AI News

A systematic investigation of molecular encoding methods for drug property predictions across neural network and Transformer encoder-based model (arxiv.org)

Comparative evaluation of training strategies using partially labelled datasets for segmentation of white matter hyperintensities and stroke lesions in FLAIR MRI (arxiv.org)

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units (arxiv.org)

UA-DCM: Uncertainty-aware Causal Decision Making via Effect Bound Decomposition (arxiv.org)

MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering (arxiv.org)

Families of Control-Cost-Parametrized Inverse-Optimal Universal Stabilizers (arxiv.org)

MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation (arxiv.org)

Alcmean's: Unsupervised community detection using local Laplacian, automatic detection of the number of centers (arxiv.org)

Nonparametric LLM Evaluation from Preference Data (arxiv.org)

Cosmo3DFlow: Wavelet Flow Matching for Spatial-to-Spectral Compression in Reconstructing the Early Universe (arxiv.org)

Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions (arxiv.org)

Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints (arxiv.org)

Variational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequence Acceptance (arxiv.org)

When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents (arxiv.org)

Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning (arxiv.org)

The Label Horizon Paradox: Rethinking Supervision Targets in Financial Forecasting (arxiv.org)

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature (arxiv.org)

Foundation Inference Models for Ordinary Differential Equations (arxiv.org)

A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation (arxiv.org)

An 84-Format Numeric Catalog with Bit-Exact Conformance Vectors: A Vendor-Neutral Reference for FP8, BF16, MXFP4, and Microscaling Formats (arxiv.org)

Observability for Delegated Execution in Agentic AI Systems (arxiv.org)

FASE: Fast Adaptive Semantic Entropy for Code Quality (arxiv.org)

Who Earns the Safety? Intervention-Aware Quantum Predictive Control with Safety Attribution (arxiv.org)

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger (arxiv.org)

Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics (arxiv.org)

Operationalising the Superficial Alignment Hypothesis via Task Complexity (arxiv.org)

Geometry-Aware Uncertainty Quantification via Conformal Prediction on Manifolds (arxiv.org)

GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation (arxiv.org)

Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model (arxiv.org)

AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing (arxiv.org)

PTL-Diffusion: Manifold-Aware Diffusion with Periodic Terminal Laws (arxiv.org)

OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics (arxiv.org)

A Survey on Large Language Model-Based Game Agents (arxiv.org)

TQA-Bench: Evaluating LLMs for Multi-Table Question Answering (arxiv.org)

IDEQ -- Improving Diffusion Models for the Traveling Salesman Problem (TSP) by Leveraging the Structure of the Solution Space (arxiv.org)

Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP (arxiv.org)

Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations (arxiv.org)

A Geometric Theory of Cognition for Machine Intelligence (arxiv.org)

Discovering heuristics in a complex SAT solver with large language models (arxiv.org)

CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning (arxiv.org)

MixReasoning: Switching Modes to Think (arxiv.org)

MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs (arxiv.org)

TempoBench: Evaluating Temporal Causal Reasoning in Large Language Models (arxiv.org)

Label-Conditioned Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Curriculum-Gated Contrastive Alignment (arxiv.org)

A Geometric Unification of Concept Learning with Concept Cones (arxiv.org)

Understanding Benchmark Language Under Weakened Formal Semantics (arxiv.org)

Projection and Quantisation: A Unifying View of Learning to Hash, from Random Projections to the RAG Era (arxiv.org)

Correcting Mean Bias in Text Embeddings: A Refined Renormalization with Training-Free Improvements on MMTEB (arxiv.org)

SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM (arxiv.org)

MedVision: Benchmarking Quantitative Medical Image Analysis (arxiv.org)