer.com/post/learning-continuous-regional-temperature-fields-with-lead-time-and-resolution-quSecFeedde2026-08-27T05:17:38.793311+00:00Learning Continuous Regional Temperature Fields with Lead-Time and Resolution Querieshttps://blog.schoergendorfer.com/post/geometry-constrained-kolmogorov-arnold-networks-learning-edge-geometry-via-banacSecFeedde2026-08-27T05:17:38.731124+00:00Geometry-Constrained Kolmogorov-Arnold Networks: Learning Edge Geometry via Banach Dualityhttps://blog.schoergendorfer.com/post/exaone-tabular-10-technical-reportSecFeedde2026-08-27T05:17:38.672134+00:00EXAONE Tabular 1.0 : Technical Reporthttps://blog.schoergendorfer.com/post/drift-aware-multimodal-user-representation-learning-via-multi-scale-temporal-modSecFeedde2026-08-27T05:17:38.629101+00:00Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Expertshttps://blog.schoergendorfer.com/post/learning-from-waste-machine-learning-for-health-risk-prediction-and-computer-visSecFeedde2026-08-27T05:17:38.598165+00:00Learning from waste: Machine Learning for health risk prediction and computer vision-based sorting in Ghanahttps://blog.schoergendorfer.com/post/tailsft-filtered-fine-tuning-improves-post-training-performanceSecFeedde2026-08-27T05:17:38.567903+00:00TailSFT: Filtered Fine-Tuning Improves Post-Training Performancehttps://blog.schoergendorfer.com/post/comparing-corrupted-constrained-learning-problemsSecFeedde2026-08-27T05:17:38.533416+00:00Comparing Corrupted Constrained Learning Problemshttps://blog.schoergendorfer.com/post/a-constitutive-markov-physics-informed-neural-operator-mpno-for-autoregressive-sSecFeedde2026-08-27T05:17:38.500581+00:00A Constitutive Markov Physics-Informed Neural Operator (MPNO) for Autoregressive Stability in Transient Dynamicshttps://blog.schoergendorfer.com/post/are-llm-enhanced-gnns-privacy-safeSecFeedde2026-08-27T05:17:38.468124+00:00Are LLM-Enhanced GNNs Privacy-Safe?https://blog.schoergendorfer.com/post/why-does-graph-learning-fail-to-fully-benefit-from-a-text-teacherSecFeedde2026-08-27T05:17:38.439114+00:00Why Does Graph Learning Fail to Fully Benefit from a Text Teacher?https://blog.schoergendorfer.com/post/fairness-aware-test-time-prompt-tuningSecFeedde2026-08-27T05:02:44.159485+00:00Fairness-Aware Test-Time Prompt Tuninghttps://blog.schoergendorfer.com/post/tropospheric-temperature-and-humidity-profile-retrieval-from-meteosat-flexible-cSecFeedde2026-08-27T05:02:44.129704+00:00Tropospheric temperature and humidity profile retrieval from Meteosat Flexible Combined Imager based on deep learninghttps://blog.schoergendorfer.com/post/modeling-spatio-temporal-locality-in-multi-step-forecasting-of-geo-referenced-tiSecFeedde2026-08-27T05:02:44.097886+00:00Modeling spatio-temporal locality in multi-step forecasting of geo-referenced time serieshttps://blog.schoergendorfer.com/post/ldac-net-a-learnable-multi-lag-differencing-attention-convolution-network-for-drSecFeedde2026-08-27T05:02:44.036161+00:00LDAC-Net: A Learnable Multi-Lag Differencing Attention-Convolution Network for Drift-Robust Recognition with Low-Cost MOX Gas Sensorshttps://blog.schoergendorfer.com/post/a-token-level-analysis-of-sampled-token-reverse-kl-on-policy-distillationSecFeedde2026-08-27T05:02:44.003371+00:00A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillationhttps://blog.schoergendorfer.com/post/dceo-direct-causal-effect-optimization-for-long-term-user-value-modeling-in-e-coSecFeedde2026-08-27T05:02:43.974768+00:00DCEO: Direct Causal Effect Optimization for Long-Term User Value Modeling in E-commerce Searchhttps://blog.schoergendorfer.com/post/frequency-aware-forecasting-for-short-term-typhoon-gust-predictionSecFeedde2026-08-27T05:02:43.934348+00:00Frequency-aware forecasting for short-term typhoon gust predictionhttps://blog.schoergendorfer.com/post/beyond-scaling-self-evolving-llm-agents-for-hardware-kernel-optimization-via-anSecFeedde2026-08-27T05:02:43.846997+00:00Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memoryhttps://blog.schoergendorfer.com/post/physics-informed-foresight-pruning-for-sparse-pinn-solvers-of-nonlinear-pdesSecFeedde2026-08-27T05:02:43.814558+00:00Physics-Informed Foresight Pruning for Sparse PINN Solvers of Nonlinear PDEshttps://blog.schoergendorfer.com/post/beyond-optimal-rates-in-stochastic-optimization-trajectory-adaptive-stopping-rulSecFeedde2026-08-27T05:02:43.787497+00:00Beyond Optimal Rates in Stochastic Optimization: Trajectory-Adaptive Stopping Ruleshttps://blog.schoergendorfer.com/post/interpreting-protein-language-model-embeddings-via-orthogonal-projection-for-proSecFeedde2026-08-27T05:02:43.745346+00:00Interpreting Protein Language Model Embeddings via Orthogonal Projection for Protein Fitness Predictionhttps://blog.schoergendorfer.com/post/reflection-steering-disentangling-reflection-from-reasoning-in-activation-spaceSecFeedde2026-08-27T05:02:43.718671+00:00Reflection Steering: Disentangling Reflection from Reasoning in Activation Space for Token-Efficient