Yuxiao Yang

Yuxiao Yang

Hi, I’m Yuxiao Yang (杨宇骁).

I am a first-year Ph.D. student in Computer Science at the University of North Carolina at Chapel Hill, where I am fortunate to be advised by Prof. Weitong Zhang.

My research focuses on reinforcement learning and post-training for large language models, particularly policy optimization, self-improvement, and knowledge distillation for reasoning.

Before joining UNC, I earned my bachelor’s degree in Computer Science from the John Hopcroft Class at Shanghai Jiao Tong University.

Yuxiao Yang in New York City

📋 CV

View CV (PDF)

📝 Publications

  • Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning (ICML 2026)
    Yuxiao Yang, Weitong Zhang
    Paper · Code
  • Provable and Practical In-Context Policy Optimization for Self-Improvement (ICLR 2026)
    Tianrun Yu*, Yuxiao Yang*, Zhaoyang Wang, Kaixiang Zhao, Porter Jenkins, Xuchao Zhang, Chetan Bansal, Huaxiu Yao, Weitong Zhang
    Paper · Code

* indicates equal contribution.

📄 Preprints

  • OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
    Yuxiao Yang, Xiaoyun Wang, Weitong Zhang
    Paper
  • When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation #2 Paper of the Day
    Yuxiao Yang, Tianrun Yu, Shangzhe Li, Kaixiang Zhao, Xuchao Zhang, Chetan Bansal, Huaxiu Yao, Taylor W. Killian, Weitong Zhang
    Paper
  • REVO: Rollout-Efficient Off-Policy Distillation via Variance-Guided Reuse
    Yuxiao Yang, Shangzhe Li, Tianrun Yu, Kaixiang Zhao, Taylor W. Killian, Weitong Zhang
    Paper
  • Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It
    Tianrun Yu, Kaixiang Zhao, Shangzhe Li, Yuxiao Yang, Porter Jenkins, Weitong Zhang, Taylor W. Killian
    Paper
  • An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning
    Shangzhe Li, Yuxiao Yang, Tianrun Yu, Kaixiang Zhao, Xiaoyun Wang, Taylor W. Killian, Weitong Zhang
    Paper
  • Recovering Reliable Supervision via Critique-Guided On-Policy Distillation
    Kaixiang Zhao, Tianrun Yu, Shangzhe Li, Yuxiao Yang, Amanda Hughes, Weitong Zhang, Taylor W. Killian
    Paper

🤝 Academic Service

  • Conference Reviewer: AAAI 2027, ICLR 2027
  • Journal Reviewer: Transactions on Machine Learning Research (TMLR)

🎓 Teaching

  • Teaching Assistant: DATA 521: Foundations of AI, UNC-Chapel Hill (Fall 2026)