Chinese University of Hong Kong, Shenzhen

Chinese University of Hong Kong, Shenzhen on Hugging Face Daily Papers: 14 papers, 1 in the top 3 of their day, 0 paper of the day.

  1. Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models 9 upvotes, #18 of 2026-11-06
  2. R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop 48 upvotes, #2 of 2026-11-02
  3. WorldCast: Distributed Multiplayer World Models 3 upvotes, #80 of 2026-10-14
  4. UNITAS: A 3D-Native World Action Model for Embodied Manipulation 6 upvotes, #24 of 2026-10-13
  5. HuatuoGPT-3: RL-Only Domain Adaptation from Base Models 47 upvotes, #7 of 2026-10-07
  6. COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization 43 upvotes, #9 of 2026-09-14
  7. SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models 147 upvotes, #4 of 2026-09-03
  8. SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation 28 upvotes, #10 of 2026-08-11
  9. Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment 6 upvotes, #12 of 2026-07-06
  10. GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine? 55 upvotes, #5 of 2026-06-17
  11. TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders 50 upvotes, #7 of 2026-06-11
  12. Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning 23 upvotes, #7 of 2026-04-20
  13. BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation 2 upvotes, #20 of 2026-03-11
  14. Janus: Disaggregating Attention and Experts for Scalable MoE Inference 5 upvotes, #27 of 2025-12-17

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.