Muheng Li

Muheng Li

University of Toronto

Hi! I am a second-year Ph.D. student in Statistics at the University of Toronto. I am very fortunate to be advised by Prof. Wenlong Mou and Prof. Xin Bing. I am also affiliated with the Vector Institute. Prior to my Ph.D. study, I received my B.S. in Statistics from Nanjing University in 2024.

My research focuses on the statistical and computational foundations of machine learning. I currently work on LLM post-training, inference-time methods, and environments for AI agents. I am particularly interested in designing environments that help agents apply their coding and reasoning abilities to new domains, such as the natural sciences and engineering.

Email: muheng [DOT] li [AT] mail [DOT] utoronto [DOT] ca

News

  • Sep 2026, two papers accepted by NeurIPS 2026.
  • May 2026, New preprint on post-training optimization from a test-time scaling law perspective.
  • May 2026, one paper accepted by KDD 2026 D&B Track.
  • Feb 2026, New preprint on test-time scaling laws and budget-efficient inference-time search.
  • Feb 2025, one paper accepted by TMLR.

Publications

  • What should post-training optimize? A test-time scaling law perspective
    Conference on Neural Information Processing Systems (NeurIPS 2026)
    Muheng Li, Jian Qian, Wenlong Mou
    Paper

  • Predicting and Improving Test-time Scaling Laws via Reward Tail-guided Search
    Conference on Neural Information Processing Systems (NeurIPS 2026)
    Muheng Li, Jian Qian, Wenlong Mou
    Paper · Code

  • Solving Urban Network Security Games: Learning Platform, Benchmark, and Challenge for AI Research
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026, D&B Track)
    Shuxin Zhuang, Shuxin Li, Tianji Yang, Muheng Li, Xianjie Shi, Bo An, Youzhi Zhang
    Paper

  • Reheated Gradient-based Discrete Sampling for Combinatorial Optimization
    Transactions on Machine Learning Research (TMLR), 2025
    Muheng Li, Ruqi Zhang
    Paper· Code

Services

  • Conference Reviewer: UAI (2024, 2025); ICML (2025, 2026; Silver Reviewer in 2026); ICLR (2025); NeurIPS (2026)

Teaching

  • STA314H1F: Statistical Methods for Machine Learning I (Fall 2025), Teaching Assistant, University of Toronto.
  • STA255: Statistical Theory (Winter 2025), Teaching Assistant, University of Toronto.