Skip to content

AI论文速递 2026年04月26日（HuggingFace Daily Papers）

数据来源：https://huggingface.co/papers 采集时间：2026-04-26

📌 重点关注

  1. OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis | arXiv — 【重点关注】 Mobile agents powered by vision-language models have demonstrated impressive ...
  2. WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning | arXiv — 【重点关注】 While Large Language Models (LLMs) excel at function-level code generation, p...
  3. LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics | arXiv — 【重点关注】 Comprehensive understanding of time series remains a significant challenge fo...

📋 其他值得关注

  1. PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents | arXiv — Personalizing language models by effectively incorporating user interaction h...
  2. Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks | arXiv — Long horizon interactive environments are a testbed for evaluating agents ski...
  3. 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding | arXiv — Large multimodal models are increasingly used as the reasoning core of embodi...
  4. Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges | arXiv — Reinforcement Learning from Human Feedback (RLHF) and related alignment parad...
  5. CreativeGame:Toward Mechanic-Aware Creative Game Generation | arXiv — Large language models can generate plausible game code, but turning this capa...
  6. Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs | arXiv — Prior work shows that fine-tuning aligned models on benign data degrades safe...
  7. LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model | arXiv — We present LLaDA2.0-Uni, a unified discrete diffusion large language model (d...