Research

Service

  • AI@MIT Reading Group co-organizer (Fall 2024–present)
  • Reviewer for ICLR 2025 and ICLR 2026
  • Reviewer for MATH-AI Workshop at NeurIPS 2024

Mentorship

Current mentees:

Past mentees:

Invited talks

  1. Predictive Chemistry Augmented with Text Retrieval (video link)
    Molecular Modeling & Drug Discovery (M2D2) Reading Group, Valence Labs

All publications

  1. EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths
    Zhening Li, Armando Solar-Lezama, Yisong Yue, Stephan Zheng
    Conference on Neural Information Processing Systems, 2025
  2. Beyond I-Con: A Roadmap for Representation Learning Loss Discovery
    Jasmine Shone*, Zhening Li*, Shaden Alshammari, Mark Hamilton, William Freeman
    NeurIPS 2025 Women in Machine Learning Workshop, 2025
    NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations, 2025
  3. When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions
    Zhening Li, Gabriel Poesia, Armando Solar-Lezama
    International Conference on Machine Learning, 2024
  4. Predictive Chemistry Augmented with Text Retrieval
    Yujie Qian, Zhening Li, Zhengkai Tu, Connor Coley, Regina Barzilay
    Conference on Empirical Methods in Natural Language Processing, 2023
  5. MolScribe: Robust Molecular Structure Recognition with Image-to-Graph Generation
    Yujie Qian, Jiang Guo, Zhengkai Tu, Zhening Li, Connor W Coley, Regina Barzilay
    Journal of Chemical Information Modeling 63(7), 2023
  6. LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions
    Zhening Li*, Gabriel Poesia*, Omar Costilla-Reyes, Noah Goodman, Armando Solar-Lezama
    NeurIPS 2022 MATH-AI Workshop, 2022

Preprints

  1. Nestedness Promotes Stability in Maximum-Entropy Bipartite Food Webs
    Zhening Li, John Harte
    arXiv preprint arXiv:2401.04815, 2024