HF Daily Papers · 2026-11-04

HF Daily Papers 精选（15 篇，按社区票数排序）

  • [110▲] Advances in Agentic Computer Graphics — https://arxiv.org/abs/2611.01860
  • [103▲] Wave Forcing: Towards Speed-of-Light Streaming Video Generation — https://arxiv.org/abs/2611.00859
  • [92▲] CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements — https://arxiv.org/abs/2611.03126
  • [88▲] CoworkOS:Scaling Agent Coworkers for Real-world Automation — https://arxiv.org/abs/2611.03178
  • [69▲] Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement — https://arxiv.org/abs/2610.40191
  • [42▲] Democratizing Robot-Use Agents: A Unified Harness with Open Models — https://arxiv.org/abs/2611.01560
  • [34▲] SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training — https://arxiv.org/abs/2611.02074
  • [30▲] NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale — https://arxiv.org/abs/2611.02102
  • [29▲] PhotoGuider: Composition-Aware Cropping and 360^{circ} View Framing with Explainable Photographic Assessments — https://arxiv.org/abs/2611.02897
  • [29▲] Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay — https://arxiv.org/abs/2610.27954
  • [29▲] Follow the Gradient: Tracing Safety Degradation Back to Training Data — https://arxiv.org/abs/2610.37481
  • [26▲] Order-Only On-Policy Distillation — https://arxiv.org/abs/2611.02112
  • [25▲] IdeaTaste: Do LLMs Share the Research Taste of Human Researchers? — https://arxiv.org/abs/2611.03424
  • [25▲] Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning — https://arxiv.org/abs/2611.03602
  • [23▲] When Does Latent Prediction Error Support Physical Surprise Claims in Video World Models? — https://arxiv.org/abs/2611.01815