订阅

AI 深研院 · 重点 0 · 其他 15 条

AI 深研院 · 论文

Hugging Face Daily Papers 与 arXiv 精选

其他 15 条去噪后未进重点的条目，按发布时间倒序

更多 34 条未进正文的候选，按发布时间倒序；默认折叠
  1. AnyGoal: On World Model Generalization Beyond Expert RolloutsHF Daily Papers · 10月19日
  2. DeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay RemovalHF Daily Papers · 10月19日
  3. Kronecker Delta Rule for Long Context Linear AttentionHF Daily Papers · 10月19日
  4. RoAR-VAE: Improving Latent Diffusability through Robust PredictionHF Daily Papers · 10月19日
  5. InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural GenerationHF Daily Papers · 10月19日
  6. HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offsHF Daily Papers · 10月19日
  7. Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard PlanningHF Daily Papers · 10月19日
  8. Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policyHF Daily Papers · 10月19日
  9. Frechet Forcing: Training Long-Horizon Streaming World Models from Short ClipsHF Daily Papers · 10月19日
  10. HandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous ManipulationHF Daily Papers · 10月19日
  11. State World Models: Execute the Rules, Generate the PixelsHF Daily Papers · 10月19日
  12. Remembering Has a Price: Learning Memory Worth under Resource ConstraintsHF Daily Papers · 10月19日
  13. Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained OnHF Daily Papers · 10月18日
  14. Think Visually Across Space and Time: Grounded Reasoning for Video SegmentationHF Daily Papers · 10月18日
  15. AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot ManipulationHF Daily Papers · 10月18日
  16. FineSplat: Fine Patches, Local Groups, Detailed SplatsHF Daily Papers · 10月18日
  17. HSPR: Recovering Software-Agent Benchmark Scores via Hierarchical Posterior InferenceHF Daily Papers · 10月17日
  18. ECHO: Efficient Causal Self-Recursion Beyond Auxiliary Multi-Token PredictionHF Daily Papers · 10月17日
  19. MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image EditingHF Daily Papers · 10月16日
  20. Harnessing Textual Refusal Directions for Multimodal SafetyHF Daily Papers · 10月16日
  21. Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning ScalableHF Daily Papers · 10月16日
  22. LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process ConstraintsHF Daily Papers · 10月15日
  23. OmniXRef: A Unified Framework for Multimodal Multi-Reference Video EditingHF Daily Papers · 10月15日
  24. Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process RewardsHF Daily Papers · 10月15日
  25. Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language ModelsHF Daily Papers · 10月15日
  26. ACEdit: Stable Multi-Turn Image Editing via Asymmetric ConditioningHF Daily Papers · 10月15日
  27. Interlock: From Local Correctness to Task Completion in Long-Horizon AgentsHF Daily Papers · 10月14日
  28. Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence ExtractionHF Daily Papers · 10月14日
  29. Evidence-First Agentic VerificationHF Daily Papers · 10月13日
  30. EvoWeb: A Benchmark for Coding Agents on Evolving Web ApplicationsHF Daily Papers · 10月12日
  31. Consistent Distribution Matching for Data-Free Diffusion DistillationHF Daily Papers · 10月6日
  32. MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM AgentsHF Daily Papers · 10月5日
  33. Self-Evaluating Recursive AgentsHF Daily Papers · 10月4日
  34. OPMD: On-Policy Mechanism Distillation Beyond Output SupervisionHF Daily Papers · 9月29日