AI News

Piano2Pop: Expanding Piano Demos into Pop Productions Without Aligned Supervision (arxiv.org)

Diagnostic Loss: Asymmetric Supervision for Radiology Report Generation (arxiv.org)

Mostly Reading: What Open-Book Scores Measure in Document-Level LoRA Adapters (arxiv.org)

NN-Based Transistor Modeling for Ultra-Fast SPICE Simulation and Standard Cell Library Characterization (arxiv.org)

DRAFT: Decoding and Reconstructing 3D Room Layouts from fMRI and Camera Trajectories (arxiv.org)

Delta N-gram: Forward-Only Continual Writing into a Language Model's Native N-gram Memory (arxiv.org)

Post-Audit Mirage: Identifiability Limits of Offline Agent Verification (arxiv.org)

Mixing Matters: Evidence Position Bias Across Sequence Mixers in Long-Context Question Answering (arxiv.org)

A Strong MoE Is All You Need for Process Supervision (arxiv.org)

VeriEvolve: Evaluator-First Evolution for Tool-Using Agents (arxiv.org)

Enhancing Cross-Grade Generalization in Banana Variety Classification via Hybrid CNN-Transformers and Knowledge Self-Distillation (arxiv.org)

Beyond Small Talk: Modeling Disclosure Trajectories in Human-AI Conversation (arxiv.org)

RegoMender: A Multi-agent Framework for Automated Rego Policy Repair (arxiv.org)

GM-GReFEL: Geometry-Guided Spatiotemporal State-Space Learning for Robust Dynamic Facial Expression Recognition (arxiv.org)

Prompt Sensitivity in Tool-Augmented Model Comparisons (arxiv.org)

MoG-VLM: Efficient Video Anomaly Detection through Motion-Guided Vision-Language Models (arxiv.org)

Structure-preserving reduced-order models of thin panels in supersonic and hypersonic flow (arxiv.org)

Keeping Time vs. Understanding Time: Neither Alone Explains Temporal Reasoning in LLMs (arxiv.org)

Stationarity Constraints Improve Both Energies and Densities of Machine-Learned Exchange-Correlation Functionals (arxiv.org)

What the Author Wrote, What the Agent Reads: Silent Cue Loss in Enterprise Document Ingestion (arxiv.org)

SP-HLM: Sparse-Pose-Driven Motion Generation and Whole-Body Control for Humanoid Loco-Manipulation (arxiv.org)

SWE-DIVE: Multi-Turn Coding Agent Evaluation with Dynamic User Simulation (arxiv.org)

From Reasoning to Action: Benchmarking Frontier AI Models on LIBERO-10 Robot Manipulation Tasks (arxiv.org)

Direct Inference on Admissible Sets (Diona) (arxiv.org)

LACToS: Local Anomaly Detection via Conditional Typicality of Superpixels (arxiv.org)

Would an LLM Match into a Residency? Uncertainty, Reasoning and Image Use of Open Language Models on the Spanish MIR Examination (arxiv.org)

Beyond Best-of-$k$: Prior-Consistent DAPS for Ambiguous Nonlinear Inverse Problems (arxiv.org)

EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence (arxiv.org)

SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing (arxiv.org)

Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success (arxiv.org)

On Sex, Evolution, and the Multiplicative Weights Update Algorithm (arxiv.org)

Evolutionary Deep Nets for Non-Intrusive Load Monitoring (arxiv.org)

Are EEG Sequences Time Series? EEG Classification with Time Series Models and Joint Subject Training (arxiv.org)

Parallel AI Agent Collaboration as Graph-Structured Distributed Block Optimization (arxiv.org)

AtomicRL: Atomic Reinforcement Learning for Long-Horizon Robotic Manipulation (arxiv.org)

Solving Go under Positional Superko: Sound Proof Transfer and New Board Values (arxiv.org)

A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation (arxiv.org)

From Scores to Safe Sets: Exact Safety--Constrained Decoding for Medication Recommendation (arxiv.org)

Action Learning for Scientific Simulations (arxiv.org)

CrashGym: Measuring the Decision Value of Experimentation for LLM Agents in Counterfactual Market Crashes (arxiv.org)

CRANE: Post-Hoc Counterfactual Retrieval for Multimodal Classifiers (arxiv.org)

Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning (arxiv.org)

ARCANA: A Benchmark for Abstraction and Analogical Reasoning (arxiv.org)

Same Probabilities, Different Advice: Gain-Loss Framing Effects in High-Stakes LLM Decision Support (arxiv.org)

LLM-Based Exogenous World Modeling for Dynamic Scheduling (arxiv.org)

SpatialBrain: Spatial Intelligence Growing from Experience (arxiv.org)

AgentMonopoly: Behavioral Patterns and Persona Control in LLM Agents (arxiv.org)

From Prompts to Posteriors: Can LLM Agents Perform Bayesian Inference in Context? (arxiv.org)

Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use (arxiv.org)

Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research (arxiv.org)