Miao Lu

About Me Welcome to my homepage! I am a third-year Ph.D. candidate from the Department of Management Science and Engineering (MS&E) at Stanford University, advised by Prof. Jose Blanchet. I obtained my Bachelor's degree in Mathematics from the University of Science and Technology of China (USTC). Currently I am also a research scientist intern at NVIDIA Research. I previously interned at ByteDance Seed and Ubiquant Investment. Research Interests My recent research centers around RL, long-horizon LLM post-training. With backgrounds in probability and statistics, my past research includes mathematical theory and algorithm design of RL, training dynamics and generalization in deep learning, and RL for operations and economics. Contact Information Email: miaolu at stanford dot edu [Google Scholar] [GitHub] [LinkedIn] [CV]

Selected Publications

• INFUSER: Influence-Guided Self-Evolution Improves Reasoning
  with Siyu Chen, Beining Wu, Heejune Sheen, Fengzhuo Zhang,
  Shuangning Li, Zhiyuan Li, Jose Blanchet, Tianhao Wang, Zhuoran Yang
  arXiv preprint, Jun 2026
  

• Scaling Long-Horizon LLM Agent via Context Folding
  with Weiwei Sun, Zhan Ling, Kang Liu, Xuesong Yao, Yiming Yang, Jiecao Chen
  International Conference on Machine Learning (ICML) 2026
  

• Beyond the Context Window: Scaling Agentic RL via End-to-end Optimized Context Compression
  with Weiwei Sun, Weihua Du, Zhan Ling, Xuesong Yao, Kang Liu, Jiecao Chen
  Association for Computational Linguistics (ACL) 2026
  

• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
  with Zhihan Liu, Shenao Zhang, Boyi Liu, Hongyi Guo, Yingxiang Yang, Jose Blanchet, Zhaoran Wang
  Neural Information Processing Systems (NeurIPS) 2024
  

• Benign Oscillation of Stochastic Gradient Descent with Large Learning Rates
  with Beining Wu, Xiaodong Yang, Difan Zou
  International Conference on Learning Representations (ICLR) 2024
  

• Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration
  with Zhihan Liu, Wei Xiong, Han Zhong, Hao Hu, Shenao Zhang, Sirui Zheng, Zhuoran Yang, Zhaoran Wang
  Neural Information Processing Systems (NeurIPS) 2023
  

• Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage
  with Jose Blanchet, Tong Zhang, Han Zhong
  Neural Information Processing Systems (NeurIPS) 2023