Skip to content

AI论文速递 2026年05月02日（HuggingFace Daily Papers）

数据来源：https://huggingface.co/papers 采集时间：2026-05-02

📌 重点关注

  1. FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption | arXiv — 【重点关注】 Long-context large language models (LLMs)-for example, Gemini-3.1-Pro and Qwe...

💡 为大模型安全防护提供新思路 2. InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation? | arXiv — 【重点关注】 With the advancement of multimodal large language models (MLLMs) and coding a...

💡 解决AI应用中的盲执行问题 3. Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductors Discovery | arXiv — 【重点关注】 The discovery of novel materials is critical for global energy and quantum te...

💡 加速新材料研发的智能方法

📋 其他值得关注

  1. GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents | arXiv — We present GLM-5V-Turbo, a step toward native foundation models for multimoda...
  2. Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models | arXiv — Large Language Models (LLMs) are known to acquire reasoning capabilities thro...
  3. ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control | arXiv — Humanoid control systems have made significant progress in recent years, yet ...
  4. AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery | arXiv — Autonomous scientific research is significantly advanced thanks to the develo...
  5. Large Language Models Explore by Latent Distilling | arXiv — Generating diverse responses is crucial for test-time scaling of large langua...
  6. Step-level Optimization for Efficient Computer-use Agents | arXiv — Computer-use agents provide a promising path toward general software automati...
  7. Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence | arXiv — We introduce Nemotron 3 Nano Omni, the latest model in the Nemotron multimoda...