AI News

When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting (arxiv.org)

Investigating Linear Probe Robustness to Linguistic Register, Medical Specialty, and Corpus Shifts in Medical QA (arxiv.org)

Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories (arxiv.org)

Replicating TRACE: A Practitioner's Guide to Its Threshold and Particle Budget (arxiv.org)

Neural Symbollic Regression Using Deep Learning and Sparse Modelling (arxiv.org)

Subliminal Learning as Trait-Direction Drift: A Mechanism and Targeted Control under SFT Distillation (arxiv.org)

Modelpedia: A Catalog of Model Findings for the Meta-Science of AI (arxiv.org)

Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration (arxiv.org)

Semantic-Guided Multimodal Preprocessing for Vision Transformer-Based Clear Cell Renal Cell Carcinoma Grading (arxiv.org)

Learning Sparse Decision Trees via Transformer Variational Auto-Encoders (arxiv.org)

Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds (arxiv.org)

Poisson-Gamma Dynamical Systems with Time-varying Transition Dynamics (arxiv.org)

iPINN for Broadband CARS Phase Retrieval: A Framework for Function Approximation and Inverse Modeling Problems in Nonlinear Spectroscopy (arxiv.org)

MemoryWalker: Stop Training Agents on Contexts They Never Saw (arxiv.org)

Conditional Flow Matching for ML-Based Inverse Design Problems (arxiv.org)

SAGE: Subpopulation-Aware Generative Enhancement for Mitigating Spurious Correlations (arxiv.org)

REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs (arxiv.org)

Sierpi\'nski--Knopp Wasserstein Distance for Persistence Diagrams and Applications to 2-Wasserstein Approximation (arxiv.org)

HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution (arxiv.org)

Subspace Levenberg Marquardt Algorithms in Training Neural Networks (arxiv.org)

Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures (arxiv.org)

Frozen Cores Need Task Signal: Fisher-Whitened Cross-Covariance for Low-Resource LLM Adaptation (arxiv.org)

Human-AI Co-Interpretation for Responsible AI: A Hermeneutic Perspective (arxiv.org)

ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback (arxiv.org)

AI Should Not Only Be Helpful. It Should Be Contingent. Artificial Intimacy, Sycophancy, and the Future of Social Learning (arxiv.org)

ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation (arxiv.org)

Invalidation Contracts for Cross-Episode Agent Memory (arxiv.org)

Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs (arxiv.org)

LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New Benchmark (arxiv.org)

Asymmetries in Spontaneous and Instructed Deception (arxiv.org)

IMPACT: Attention Is the Interaction Map for Scalable Interaction-Aware World Model Training (arxiv.org)

Recursive Criticality of AI Self-Improvement (arxiv.org)

Deploying and Evaluating a Smart-Agriculture Agentic Engine for Full-Season Soybean Farm Operations (arxiv.org)

DNC-IMM: Early Lane-Change Intention Recognition via Neural Calibration Based on Driving Context Information (arxiv.org)

Different representation learning objectives recover distinct latent structures from the same psychometric data (arxiv.org)

AI Morbidity and Mortality: A Framework for Clinical AI Failure Review (arxiv.org)

MiNER: Fine-Tuned Biomedical Natural Language Processing for Malaria Disease Entity Recognition in Clinical Texts (arxiv.org)

When Prediction Error Is Not Enough: Evaluating Nuisance-Function Prediction for Causal Estimation (arxiv.org)

Control Variate Score Matching for Diffusion Models (arxiv.org)

EULER: Exploring Underused Links with Evidence-Checked Return for Multi-Agent Mathematical Discovery (arxiv.org)

UI-Venus-2 Technical Report (arxiv.org)

Variance-Adaptive Muon: Pre-Orthogonalization Variance Modulation for Efficient Language Model Pretraining (arxiv.org)

SCAFFOLD: A Large-Scale Structured Dataset of Computer Science Research Figures with Diagram QA and Chain-of-Thought Reasoning Traces (arxiv.org)

OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets (arxiv.org)

Long-Horizon State Tracking in LLMs: Executing MD5 through a Deep Sequence of Dependent Tool Calls (arxiv.org)

Incremental Risk Assessment of Progressive Elder Financial Scams via Instruction-Tuned Small Language Models (arxiv.org)

FloydNet: A Learning Paradigm for Global Relational Reasoning (arxiv.org)

The Assistant's Ideal Self (arxiv.org)

Discrete-Time MDP Modeling for Multi-Item Capacitated Lot Sizing with Stochastic Demand Timing (arxiv.org)

I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models (arxiv.org)