News

  1. New note, Crooked Environments, Crooked Agents: I went through three public RL training records and found a pattern in how agents go crooked. With a short film and the scan code.
  2. Started a research internship at Microsoft Research Asia, Singapore.
  3. Released Action Shaping: Policies Absorb What They Can Express on arXiv:2609.32752.
  4. FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control accepted at NeurIPS 2026 (co-author).
  5. Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning accepted at EMNLP 2026 Findings (co-author).
  6. Passed the confirmation of candidature for my PhD at The Hong Kong Polytechnic University, with the thesis Towards Efficient Reinforcement Learning via Environment Measurement and Shaping.
  7. Shortlisted for PolyU Micro Fund 2025/26 Cohort 2 (HK$20,000 cash prize), with a conditional offer to the HKSTP Ideation Programme.
  8. Released The Trace Is the State: Exact Credit Assignment for LLM Agent Teams on arXiv:2603.06859.
  9. Co-authored a comprehensive survey on latent chain-of-thought reasoning (arXiv:2505.16782).
  10. Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning accepted at ACL 2025 Findings (co-author).
  11. Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation accepted at the NAACL 2025 Student Research Workshop (co-author).
  12. The Accuracy Paradox in RLHF: When Better Reward Models Don’t Yield Better Language Models accepted at EMNLP 2024.