Inferencehttps://blog.schoergendorfer.com/post/fedqos-federated-qos-risk-learning-for-heterogeneous-indoor-outdoor-access-selecSecFeedde2026-08-27T05:02:43.693722+00:00FedQoS: Federated QoS-Risk Learning for Heterogeneous Indoor-Outdoor Access Selectionhttps://blog.schoergendorfer.com/post/resilient-decentralized-wireless-federated-learning-via-gradient-tracking-with-aSecFeedde2026-08-27T05:02:43.662676+00:00Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamWhttps://blog.schoergendorfer.com/post/a-storage-retrieval-gap-in-parametric-knowledge-graph-memorySecFeedde2026-08-27T05:02:43.631950+00:00A Storage-Retrieval Gap in Parametric Knowledge Graph Memoryhttps://blog.schoergendorfer.com/post/resolving-multi-modal-regression-by-difference-quotient-based-clusteringfast-coaSecFeedde2026-08-27T05:02:43.596648+00:00Resolving Multi-Modal Regression by Difference-Quotient-Based Clustering:Fast Coarse Conditional-Label Assignmenthttps://blog.schoergendorfer.com/post/joint-initialization-of-flux-networks-and-effective-multiplication-factor-for-phSecFeedde2026-08-27T04:48:26.116534+00:00Joint Initialization of Flux Networks and Effective Multiplication Factor for Physics-Informed Neural Networks Solving Neutron Diffusion Problemshttps://blog.schoergendorfer.com/post/refusal-geometry-reflects-refusal-training-diverse-refusal-prefixes-can-raise-stSecFeedde2026-08-27T04:48:26.075715+00:00Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attackshttps://blog.schoergendorfer.com/post/pasta-noisy-node-classification-with-partial-label-learningSecFeedde2026-08-27T04:48:26.042366+00:00PaSta: Noisy Node Classification with Partial Label Learninghttps://blog.schoergendorfer.com/post/beyond-pairwise-feedback-listwise-vision-language-supervision-for-preference-basSecFeedde2026-08-27T04:48:26.013728+00:00Beyond Pairwise Feedback: Listwise Vision-Language Supervision for Preference-Based Reward Learninghttps://blog.schoergendorfer.com/post/escaping-low-dimensional-overlap-multi-task-model-merging-via-high-dimensional-sSecFeedde2026-08-27T04:48:25.983753+00:00Escaping Low-Dimensional Overlap: Multi-Task Model Merging via High-Dimensional Sparse Disentanglementhttps://blog.schoergendorfer.com/post/neither-precision-nor-architecture-alone-controlled-tests-of-failure-remedies-foSecFeedde2026-08-27T04:48:25.955721+00:00Neither Precision Nor Architecture Alone: Controlled Tests of Failure Remedies for Physics-Informed Neural Networkshttps://blog.schoergendorfer.com/post/two-dimensions-govern-agnostic-multiclass-transductive-learningSecFeedde2026-08-27T04:48:25.928172+00:00Two Dimensions Govern Agnostic Multiclass Transductive Learninghttps://blog.schoergendorfer.com/post/activation-space-order-swap-geometry-a-site-asymmetry-auditSecFeedde2026-08-27T04:48:25.901086+00:00Activation-Space Order-Swap Geometry: A Site-Asymmetry Audithttps://blog.schoergendorfer.com/post/insightsr-refining-symbolic-regression-search-spaces-via-parallel-semantic-and-sSecFeedde2026-08-27T04:48:25.848785+00:00InsightSR: Refining Symbolic Regression Search Spaces via Parallel Semantic and Structural LLM Guidancehttps://blog.schoergendorfer.com/post/shsp-structure-aware-hierarchical-solution-prediction-for-mixed-integer-linear-pSecFeedde2026-08-27T04:48:25.816286+00:00SHSP: Structure-Aware Hierarchical Solution Prediction for Mixed-Integer Linear Programminghttps://blog.schoergendorfer.com/post/mitigating-llm-sycophancy-with-rl-based-fine-tuning-bayesian-truth-serum-approacSecFeedde2026-08-27T04:48:25.786394+00:00Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approachhttps://blog.schoergendorfer.com/post/neural-bayesian-structure-learning-for-discrete-choice-modelingSecFeedde2026-08-27T04:48:25.759043+00:00Neural-Bayesian Structure Learning for Discrete Choice Modelinghttps://blog.schoergendorfer.com/post/shuttlearena-interpretable-self-play-in-physics-based-badmintonSecFeedde2026-08-27T04:48:25.727022+00:00ShuttleArena: Interpretable Self-Play in Physics-Based Badmintonhttps://blog.schoergendorfer.com/post/long-term-behavioral-evaluation-for-trusted-collaborator-selection-via-bidirectiSecFeedde2026-08-27T04:48:25.699609+00:00Long-Term Behavioral Evaluation for Trusted Collaborator Selection via Bidirectional Mambahttps://blog.schoergendorfer.com/post/output-dilution-redundant-but-fragile-representations-in-moe-modelsSecFeedde2026-08-27T04:48:25.667310+00:00Output Dilution: Redundant but Fragile Representations in MoE Modelshttps://blog.schoergendorfer.com/post/representing-max-functions-using-two-hidden-layer-relu-networksSecFeedde2026-08-27T04:48:25.635372+00:00Representing MAX functions using two-hidden-layer ReLU networkshttps://blog.schoergendorfer.com/post/trust-the-mass-forced-weights-in-kv-cache-evictionSecFeedde2026-08-27T04:48:25.605668+00:00Trust the Mass: Forced Weights in KV-Cache Evictionhttps://blog.schoergendorfer.com/post/libribrain100-one-hundred-hours-of-broad-and-deep-meg-data-for-neural-speech-decSecFeedde2026-08-27T04:48:25.575436+00:00LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scalehttps://blog.schoergendorfer.com/post/learning-mixtures-of-plackett-luce-models-for-multi-objective-alignmentSecFeedde2026-08-27T04:48:25.538467+00:00Learning