HF Daily Papers · 2026-10-21

HF Daily Papers 精选（15 篇，按社区票数排序）

  • [234▲] Scaling Parameter-Efficient Fine-Tuning for Brain Encoding — https://arxiv.org/abs/2610.26802
  • [146▲] MemT-1.0: Towards Memory-Native Evolution — https://arxiv.org/abs/2610.26825
  • [110▲] Holi-World: Building Holistic World Intelligence from Human-Ego Experience — https://arxiv.org/abs/2610.26549
  • [107▲] Learning from Fleet Experience: A Collective Learning Paradigm for Robots — https://arxiv.org/abs/2610.25736
  • [81▲] SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum — https://arxiv.org/abs/2610.26824
  • [28▲] Kronecker Delta Rule for Long Context Linear Attention — https://arxiv.org/abs/2610.26834
  • [27▲] AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments — https://arxiv.org/abs/2610.25950
  • [26▲] MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents — https://arxiv.org/abs/2610.06830
  • [26▲] InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation — https://arxiv.org/abs/2610.26853
  • [23▲] RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models — https://arxiv.org/abs/2610.26663
  • [21▲] BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References — https://arxiv.org/abs/2610.23986
  • [18▲] FineSplat: Fine Patches, Local Groups, Detailed Splats — https://arxiv.org/abs/2610.25011
  • [17▲] AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation — https://arxiv.org/abs/2609.22332
  • [16▲] Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy — https://arxiv.org/abs/2610.26848
  • [16▲] Evidence-First Agentic Verification — https://arxiv.org/abs/2610.17724