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. Rethinking Sequence Compression with Test-time RegressionHF Daily Papers · 10月22日
  2. AgentVQA: A Unified Benchmark for Agentic Visual UnderstandingHF Daily Papers · 10月22日
  3. AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level BenchmarkHF Daily Papers · 10月22日
  4. Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We ThoughtHF Daily Papers · 10月22日
  5. Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete GenerationHF Daily Papers · 10月22日
  6. FilmFlow: Agentic System for 3D Virtual Film CinematographyHF Daily Papers · 10月22日
  7. Verus-Insight: Towards Explainable Artifact Detection in AI-Generated VideosHF Daily Papers · 10月22日
  8. LaLa-World: Scaling Latent World Models with Natural Language ActionsHF Daily Papers · 10月21日
  9. From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent ManipulationHF Daily Papers · 10月21日
  10. Self-Distilling Future Video Representations for World Action ModelsHF Daily Papers · 10月21日
  11. Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-UseHF Daily Papers · 10月21日
  12. PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent StatesHF Daily Papers · 10月21日
  13. Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion TransformersHF Daily Papers · 10月21日
  14. RealMe: Immersive Volumetric Video from Minimal CapturesHF Daily Papers · 10月21日
  15. Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential RecommendationHF Daily Papers · 10月21日
  16. Agentic World Action ModelsHF Daily Papers · 10月21日
  17. SpatialBrain: Spatial Intelligence Growing from ExperienceHF Daily Papers · 10月21日
  18. Evolving with Open Worlds: Towards Recursive Self-Improvement for Future ForecastingHF Daily Papers · 10月21日
  19. Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoEHF Daily Papers · 10月20日
  20. Building AI Research Teams for Autonomous Discovery of Linear Attention ArchitecturesHF Daily Papers · 10月20日
  21. Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative TasksHF Daily Papers · 10月20日
  22. Real In, Real Out: What If We Only Use Real Data for Scene Text Editing?HF Daily Papers · 10月20日
  23. Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?HF Daily Papers · 10月20日
  24. RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian SplattingHF Daily Papers · 10月20日
  25. WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent StateHF Daily Papers · 10月20日
  26. Answering in the User's Variety: Calibrated Accommodation Pairs for Post-TrainingHF Daily Papers · 10月20日
  27. VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM AgentsHF Daily Papers · 10月19日
  28. Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice AgentsHF Daily Papers · 10月19日
  29. RouteWeaver: Weaving Mode Selection and Execution into Unified LLM RoutingHF Daily Papers · 10月19日
  30. ACE-Brain-0.6: Scaling Spatial Grounding for Physical Foundation ModelsHF Daily Papers · 10月19日
  31. Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or LiterallyHF Daily Papers · 10月15日
  32. DeLoop: Repeated Actions as Self-Supervision for Long-Horizon AgentsHF Daily Papers · 10月14日
  33. RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph GenerationHF Daily Papers · 10月14日
  34. CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene ReconstructionHF Daily Papers · 10月9日

背景图 · Kirill Svetlakov · 经 Pinterest