Mixtures of Plackett-Luce Models for Multi-Objective Alignmenthttps://blog.schoergendorfer.com/post/hyperbolic-latent-geometry-for-tree-structured-prototype-networks-a-local-vs-gloSecFeedde2026-08-27T04:32:43.102184+00:00Hyperbolic Latent Geometry for Tree-Structured Prototype Networks: A Local-vs-Global Trade-offhttps://blog.schoergendorfer.com/post/what-should-a-large-language-model-see-physical-invariants-as-a-data-representatSecFeedde2026-08-27T04:32:43.069877+00:00What Should a Large Language Model See? Physical Invariants as a Data Representation for PDE Discoveryhttps://blog.schoergendorfer.com/post/transforms-for-llm-quantization-the-great-inversion-and-format-co-designSecFeedde2026-08-27T04:32:43.034805+00:00Transforms for LLM Quantization: The Great Inversion and Format Co-Designhttps://blog.schoergendorfer.com/post/simultaneous-inference-of-environmental-and-interaction-forces-in-collective-dynSecFeedde2026-08-27T04:32:42.998734+00:00Simultaneous inference of environmental and interaction forces in collective dynamicshttps://blog.schoergendorfer.com/post/snap-kg-streaming-node-assignment-via-projection-for-knowledge-graph-entity-inteSecFeedde2026-08-27T04:32:42.933359+00:00SNAP-KG: Streaming Node Assignment via Projection for Knowledge Graph Entity Integrationhttps://blog.schoergendorfer.com/post/drift-variation-autoencoder-unifying-generation-and-representation-learning-throSecFeedde2026-08-27T04:32:42.901022+00:00Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matchinghttps://blog.schoergendorfer.com/post/rethinking-the-transferable-adversarial-attacks-and-robust-defense-in-federatedSecFeedde2026-08-27T04:32:42.860883+00:00Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learninghttps://blog.schoergendorfer.com/post/when-does-context-routing-help-a-systematic-study-of-multi-modal-fusion-in-timeSecFeedde2026-08-27T04:32:42.795634+00:00When Does Context Routing Help? A Systematic Study of Multi-Modal Fusion in Time Series Forecastinghttps://blog.schoergendorfer.com/post/multimodal-injury-risk-prediction-in-tennisSecFeedde2026-08-27T04:32:42.757445+00:00Multimodal Injury Risk Prediction in Tennishttps://blog.schoergendorfer.com/post/toward-machine-learning-with-the-unit-as-a-primitive-learning-from-unit-linked-eSecFeedde2026-08-27T04:32:42.724438+00:00Toward Machine Learning with the Unit as a Primitive: Learning from Unit-Linked Eventshttps://blog.schoergendorfer.com/post/grape-gradient-refinement-and-progress-aware-exploitation-for-query-efficient-hiSecFeedde2026-08-27T04:32:42.687324+00:00GRAPE: Gradient Refinement and Progress-Aware Exploitation for Query-Efficient High-Dimensional Bayesian Optimizationhttps://blog.schoergendorfer.com/post/flower-hub-a-reproducible-benchmarking-platform-for-federated-learning-in-simulaSecFeedde2026-08-27T04:32:42.653367+00:00Flower Hub: A Reproducible Benchmarking Platform for Federated Learning in Simulation and Deploymenthttps://blog.schoergendorfer.com/post/understanding-the-energy-scaling-of-large-language-model-inference-across-contexSecFeedde2026-08-27T04:32:42.618008+00:00Understanding the Energy Scaling of Large Language Model Inference Across Context Lengths and Attention Architectureshttps://blog.schoergendorfer.com/post/the-von-neumann-state-space-transformer-for-neural-decodingSecFeedde2026-08-27T04:32:42.581877+00:00The Von-Neumann State-Space Transformer for neural decodinghttps://blog.schoergendorfer.com/post/the-frame-kernel-method-for-multiscale-operator-learningSecFeedde2026-08-27T04:32:42.543513+00:00The Frame Kernel Method for Multiscale Operator Learninghttps://blog.schoergendorfer.com/post/nvexplain-explaining-time-series-forecasting-with-latent-trajectory-analysis-andSecFeedde2026-08-27T04:32:42.511069+00:00NVExplain: Explaining Time Series Forecasting with Latent Trajectory Analysis and Structure-Preserving Surrogateshttps://blog.schoergendorfer.com/post/demmo-longitudinal-and-cross-disease-modelling-of-digital-mobility-outcomes-viaSecFeedde2026-08-27T04:32:42.472660+00:00DeMMO: Longitudinal and Cross-Disease Modelling of Digital Mobility Outcomes via Multi-Task Learninghttps://blog.schoergendorfer.com/post/on-the-representational-geometry-of-dynamic-programsSecFeedde2026-08-27T04:32:42.438244+00:00On the Representational Geometry of Dynamic Programshttps://blog.schoergendorfer.com/post/rollout-decoded-reconstruction-for-long-horizon-prediction-in-latent-world-modelSecFeedde2026-08-27T04:32:42.404797+00:00Rollout-Decoded Reconstruction for Long-Horizon Prediction in Latent World Modelshttps://blog.schoergendorfer.com/post/d3-mopd-adaptive-dynamic-domain-scheduling-for-efficient-multi-teacher-distillatSecFeedde2026-08-27T04:17:40.221203+00:00D$^3$-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillationhttps://blog.schoergendorfer.com/post/msr-iva-masked-structural-residual-independent-vector-analysis-for-state-aware-fSecFeedde2026-08-27T04:17:40.196518+00:00MSR-IVA: