AI News

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

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

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

Mining the Design Space of Multi-Agent Workflows (arxiv.org)

Advancing SVD-based LLM Compression via Layer-Wise Error Model Search (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)

Collaborative In-Context Learning for Indoor Radio Map Estimation (arxiv.org)

Benchmarks Are Surprisingly Compaction-Friendly (arxiv.org)

From Deliberately Constructed Systemic Representations of the World of Activity to Dialogue: A Five-Level Communication Architecture for Strong Language-Based ASI (arxiv.org)

Rethinking LoRA Initialization for Robust Asymmetric Learning Rates (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)

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

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

LLaCO: Continuous Diffusion for Large Language Models with Competition-Aware Semantic Scheduling (arxiv.org)

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

MBABench-2.0: Evaluating AI Agents on Constructing Financial Spreadsheets Beyond Simple Verifiability (arxiv.org)

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

MedCaseAgent: From Multimodal Clinical Evidence to Rare Disease Case Reports (arxiv.org)

IGG: A Benchmark for Interactive GUI Grounding under Visibility Constraints (arxiv.org)

Lifelong Context Adaptation through Bidirectional Memory-Skill Learning (arxiv.org)

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

Retiming Robot Demonstrations with a Learned Speed Prior (arxiv.org)

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

From Visual Affinity to Learning Credit in Multimodal Reinforcement Learning (arxiv.org)

Beyond Gain: Measuring Skill Internalization for Agent Skill Retirement (arxiv.org)

Agentic Hazard Mapper: Emulating Expert Map-Making with AI Agents for Risk Communication (arxiv.org)

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

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

A Foundation Model for Policy In-Context Longitudinal Causal Effect Estimation (arxiv.org)

TGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent (arxiv.org)

RubricCraft: Where Solutions Diverge, Criteria Emerge (arxiv.org)

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

An Agentic Approach with Evidence-Grounded Verification for Multimodal Emotion Reasoning in Conversation (arxiv.org)

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

What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design (arxiv.org)

NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding (arxiv.org)

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

Reuse, Rewrite, or Reject: Evidence-Constrained Trace Reuse for Repeated Mobile GUI Control (arxiv.org)

LGMT: A Tool for Testing the Logical Reasoning Reliability of LLMs (arxiv.org)

SemantEq: Faithful Bidirectional Equivalence of Formal Statements (arxiv.org)

Do Language Models Trust Their Own Justifications? A Study on Functional Consistency (arxiv.org)

Reimagining Enterprise RAG for Multi-Agent Systems: A Knowledge Layer That Organizes Before It Retrieves (arxiv.org)

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

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

Compact-Bench: Measuring What Context Compaction Costs Long-Horizon Coding Agents (arxiv.org)

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution (arxiv.org)

WiMoT: Replay-Free Continual Wi-Fi Sensing via Moment Transport (arxiv.org)

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

From Target Selection to Condition Reuse: Auditing Residual Interventions in Tool-Use Models (arxiv.org)