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. MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal RecordsHF Daily Papers · 10月20日
  2. Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary RigsHF Daily Papers · 10月20日
  3. Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative OffloadingHF Daily Papers · 10月20日
  4. Evolving Agent InterfacesHF Daily Papers · 10月20日
  5. Harness Self-Evolution for Long-Horizon Terminal AgentsHF Daily Papers · 10月20日
  6. Large Flow Language ModelsHF Daily Papers · 10月20日
  7. SpecKCast: Spectral Kalman Forecasting for Diffusion AccelerationHF Daily Papers · 10月19日
  8. Breaking Diffusion: Parallel Reasoning with Draft RefinementHF Daily Papers · 10月19日
  9. Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policyHF Daily Papers · 10月19日
  10. PhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural SkinningHF Daily Papers · 10月19日
  11. From Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face SwappingHF Daily Papers · 10月19日
  12. Unsupervised Tool Evolution for Coding Agents in Data-Lake AnalyticsHF Daily Papers · 10月19日
  13. HarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RLHF Daily Papers · 10月19日
  14. On the Fragility of Tasks under Composition: Implicit Budgeting in Language ModelsHF Daily Papers · 10月19日
  15. Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained OnHF Daily Papers · 10月18日
  16. FineSplat: Fine Patches, Local Groups, Detailed SplatsHF Daily Papers · 10月18日
  17. Epi: Towards a Persistent, Self-Improving Agent for Autonomous ResearchHF Daily Papers · 10月18日
  18. Painting Change Map as guidance for generating painting processesHF Daily Papers · 10月18日
  19. StopLoss: Teaching Agents to Predict Failure and Stop EarlyHF Daily Papers · 10月18日
  20. EdgeKernelBench: Unified LLM-Driven Kernel Generation for Edge BackendsHF Daily Papers · 10月17日
  21. Good Judgment, Bad Advice: Decision-Model Controllers Raise Agent Cost Without Improving SuccessHF Daily Papers · 10月17日
  22. ECHO: Efficient Causal Self-Recursion Beyond Auxiliary Multi-Token PredictionHF Daily Papers · 10月17日
  23. Progress-Aware Distillation for Mitigating Stagnation in Small Language Model AgentsHF Daily Papers · 10月17日
  24. HybridResearcher: Bridging the Structured-Unstructured Boundary for Deep Research AgentsHF Daily Papers · 10月17日
  25. UniAVC: Unified Audio-Video Creation via Progressive Training and Asymmetric SchedulingHF Daily Papers · 10月17日
  26. Harnessing Textual Refusal Directions for Multimodal SafetyHF Daily Papers · 10月16日
  27. Event-STVG: Spatio-Temporal Video Grounding for Long-Form Event ReasoningHF Daily Papers · 10月15日
  28. ACEdit: Stable Multi-Turn Image Editing via Asymmetric ConditioningHF Daily Papers · 10月15日
  29. Predicting Privileged Information Effectiveness for On-Policy Self-DistillationHF Daily Papers · 10月15日
  30. Evaluating Agentic Capabilities Before Post-Training: An End-to-End ApproachHF Daily Papers · 10月14日
  31. CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense CombatHF Daily Papers · 10月13日
  32. LLM2R: From Large Language Models to 3D ReassemblersHF Daily Papers · 10月13日
  33. EAU: Environment-Agent-User Co-evolution for Training User-Centric AgentsHF Daily Papers · 10月12日
  34. FlowState: Execution State as Memory for Long-Horizon LLM AgentsHF Daily Papers · 10月8日