Masked Structural Residual Independent Vector Analysis for State-Aware Fusion of Structural MRI and Dynamic Functional Network Connectivityhttps://blog.schoergendorfer.com/post/clearing-the-underbrush-ai-enhanced-rf-interference-suppressionSecFeedde2026-08-27T04:17:40.170880+00:00Clearing the Underbrush: AI-Enhanced RF Interference Suppressionhttps://blog.schoergendorfer.com/post/resource-efficient-pruning-for-transformer-via-low-rank-importance-estimationSecFeedde2026-08-27T04:17:40.146279+00:00Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimationhttps://blog.schoergendorfer.com/post/physics-informed-error-field-learning-a-post-training-optimization-framework-forSecFeedde2026-08-27T04:17:40.122938+00:00Physics-Informed Error Field Learning: A Post-Training Optimization Framework for Physics-Informed Neural Networkshttps://blog.schoergendorfer.com/post/why-and-when-neural-networks-improve-local-approximation-in-optimizationSecFeedde2026-08-27T04:17:40.089227+00:00Why and When Neural Networks Improve Local Approximation in Optimizationhttps://blog.schoergendorfer.com/post/afdbench-a-reasoning-first-ai-scientist-for-nationalweather-service-forecast-disSecFeedde2026-08-27T04:17:40.065260+00:00AFDBench: A Reasoning-First AI Scientist for NationalWeather Service Forecast Discussionshttps://blog.schoergendorfer.com/post/demystifying-reinforcement-learning-post-training-of-language-modelsSecFeedde2026-08-27T04:17:40.033351+00:00Demystifying Reinforcement Learning Post-Training of Language Modelshttps://blog.schoergendorfer.com/post/cat-gs-balanced-multimodal-learning-via-calibrated-gating-and-fusion-surgerySecFeedde2026-08-27T04:17:40.002611+00:00CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgeryhttps://blog.schoergendorfer.com/post/macroagent-regularity-aware-macro-legalization-with-llm-agent-designed-contour-aSecFeedde2026-08-27T04:17:39.973879+00:00MacroAgent: Regularity-Aware Macro Legalization with LLM-Agent-Designed Contour Algorithmshttps://blog.schoergendorfer.com/post/when-does-frequency-decomposition-benefit-physics-informed-neural-networks-a-preSecFeedde2026-08-27T04:17:39.940064+00:00When Does Frequency Decomposition Benefit Physics-Informed Neural Networks? A Preliminary Ablation Studyhttps://blog.schoergendorfer.com/post/fampwq-fisher-information-based-adaptive-mixed-precision-weight-quantization-forSecFeedde2026-08-27T04:17:39.911179+00:00FAMPWQ: Fisher Information-based Adaptive Mixed Precision Weight Quantization for Effective LLM Inferencehttps://blog.schoergendorfer.com/post/exfold-unified-expert-folding-for-training-free-moe-prefill-decode-accelerationSecFeedde2026-08-27T04:17:39.878944+00:00ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Accelerationhttps://blog.schoergendorfer.com/post/multi-modal-anomaly-detection-a-surveySecFeedde2026-08-27T04:17:39.851702+00:00Multi-Modal Anomaly Detection: A Surveyhttps://blog.schoergendorfer.com/post/dynamic-influence-weighted-distillation-for-single-imu-activity-recognitionSecFeedde2026-08-27T04:17:39.796068+00:00Dynamic Influence-Weighted Distillation for Single-IMU Activity Recognitionhttps://blog.schoergendorfer.com/post/dele-w05-inferring-action-from-future-latent-state-for-robotic-manipulationSecFeedde2026-08-27T04:17:39.765621+00:00DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulationhttps://blog.schoergendorfer.com/post/scaling-muon-for-diffusion-transformers-3SecFeedde2026-08-27T04:17:39.733915+00:00Scaling Muon for Diffusion Transformershttps://blog.schoergendorfer.com/post/st-lite-training-free-kv-cache-compression-with-spatio-trajectory-guidance-for-l-2SecFeedde2026-08-27T04:17:39.700578+00:00ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agentshttps://blog.schoergendorfer.com/post/can-large-language-models-still-explain-themselves-investigating-the-impact-of-q-2SecFeedde2026-08-27T04:17:39.668622+00:00Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanationshttps://blog.schoergendorfer.com/post/uco-a-multi-turn-interactive-reinforcement-learning-method-for-adaptive-teaching-2SecFeedde2026-08-27T04:02:36.485243+00:00UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Modelshttps://blog.schoergendorfer.com/post/topology-guided-modular-actor-critic-learning-for-continuous-systems-under-tempo-2SecFeedde2026-08-27T04:02:36.453925+00:00Topology-Guided Modular Actor-Critic Learning for Continuous Systems under Temporal Objectiveshttps://blog.schoergendorfer.com/post/simthesizer-an-agent-driven-simulation-framework-for-llm-serving-systems-2SecFeedde2026-08-27T04:02:36.424231+00:00Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systemshttps://blog.schoergendorfer.com/post/confidently-wrong-silently-so-auditing-undetectable-failures-of-a-deployed-on-de-2SecFeedde2026-08-27T04:02:36.395362+00:00Confidently Wrong, Silently So: Auditing Undetectable Failures of a Deployed On-Device Language