AI News

SAGE-Loop: Reliable Closed-Loop LLM-Driven AutoML with Trial-and-Correction and Adaptive Ensembling (arxiv.org)

Observation-Anchored Selective Assimilation for Longitudinal Tumor-State Proxy Forecasting in Post-Treatment Glioma (arxiv.org)

Granularity-Adaptive Credit Assignment for Long-Horizon LLM Agent Reinforcement Learning (arxiv.org)

MInTRL: Off-policy Intervention can boost On-policy RL (arxiv.org)

RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search (arxiv.org)

Amortized Low-Rank Adaptation for Model-Based Reinforcement Learning (arxiv.org)

Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models (arxiv.org)

Adaptive Chemotherapy Control under Tumor Heterogeneity via Reinforcement Learning (arxiv.org)

The Rank the Task Demands: A Causal Rank Law for Matrix Memories Trained on Group Composition (arxiv.org)

CRFCAN: A Complex-Valued Cross-Domain Residual Network for Joint Channel and Phase Noise Estimation in Sub-THz OFDM Systems (arxiv.org)

PLSP (Pre-hoc Liminal Space Profiling): OOD Prediction over Detection -- An Anticipatory Approach for Machine Learning Model Reliability (arxiv.org)

Patient-Reported Survey Data Improve Prediction of Opioid Use Disorder (arxiv.org)

Predicting Collision Cross Sections with GRACE: Geometric Residual Adduct Conditioning via Early-fusion (arxiv.org)

Certifying Concept Unlearning in Text-to-Image Diffusion Models (arxiv.org)

GUIDE: Generative Utility Inference and Decision Engine (arxiv.org)

Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks (arxiv.org)

Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases (arxiv.org)

Bias-Corrected Data Synthesis for Imbalanced Learning (arxiv.org)

Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization (arxiv.org)

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective (arxiv.org)

An ab initio foundation model of wavefunctions that accurately describes chemical bond breaking (arxiv.org)

Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference (arxiv.org)

Block-Norm Geometries for Online Mirror Descent with Sparse Losses (arxiv.org)

Estimating Pedestrian Volumes from GIS-Derived Built-Environment Features: A Machine Learning Framework (arxiv.org)

Explanations-Driven Active Feature Acquisition for Algorithmic Recourse (arxiv.org)

Almost Sure Convergence Analysis of Stochastic Gradient Methods with Clipping and Additive Noise (arxiv.org)

Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacy (arxiv.org)

Reinforcement Learning for Syndrome Extraction (arxiv.org)

Toward Reliable Railway-Bogie Response Prediction Using Multifidelity TDNN and Physics-Informed Residual Learning (arxiv.org)

Inverting Self-Triggered Control: Adversarial Reinforcement Learning for Sparse Denial-of-Service Attacks (arxiv.org)

Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning (arxiv.org)

QTrans: A Quantum Transformer for Sentiment Classification (arxiv.org)

Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble for Bias Calibration (arxiv.org)

Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale (arxiv.org)

Explainable Prediction from Mobile Sensing Data through LLM-guided Concept Integration (arxiv.org)

FINESSE: An Agent-Based Simulator and Benchmark Dataset for Multimodal Financial Event Sequences (arxiv.org)

On-Device Language Models for Privacy-Preserving Stress Prediction: A Multimodal Evaluation on Mobile Health (arxiv.org)

Space as an Interventional Invariant: Cross-Modal Predictive Geometry for Stratified Cities and Em-Spaced Intelligence (arxiv.org)

Decoding Mixture Perception through Computational Modeling of Component Interactions (arxiv.org)

Look Before You Leap: Pre-Action Verification for LLM Agents (arxiv.org)

Performance, Efficiency and Collapse -- Advantages and Challenges in Offline Post-training of Code LLMs (arxiv.org)

Efficient AI Model Deployment Using Quantization Analysis Tool (arxiv.org)

Fed-Equilibrium Framework for Topological Pareto Control in Robust and Fair Clinical Federated Learning (arxiv.org)

Beyond the Query: Do Retrieval Signals Improve Adaptive Multimodal RAG Routing? (arxiv.org)

3D Digital Twin Visualization of Multiclass GRF-Based Gait Disorder Classification (arxiv.org)

ESTS at WMT26: Routing-Informed Expert Pruning for Model Compression (arxiv.org)

On Identifying Adversarial Intent Injection in AI-Native 6G Networks (arxiv.org)

Fundamental Dynamical Units for Physics-Informed Structural Inference from Perturbation Time-Series in Networked Systems (arxiv.org)

Off-grid solar user in -20 F climate asks about 100-foot run, gets a clear answer: 'Run DC' (www.thecooldown.com)

The Two MMLU Scores: What a Benchmark Name Does Not Fix (zatona.dev)