HF Daily Papers · 2026-10-23
HF Daily Papers 精选(15 篇,按社区票数排序)
- [353▲] StreamEval: Evaluating Interactive Streaming Video Generation Models — https://arxiv.org/abs/2610.28402
- [129▲] SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes? — https://arxiv.org/abs/2610.26659
- [124▲] DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations — https://arxiv.org/abs/2610.29997
- [115▲] Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation — https://arxiv.org/abs/2610.29989
- [88▲] Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents — https://arxiv.org/abs/2610.11942
- [65▲] Agent World Model in the Wild: Computer-Use Agent Environment Synthesis — https://arxiv.org/abs/2610.26828
- [65▲] Spectral-Spatial Interpretation — https://arxiv.org/abs/2610.21114
- [49▲] PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis — https://arxiv.org/abs/2610.20538
- [49▲] Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds — https://arxiv.org/abs/2610.28698
- [32▲] Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills — https://arxiv.org/abs/2610.17860
- [28▲] Retrieval Augmented Generation Compositionality — https://arxiv.org/abs/2610.29722
- [21▲] Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research — https://arxiv.org/abs/2610.30113
- [21▲] AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics — https://arxiv.org/abs/2610.28589
- [19▲] PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States — https://arxiv.org/abs/2610.29545
- [19▲] TraceForge: Distilling with Your Own Thinking — https://arxiv.org/abs/2610.29680