Modelhttps://blog.schoergendorfer.com/post/the-invisible-editorial-layer-formalizing-undisclosed-inference-time-steering-pr-2SecFeedde2026-08-27T04:02:36.362638+00:00The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Modelshttps://blog.schoergendorfer.com/post/rebuild-dossier-mechanically-enforced-specs-for-agentic-app-rebuilds-and-what-mo-2SecFeedde2026-08-27T04:02:36.322599+00:00Rebuild Dossier: Mechanically-Enforced Specs for Agentic App Rebuilds, and What Model-Tier Failures Revealhttps://blog.schoergendorfer.com/post/matched-excess-outranker-regularization-for-candidate-set-interference-in-contin-2SecFeedde2026-08-27T04:02:36.293861+00:00Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embeddinghttps://blog.schoergendorfer.com/post/agentworld-personality-aware-reliability-evaluation-for-agentic-information-retr-2SecFeedde2026-08-27T04:02:36.253792+00:00AgentWorld: Personality-Aware Reliability Evaluation for Agentic Information Retrievalhttps://blog.schoergendorfer.com/post/diverse-by-reasoning-harnessing-the-wisdom-of-llm-crowds-for-future-prediction-2SecFeedde2026-08-27T04:02:36.206016+00:00Diverse by Reasoning: Harnessing the Wisdom of LLM Crowds for Future Predictionhttps://blog.schoergendorfer.com/post/ai-finds-a-way-2SecFeedde2026-08-27T04:02:36.163371+00:00AI Finds A Wayhttps://blog.schoergendorfer.com/post/aws-glue-51-is-now-available-in-aws-european-sovereign-cloud-regionSecFeedde2026-08-27T03:17:33.570117+00:00AWS Glue 5.1 is now available in AWS European Sovereign Cloud Regionhttps://blog.schoergendorfer.com/post/the-economics-of-agent-optimization-four-ways-to-lower-the-costSecFeedde2026-08-27T02:17:25.924907+00:00The Economics of Agent Optimization: Four ways to lower the costhttps://blog.schoergendorfer.com/post/ainews-nvidia-buys-huggingface-for-13b-as-openai-publishes-their-hf-incident-retSecFeedde2026-08-27T02:02:30.558019+00:00[AINews] NVIDIA buys HuggingFace for $13B, as OpenAI publishes their HF incident retrohttps://blog.schoergendorfer.com/post/ainews-hot-chips-openais-jalapeno-cerebras-cs-5-groq-3-lpx-apple-m6SecFeedde2026-08-27T01:47:25.132849+00:00[AINews] Hot Chips: OpenAI’s Jalapeño, Cerebras CS-5, Groq 3 LPX, Apple M6https://blog.schoergendorfer.com/post/a-reported-log4j-rce-is-more-complicated-than-it-looksSecFeedde2026-08-27T00:47:28.640643+00:00A Reported Log4j RCE Is More Complicated Than It Lookshttps://blog.schoergendorfer.com/post/mini-shai-hulud-npm-attack-over-2200-components-compromisedSecFeedde2026-08-27T00:17:33.537475+00:00Mini Shai-Hulud npm Attack: Over 2,200 Components Compromisedhttps://blog.schoergendorfer.com/post/anthropics-claude-now-has-a-browser-of-its-ownSecFeedde2026-08-26T22:17:43.998293+00:00Anthropic’s Claude now has a browser of its ownhttps://blog.schoergendorfer.com/post/zai-releases-glm-53-flash-a-320b-a18b-natively-multimodal-moe-with-a-1m-token-coSecFeedde2026-08-26T21:47:37.106326+00:00Z.ai Releases GLM-5.3-Flash: A 320B-A18B Natively Multimodal MoE With a 1M-Token Contexthttps://blog.schoergendorfer.com/post/x-sent-nitter-a-cease-and-desist-then-it-went-after-the-source-codeSecFeedde2026-08-26T21:17:56.823507+00:00X sent Nitter a cease-and-desist. Then it went after the source code.https://blog.schoergendorfer.com/post/aws-glue-now-supports-catalog-federation-for-remote-apache-iceberg-catalogs-in-aSecFeedde2026-08-26T21:17:56.795442+00:00AWS Glue now supports catalog federation for remote Apache Iceberg catalogs in AWS GovCloud (US) regionshttps://blog.schoergendorfer.com/post/aws-backup-adds-cross-region-backup-copy-and-logically-air-gapped-vault-supportSecFeedde2026-08-26T21:17:56.763279+00:00AWS Backup adds cross-Region backup copy and logically air-gapped vault support for Amazon DocumentDB in nine additional AWS Regionshttps://blog.schoergendorfer.com/post/mountpoint-for-amazon-s3-adds-memory-usage-controlsSecFeedde2026-08-26T21:17:56.732280+00:00Mountpoint for Amazon S3 adds memory usage controlshttps://blog.schoergendorfer.com/post/amazon-connect-customer-now-supports-unplanned-shrinkage-in-agent-schedulesSecFeedde2026-08-26T21:17:56.701399+00:00Amazon Connect Customer now supports unplanned shrinkage in agent scheduleshttps://blog.schoergendorfer.com/post/openais-astra-can-do-a-researchers-week-of-work-thats-the-problemSecFeedde2026-08-26T20:32:57.371863+00:00OpenAI’s Astra can do a researcher’s week of work. That’s the problem.https://blog.schoergendorfer.com/post/observability-has-a-data-problem-ai-is-about-to-make-it-worseSecFeedde2026-08-26T20:17:40.635485+00:00Observability has a data problem. AI is about to make it worse.https://blog.schoergendorfer.com/post/amazon-connect-customer-now-supports-points-based-scoring-in-performance-evaluatSecFeedde2026-08-26T20:17:40.605220+00:00Amazon Connect Customer now supports points-based scoring in performance evaluationshttps://blog.schoergendorfer.com/post/github-copilot-app-for-beginners-automate-dependabot-pull-request-triageSecFeedde2026-08-26T20:17:40.576212+00:00GitHub Copilot app for Beginners: Automate Dependabot pull request triagehttps://blog.schoergendorfer.com/post/dynamic-capacity-management-for-ai-infrastructureSecFeedde2026-08-26T20:17:40.548870+00:00Dynamic