AI News

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

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

Rethinking LoRA Initialization for Robust Asymmetric Learning Rates (arxiv.org)

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

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

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

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

RSIHub: A Composable Framework for Agent-Evolution Methods (arxiv.org)

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

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

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

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

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

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

Benchmarks Are Surprisingly Compaction-Friendly (arxiv.org)

Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis (arxiv.org)

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

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

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

Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery (arxiv.org)

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

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

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

Do "True" and "False" Add Up to One? Complement Consistency in LLM-Agent Opinion Simulations (arxiv.org)

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

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

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

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

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

Phronix: The Capability-Centric Learning Paradigm for Agents (arxiv.org)

Softly Symbolifying Kolmogorov-Arnold Networks (arxiv.org)

Compatible Likelihoods for Flow Matching on Manifolds (arxiv.org)

ACVA-Bench: Beyond Prompt Following in Abstract Concept Visualization Ability for Text-to-Image Models (arxiv.org)

Effectiveness of Curriculum Learning Depends on Reward Sparsity and Competing Optima (arxiv.org)

POSEIDON: Scaling Training Environments for Scientific Agents from Code Repositories (arxiv.org)

A Randomized Permutation Whole-Model Test Heuristic for Self-Validated Ensemble Models (SVEM) (arxiv.org)

ENCL: Enabling Efficient Neuromorphic Continual Learning with Local Learning Rule and Sub-Network Freezing Strategy (arxiv.org)

ReMedI: Inference-Time Refinement and Self-Distillation for Controllable Molecular Optimization (arxiv.org)

Latent-Space Importance Weighting under Covariate Shift (arxiv.org)

A Mathematical Theory of the Jacobian Lens (arxiv.org)

When to Stop Penalizing Actions? Martingale GRPO for VLA Reinforcement Learning (arxiv.org)

REACT: Representational Early Analysis and Control of Chain-of-Thought Trajectories (arxiv.org)

CauProphet: Teaching Agents to Develop Causal Cognition like Humans (arxiv.org)

TTT in VLA Models: Exploring Training with Human Demonstrations (arxiv.org)

Tampered ML: Evaluating LLM Judgment of Machine Learning Research (arxiv.org)

BARC-Bench: Benign Asks, Risky Consequences (arxiv.org)

Async-RBench: Benchmarking Asynchronous Task Execution in LLM Agents (arxiv.org)

Beyond On-Policy vs. Off-Policy: At What Level Should LLM Agent Distillation Follow the Student? (arxiv.org)

Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders (arxiv.org)