AI论文速递 2026年05月09日（HuggingFace Daily Papers）¶
数据来源：https://huggingface.co/papers 采集时间：2026-05-09
📌 重点关注¶
- Audio-Visual Intelligence in Large Foundation Models | arXiv — 【重点关注】 Audio-Visual Intelligence (AVI) has emerged as a central frontier in artifici...
💡 多模态AI新方向，移动端应用潜力巨大
- ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning | arXiv — 【重点关注】 Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of L...
💡 强化学习新范式，推理能力突破的关键
- BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models | arXiv — 【重点关注】 Despite the success of large language models (LLMs) on general-purpose tasks...
💡 垂直领域AI工具化，医疗AI落地加速
📋 其他值得关注¶
- Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling | arXiv — Recent advances in generative video models are increasingly driven by post-tr...
- KinDER: A Physical Reasoning Benchmark for Robot Learning and Planning | arXiv — Robotic systems that interact with the physical world must reason about kinem...
- CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing | arXiv — Recent advances in large language models have led to strong performance on re...
- EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions | arXiv — Multimodal Large Language Models (MLLMs) hold significant promise for revolut...
- ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving | arXiv — We introduce ReflectDrive-2, a masked discrete diffusion planner with separat...
- Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction | arXiv — Modern retrieval systems, whether lexical or semantic, expose a corpus throug...
- Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Environments | arXiv — This paper identifies a critical yet underexplored challenge in reasoning ali...