capacity management for AI infrastructurehttps://blog.schoergendorfer.com/post/lovable-cto-the-future-of-saas-is-apps-that-agents-can-useSecFeedde2026-08-26T19:47:46.212229+00:00Lovable CTO: The Future of SaaS Is Apps That Agents Can Usehttps://blog.schoergendorfer.com/post/icymi-july-2026-aws-securitySecFeedde2026-08-26T19:47:46.176631+00:00ICYMI: July 2026 @AWS Securityhttps://blog.schoergendorfer.com/post/the-inside-story-on-why-openai-agents-hacked-hugging-faceSecFeedde2026-08-26T19:33:51.616645+00:00The inside story on why OpenAI agents hacked Hugging Facehttps://blog.schoergendorfer.com/post/tricentis-preps-wave-of-additional-ai-testing-capabilitiesSecFeedde2026-08-26T19:18:27.299108+00:00Tricentis Preps Wave of Additional AI Testing Capabilitieshttps://blog.schoergendorfer.com/post/evaluate-any-agent-framework-with-amazon-bedrock-agentcore-evaluationsSecFeedde2026-08-26T19:18:27.269801+00:00Evaluate any agent framework with Amazon Bedrock AgentCore Evaluationshttps://blog.schoergendorfer.com/post/cisa-adds-six-known-exploited-vulnerabilities-to-catalogSecFeedde2026-08-26T18:47:46.837681+00:00CISA Adds Six Known Exploited Vulnerabilities to Cataloghttps://blog.schoergendorfer.com/post/when-ai-infrastructure-becomes-the-target-securing-gateways-and-control-pointsSecFeedde2026-08-26T18:17:42.361422+00:00When AI infrastructure becomes the target: Securing gateways and control pointshttps://blog.schoergendorfer.com/post/simplify-your-resilience-testing-strategy-with-fault-injection-testingSecFeedde2026-08-26T18:17:42.321453+00:00Simplify your resilience testing strategy with Fault Injection Testinghttps://blog.schoergendorfer.com/post/action-required-for-google-container-registry-users-scream-tests-and-our-move-toSecFeedde2026-08-26T18:02:35.675126+00:00ACTION REQUIRED FOR GOOGLE CONTAINER REGISTRY USERS, scream tests, and our move to AWShttps://blog.schoergendorfer.com/post/closing-the-ai-agent-trust-gap-with-graduated-autonomySecFeedde2026-08-26T17:47:52.083786+00:00Closing the AI agent trust gap with graduated autonomyhttps://blog.schoergendorfer.com/post/gallup-scales-real-time-coaching-for-thousands-with-amazon-bedrockSecFeedde2026-08-26T17:47:52.049531+00:00Gallup scales real-time coaching for thousands with Amazon Bedrockhttps://blog.schoergendorfer.com/post/detecting-multi-stage-attacks-on-aws-a-guide-to-cross-service-signal-correlationSecFeedde2026-08-26T17:47:52.016538+00:00Detecting multi-stage attacks on AWS: A guide to cross-service signal correlationhttps://blog.schoergendorfer.com/post/claude-desktop-can-now-easily-run-qwen-deepseek-and-kimi-models-after-ollamas-fiSecFeedde2026-08-26T17:17:55.575111+00:00Claude Desktop can now easily run Qwen, DeepSeek and Kimi models — after Ollama’s first effort stalledhttps://blog.schoergendorfer.com/post/amazon-ec2-c8id-and-m8id-instances-are-now-available-in-additional-aws-regionsSecFeedde2026-08-26T17:17:55.411381+00:00Amazon EC2 C8id and M8id instances are now available in additional AWS Regionshttps://blog.schoergendorfer.com/post/amazon-ec2-r8id-instances-are-now-available-in-additional-aws-regionsSecFeedde2026-08-26T17:17:55.376457+00:00Amazon EC2 R8id instances are now available in additional AWS Regionshttps://blog.schoergendorfer.com/post/how-godaddy-transformed-its-analytics-with-amazon-quickSecFeedde2026-08-26T17:02:51.449411+00:00How GoDaddy transformed its analytics with Amazon Quickhttps://blog.schoergendorfer.com/post/kubernetes-v137-garhwalSecFeedde2026-08-26T17:02:51.411360+00:00Kubernetes v1.37: Garhwalhttps://blog.schoergendorfer.com/post/zais-glm-53-flash-is-cheap-good-and-served-on-chinese-chips-2SecFeedde2026-08-26T16:49:18.477830+00:00Z.ai’s GLM-5.3-Flash is cheap, good, and served on Chinese chipshttps://blog.schoergendorfer.com/post/googles-new-legal-ai-exposes-a-bigger-battle-over-the-enterprise-stackSecFeedde2026-08-26T16:49:18.442903+00:00Google’s new legal AI exposes a bigger battle over the enterprise stackhttps://blog.schoergendorfer.com/post/bring-your-own-model-with-amazon-sagemaker-ai-script-mode-in-sdk-v3SecFeedde2026-08-26T16:49:18.386832+00:00Bring your own model with Amazon SageMaker AI: Script mode in SDK v3https://blog.schoergendorfer.com/post/nateras-intelligent-appointment-scheduling-with-amazon-bedrock-agentcoreSecFeedde2026-08-26T16:49:18.343257+00:00Natera’s intelligent appointment scheduling with Amazon Bedrock AgentCorehttps://blog.schoergendorfer.com/post/perplexity-just-separated-reasoning-from-authority-heres-why-it-matters-for-enteSecFeedde2026-08-26T16:32:54.266227+00:00Perplexity just separated reasoning from authority. Here’s why it matters for enterprises.https://blog.schoergendorfer.com/post/zais-glm-53-flash-is-cheap-good-and-served-on-chinese-chipsSecFeedde2026-08-26T16:32:54.238952+00:00Z.ai’s GLM-5.3 Flash is cheap, good, and served on Chinese chipshttps://blog.schoergendorfer.com/post/preparing-data-for-supervised-fine-tuning-part-1-formatting-and-qualitySecFeedde2026-08-26T16:32:54.206658+00:00Preparing