Beijing Academy of Artificial Intelligence

Beijing Academy of Artificial Intelligence on Hugging Face Daily Papers: 25 papers, 6 in the top 3 of their day, 4 paper of the day.

  1. AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks 131 upvotes, #6 of 2026-10-01
  2. CoWindow Attention: Full Causal Coverage Is a Collective Property 67 upvotes, #10 of 2026-09-29
  3. MassAlloc Attention: Let Attention Allocate Its Own Compute 75 upvotes, #8 of 2026-09-29
  4. Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills 540 upvotes, #1 of 2026-09-03
  5. Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization 12 upvotes, #15 of 2026-08-21
  6. Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge 6 upvotes, #34 of 2026-08-04
  7. AREX: Towards a Recursively Self-Improving Agent for Deep Research 149 upvotes, #1 of 2026-07-24
  8. When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents 4 upvotes, #23 of 2026-06-25
  9. ChartWalker: Benchmarking the Cross-Chart RAG Task 3 upvotes, #21 of 2026-06-24
  10. ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control 39 upvotes, #7 of 2026-05-01
  11. AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery 30 upvotes, #4 of 2026-04-29
  12. UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models 6 upvotes, #21 of 2026-04-22
  13. OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale 9 upvotes, #21 of 2026-02-09
  14. EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models 37 upvotes, #7 of 2026-02-05
  15. Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation 5 upvotes, #24 of 2025-12-30
  16. Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation 44 upvotes, #5 of 2025-12-30
  17. RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics 36 upvotes, #6 of 2025-12-17
  18. General Agentic Memory Via Deep Research 150 upvotes, #1 of 2025-11-25
  19. Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench 11 upvotes, #19 of 2025-11-04
  20. Emu3.5: Native Multimodal Models are World Learners 102 upvotes, #2 of 2025-10-31
  21. Uniform Discrete Diffusion with Metric Path for Video Generation 39 upvotes, #6 of 2025-10-29
  22. EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling 26 upvotes, #16 of 2025-09-30
  23. Open Data Synthesis For Deep Research 64 upvotes, #1 of 2025-09-04
  24. RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics 39 upvotes, #5 of 2025-06-06
  25. MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents 32 upvotes, #3 of 2024-10-11

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.