HF Daily Papers · 2026-10-15

HF Daily Papers 精选（15 篇，按社区票数排序）

  • [266▲] Jeva: System One Models from First Principles — https://arxiv.org/abs/2610.18773
  • [193▲] Agent-Reflex: Teaching Language Agents to Act Reflectively — https://arxiv.org/abs/2610.17953
  • [110▲] Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes — https://arxiv.org/abs/2610.18356
  • [82▲] GreenWAM: A World Foundation Model for Robotics — https://arxiv.org/abs/2610.18774
  • [52▲] Last Secure Code Benchmark: Is the Code You Vibe Secure? — https://arxiv.org/abs/2610.14766
  • [51▲] EviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment — https://arxiv.org/abs/2610.14609
  • [41▲] APEX: Asynchronous Prefix Denoising for Extreme Compression — https://arxiv.org/abs/2610.12843
  • [34▲] FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching — https://arxiv.org/abs/2610.17552
  • [29▲] Self-Distillation with Verbal Regularization — https://arxiv.org/abs/2610.16354
  • [25▲] Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping — https://arxiv.org/abs/2610.15782
  • [24▲] Cepheid: Decoupling Scale from Structure for Cross-Family Motion Completion — https://arxiv.org/abs/2610.18871
  • [22▲] WAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction — https://arxiv.org/abs/2610.18568
  • [19▲] ReTerm: Recovery Training for Self-Improving Terminal Agents — https://arxiv.org/abs/2610.18484
  • [18▲] Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence — https://arxiv.org/abs/2610.17656
  • [16▲] LightVAE: Towards Compact and Efficient Video Autoencoders — https://arxiv.org/abs/2610.14726