data for supervised fine-tuning Part 1: Formatting and qualityhttps://blog.schoergendorfer.com/post/preparing-data-for-supervised-fine-tuning-part-2-advanced-data-strategiesSecFeedde2026-08-26T16:32:54.173867+00:00Preparing data for supervised fine-tuning Part 2: Advanced data strategieshttps://blog.schoergendorfer.com/post/the-future-of-saas-is-apps-that-agents-can-useSecFeedde2026-08-26T16:32:54.137061+00:00The Future of SaaS Is Apps That Agents Can Usehttps://blog.schoergendorfer.com/post/break-glass-access-for-amazon-eks-when-federated-identity-failsSecFeedde2026-08-26T16:32:54.097747+00:00Break-glass access for Amazon EKS when federated identity failshttps://blog.schoergendorfer.com/post/how-uber-improves-network-reliability-while-unblocking-cloud-migrationSecFeedde2026-08-26T16:18:22.734382+00:00How Uber improves network reliability while unblocking cloud migrationhttps://blog.schoergendorfer.com/post/using-okf-with-knowledge-catalog-to-serve-context-for-agentsSecFeedde2026-08-26T16:18:22.701250+00:00Using OKF with Knowledge Catalog to serve context for agentshttps://blog.schoergendorfer.com/post/simplify-your-resilience-testing-strategy-with-google-cloud-fault-injection-testSecFeedde2026-08-26T16:18:22.659390+00:00Simplify your resilience testing strategy with Google Cloud Fault Injection Testinghttps://blog.schoergendorfer.com/post/connect-amazon-bedrock-agentcore-to-cross-account-knowledge-basesSecFeedde2026-08-26T16:03:19.465582+00:00Connect Amazon Bedrock AgentCore to cross-account knowledge baseshttps://blog.schoergendorfer.com/post/who-has-admin-rights-in-your-entra-id-directoryx3f-wed-aug-26thSecFeedde2026-08-26T16:03:19.429799+00:00Who Has Admin Rights in your Entra ID Directory?, (Wed, Aug 26th)https://blog.schoergendorfer.com/post/git-was-built-for-humans-agents-need-an-upgradeSecFeedde2026-08-26T15:47:36.141060+00:00Git was built for humans — agents need an upgradehttps://blog.schoergendorfer.com/post/your-chance-to-start-building-ai-agents-from-the-absolute-basicsSecFeedde2026-08-26T15:47:36.108480+00:00Your chance to start building AI agents from the absolute basicshttps://blog.schoergendorfer.com/post/we-have-foundation-models-for-language-not-for-physics-anima-anandkumar-bren-proSecFeedde2026-08-26T15:32:55.713031+00:00🔬“We have foundation models for language, not for physics” — Anima Anandkumar, Bren Professor of Computinghttps://blog.schoergendorfer.com/post/copilot-code-reviews-for-azure-repos-public-previewSecFeedde2026-08-26T15:32:55.675173+00:00Copilot Code Reviews for Azure Repos (public preview)https://blog.schoergendorfer.com/post/alibabas-qwen-team-releases-qwen38-flash-next-a-125b-multimodal-moe-with-6b-actiSecFeedde2026-08-26T15:32:55.640196+00:00Alibaba’s Qwen Team Releases Qwen3.8-Flash-Next: A 125B Multimodal MoE With 6B Active Parameters Previewing the Qwen4 Architecturehttps://blog.schoergendorfer.com/post/orchestration-is-the-new-challenge-for-cx-in-the-age-of-ai-agentsSecFeedde2026-08-26T14:47:53.386980+00:00Orchestration is the new challenge for CX in the age of AI agentshttps://blog.schoergendorfer.com/post/cisa-vulnerability-reviewSecFeedde2026-08-26T14:32:43.160055+00:00CISA Vulnerability Reviewhttps://blog.schoergendorfer.com/post/what-would-have-to-be-true-for-agentic-coding-to-replace-junior-engineersSecFeedde2026-08-26T14:32:43.126540+00:00What Would Have to Be True for Agentic Coding to Replace Junior Engineershttps://blog.schoergendorfer.com/post/finops-for-the-ai-era-new-flexible-billing-and-cost-controls-for-agentsSecFeedde2026-08-26T13:47:40.166181+00:00FinOps for the AI era: New flexible billing and cost controls for agentshttps://blog.schoergendorfer.com/post/infrastructure-for-the-ai-era-dynamic-capacity-management-for-agentsSecFeedde2026-08-26T13:47:40.133363+00:00Infrastructure for the AI era: Dynamic capacity management for agentshttps://blog.schoergendorfer.com/post/ai-driven-software-delivery-with-kiro-aws-devops-agent-and-bluebox-by-dynatraceSecFeedde2026-08-26T13:18:15.151674+00:00AI-driven software delivery with Kiro, AWS DevOps Agent and Bluebox by Dynatracehttps://blog.schoergendorfer.com/post/edge-infrastructure-under-siege-what-two-independent-datasets-reveal-about-whosSecFeedde2026-08-26T13:18:15.113407+00:00Edge infrastructure under siege: what two independent datasets reveal about who's exploiting your perimeterhttps://blog.schoergendorfer.com/post/when-ai-agent-traces-become-application-dataSecFeedde2026-08-26T13:02:34.863824+00:00When AI agent traces become application datahttps://blog.schoergendorfer.com/post/usn-8678-2-openssl-openssl-10-vulnerabilitiesSecFeedde2026-08-26T13:02:34.830431+00:00USN-8678-2: OpenSSL, OpenSSL 1.0 vulnerabilitieshttps://blog.schoergendorfer.com/post/microsoft-just-released-agent-lightning-v10-heres-why-it-matters-for-platform-enSecFeedde2026-08-26T12:32:36.322281+00:00Microsoft just released Agent Lightning v1.0. Here’s why it matters for platform engineers.https://blog.schoergendorfer.com/post/making-room-for-whats-next-in-the-gitlab-uiSecFeedde2026-08-26T12:17:30.623939+00:00Making