AI News

Watermarking Diffusion Language Models with Learned Foresight and Balanced Bands (arxiv.org)

SWE-Shift: Evaluating Coding Agents in Evolving Workspaces (arxiv.org)

Evidence-Grounded SLM Behavioral Prediction Architecture for Future Assistance Use (arxiv.org)

Correct Answers, Closed Gates: SolveBind for GUI Agents at the Verification Barrier (arxiv.org)

Not All Information Is Worth Asking For: Decision-Informed Information Seeking with LLMs (arxiv.org)

$\Psi$-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model (arxiv.org)

MPQ: A Message-Passing View of Post-Training Quantization (arxiv.org)

Who Verifies the Tools? How Warped Formatters Mislead Agents and Their Verifiers (arxiv.org)

PersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers (arxiv.org)

Learning Nonlinear Waveform Fusion Across Scales for Integrated Sensing and Communication (arxiv.org)

DELA: Learning Controllable Edits for Diffusion Language Models (arxiv.org)

What Open-Source Projects Tell Their Coding Agents: A Census of AGENTS.md and CLAUDE.md (arxiv.org)

End-to-End Differentiable Diffusion Conditioning for Physics-Informed Optimization (arxiv.org)

Do VLAs Know They Will Fail? Interpretable Success and Failure Patterns in Physical AI Systems (arxiv.org)

Autoregressive Multimodal Anomaly Detection with Large Language Models for Microservice Systems (arxiv.org)

Generalized green and red concepts for artificial intelligence, big data, and information and communication technologies: Multidimensional framework and countermeasures (arxiv.org)

Benchmarks Are Surprisingly Compaction-Friendly (arxiv.org)

PrefO2O: Zero-Shot Preference-Based Reinforcement Learning via Offline-to-Online Latent Preference Transfer (arxiv.org)

MusicTwins: Training Audio-Language Models to Listen like Their Persona (arxiv.org)

What the Query Remembers: Query Abstraction Governs Lexical and Dense Retrieval of Classical Arabic Poetry (arxiv.org)

Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries Are Statistical (arxiv.org)

GeoDiv KAN Solver for Time Fractional Navier Stokes Equations on Complex Domains to Realistic CFD Reconstruction (arxiv.org)

Learning from Next-Frame Prediction: Towards Unified and Scalable Visual World Modeling (arxiv.org)

How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions (arxiv.org)

SEVI: Safe Evidential Real-World Reinforcement Learning (arxiv.org)

Rethinking Multi-View Fusion for Urban Representation Learning (arxiv.org)

SWE-Clar: Can Coding Agents Clarify Incomplete Client Requirements and Deliver Greenfield Software? (arxiv.org)

Machine-Readable Operator Manuals over the ISO 11783 Network for Offline, Multilingual LLM Assistance (arxiv.org)

FSVL: Taxonomic Fast-Slow Vision-to-Language Collaborative Framework for Interpretable Confusable Fish Species Identification and Knowledge Generation in the Middle Yangtze River (arxiv.org)

ImageRSI: Verification-Driven Recursive Self-Improvement for Agentic Image Generation (arxiv.org)

Beyond Data Schedule: Fast LLM Pretraining on Data Mixtures by Loss-Reweighting (arxiv.org)

Heterogeneous Space Data Centers: A Key Paradigm for Future Non-Terrestrial and In-Orbit Services (arxiv.org)

Sparsity-driven emergence of functional modularity in multitask neural networks (arxiv.org)

MG-REPA: Multi-Granularity Representation Alignment for Generative Target Speaker Extraction (arxiv.org)

Searching with Sparse Histories: Cross-Task Architecture Search from Incomplete Search Logs and Zero-Cost Proxies (arxiv.org)

Uni-Stream: A Unified Streaming Speech Language Model for Speech Synthesis and Recognition (arxiv.org)

Dual-Adaptive Z-Score PPO: Dynamic Clipping Using Action Confidence and Normalized Advantage Magnitude (arxiv.org)

SOPO: Socratic Guided Policy Optimization for Span-Level Hallucination Detection (arxiv.org)

Head Dimension Matters in Language Models for Long-Context Retrieval (arxiv.org)

Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction (arxiv.org)

Anti-coherence Regularized Absolute Scaling for Out-of-Distribution Detection (arxiv.org)

Representation Learning via Composite Subspace Flow Matching (arxiv.org)

Beyond Pattern Matching in 3D MLLMs: Part-Level Functional Reasoning for Generalizable Recognition (arxiv.org)

Tokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs (arxiv.org)

"Not" is Not Lost in Translation: A Causal Analysis of Negation Representations in Multilingual LLMs (arxiv.org)

Complementing DINO Features with Image Structure for Part Discovery (arxiv.org)

ChoreoStudio: Planning What, When, and Who in Music-Driven Group Choreography (arxiv.org)

4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented Agents (arxiv.org)

Data-Efficient Backdoor Attacks on Code Models via Trigger-Neutralized Counterfactual Scoring (arxiv.org)

TENET: Time-point Encoding Network for Multivariate Time Series Anomaly Detection (arxiv.org)