room for what's next in the GitLab UIhttps://blog.schoergendorfer.com/post/governance-guidance-for-cncf-projects-choosing-the-right-structure-for-your-proj-2SecFeedde2026-08-26T12:17:30.539414+00:00Governance guidance for CNCF projects: Choosing the right structure for your project’s size and stagehttps://blog.schoergendorfer.com/post/usn-8681-1-openjdk-25-vulnerabilitiesSecFeedde2026-08-26T12:02:51.750060+00:00USN-8681-1: OpenJDK 25 vulnerabilitieshttps://blog.schoergendorfer.com/post/exploits-and-vulnerabilities-in-q2-2026SecFeedde2026-08-26T12:02:51.666481+00:00Exploits and vulnerabilities in Q2 2026https://blog.schoergendorfer.com/post/choose-your-fighter-balancing-competing-requirements-to-select-models-for-your-aSecFeedde2026-08-26T12:02:51.581663+00:00Choose your fighter: Balancing competing requirements to select models for your AI SOChttps://blog.schoergendorfer.com/post/ai-models-flub-these-intelligence-tests-can-you-fare-any-betterSecFeedde2026-08-26T12:02:50.702030+00:00AI models flub these intelligence tests. Can you fare any better?https://blog.schoergendorfer.com/post/raised-on-aiSecFeedde2026-08-26T11:47:31.220314+00:00Raised on AIhttps://blog.schoergendorfer.com/post/the-missing-runtime-for-long-running-ai-agentsSecFeedde2026-08-26T11:47:30.438900+00:00The Missing Runtime for Long-Running AI Agentshttps://blog.schoergendorfer.com/post/automated-diagnosis-isnt-automated-understanding-what-postmortems-teach-us-aboutSecFeedde2026-08-26T11:47:30.401936+00:00Automated Diagnosis Isn’t Automated Understanding: What Postmortems Teach Us About Building Trustworthy Incident AIhttps://blog.schoergendorfer.com/post/ai-can-generate-your-infrastructure-can-your-cicd-pipeline-trust-itSecFeedde2026-08-26T11:32:52.752236+00:00AI Can Generate Your Infrastructure. Can Your CI/CD Pipeline Trust It?https://blog.schoergendorfer.com/post/your-ai-coding-budget-is-becoming-a-variable-cloud-billSecFeedde2026-08-26T11:17:34.323668+00:00Your AI Coding Budget Is Becoming a Variable Cloud Billhttps://blog.schoergendorfer.com/post/bill-gates-says-weve-passed-ais-danger-thresholds-now-whatSecFeedde2026-08-26T11:02:52.893030+00:00Bill Gates says we’ve passed AI’s danger thresholds. Now what?https://blog.schoergendorfer.com/post/amazon-gamelift-servers-enhanced-ddos-protection-now-availableSecFeedde2026-08-26T10:47:50.174644+00:00Amazon GameLift Servers enhanced DDoS Protection now availablehttps://blog.schoergendorfer.com/post/amazon-ec2-m8i-and-m8i-flex-instances-are-now-available-in-canada-west-calgary-rSecFeedde2026-08-26T10:47:50.142346+00:00Amazon EC2 M8i and M8i-flex instances are now available in Canada West (Calgary) regionhttps://blog.schoergendorfer.com/post/ibm-releases-granite-42-bringing-native-reasoning-and-agentic-rl-to-open-enterprSecFeedde2026-08-26T10:47:50.036500+00:00IBM Releases Granite 4.2: Bringing Native Reasoning and Agentic RL to Open Enterprise Modelshttps://blog.schoergendorfer.com/post/att-and-microsoft-scale-trillion-token-workloads-with-microsoft-foundry-and-amd-2SecFeedde2026-08-26T10:47:50.008951+00:00AT&T and Microsoft scale trillion-token workloads with Microsoft Foundry and AMDhttps://blog.schoergendorfer.com/post/the-economics-of-agent-optimization-from-pilots-to-measurable-returns-2SecFeedde2026-08-26T10:47:49.977492+00:00The Economics of Agent Optimization: From pilots to measurable returnshttps://blog.schoergendorfer.com/post/microsoft-named-a-leader-in-the-2026-gartner-magic-quadranttm-for-cloud-native-a-2SecFeedde2026-08-26T10:47:49.949705+00:00Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for Cloud-Native Application Platformshttps://blog.schoergendorfer.com/post/the-patch-window-is-collapsing-why-security-needs-a-new-control-plane-2SecFeedde2026-08-26T10:47:49.910741+00:00The patch window is collapsing: Why security needs a new control planehttps://blog.schoergendorfer.com/post/constructcie-a-dataset-for-extracting-causal-information-from-construction-accid-3SecFeedde2026-08-26T10:47:49.824471+00:00ConstructCIE: A Dataset for Extracting Causal Information from Construction Accident Narrativeshttps://blog.schoergendorfer.com/post/rig-rope-relation-stratified-multimodal-attention-with-instance-local-rotary-geo-3SecFeedde2026-08-26T10:47:49.798757+00:00RIG-RoPE: Relation-Stratified Multimodal Attention with Instance-Local Rotary Geometry and Representation-Aware Traversal Coordinateshttps://blog.schoergendorfer.com/post/robustness-of-ir-models-to-collection-growth-2SecFeedde2026-08-26T10:47:49.773439+00:00Robustness of IR Models to Collection Growthhttps://blog.schoergendorfer.com/post/expectations-and-practices-around-ai-disclosure-in-cs-research-2SecFeedde2026-08-26T10:47:49.750149+00:00Expectations and Practices around AI Disclosure in CS Researchhttps://blog.schoergendorfer.com/post/cyberfactory-scaling-cyber-security-capabilities-with-instances-from-the-wild-2SecFeedde2026-08-26T10:47:49.722873+00:00CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild