Leon Li

profile_pic.jpg

al6843[at]nyu[dot]edu

CV Google Scholar LinkedIn GitHub HuggingFace Substack

Hi, I am Leon (Ang Li 李昂). I am an incoming PhD student at New York University, advised by Prof. Pavel Izmailov and Prof. Micah Goldblum. Previously, I completed my B.S. and M.S. in Computer Science at Columbia University, where I was fortunate to work with Prof. Micah Goldblum, Prof. Tianyi Peng, Prof. Jing Dong, and Prof. Hongseok Namkoong.

My research interest was sparked by the AlphaGo moment, which inspired me to develop AI systems that push the boundaries of reasoning and decision-making. Specifically, I am interested in reinforcement learning, reasoning, test-time algorithm, and world models.

News

Jul 22, 2025 Check out our new paper Zebra-CoT on interleaved text and visual reasoning! Dataset and model are available on Hugging Face 🤗.
May 01, 2025 I will be starting my PhD at NYU this Fall, working with Prof. Pavel Izmailov and Prof. Micah Goldblum!
Mar 24, 2025 Talk at AWS Responsible AI Group on LLM Agent Attacks.

Publications

2025

  1. zebra-cot.png
    Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
    Ang Li*, Charles Wang*, Kaiyu Yue*, Zikui Cai*, Ollie Liu*, Deqing Fu*, Peng Guo*, Wang Bill Zhu*, Vatsal Sharan, Robin Jia, Willie Neiswanger, Furong Huang, Tom Goldstein, and Micah Goldblum
    2025
    📄 Paper GitHub Code Hugging Face Model Hugging Face Dataset
  2. digital-twin.png
    Twin-2K-500: A dataset for building digital twins of over 2,000 people based on their answers to over 500 questions
    Olivier Toubia, George Z Gui, Tianyi Peng, Daniel J Merlau, Ang Li, and Haozhe Chen
    Conference on Language Modeling Workshop (COLM), 2025
    📄 Paper GitHub Code Hugging Face Dataset
  3. Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks
    Ang Li*, Yin Zhou*, Vethavikashini Chithrra Raghuram*, Tom Goldstein, and Micah Goldblum
    2025
    📄 Paper
  4. persona.png
    LLM Generated Persona is a Promise with a Catch
    Ang Li, Haozhe Chen, Hongseok Namkoong, and Tianyi Peng
    Conference on Language Modeling Workshop (COLM), 2025
    📄 Paper Hugging Face Dataset
  5. permutation-invariant-overall.png
    Architectural and Inferential Inductive Biases For Exchangeable Sequence Modeling
    Daksh Mittal*, Ang Li*, Tzu-Ching Yen*, Daniel Guetta, and Hongseok Namkoong
    2025
    📄 Paper
  6. personallm_ds.png
    PersonalLLM: Tailoring LLMs to Individual Preferences
    Thomas Zollo*, Andrew Siah*, Naimeng Ye, Ang Li, and Hongseok Namkoong
    International Conference on Learning Representations (ICLR), 2025
    📄 Paper GitHub Code Hugging Face Dataset

2024

  1. qgym.png
    QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers
    Haozhe Chen*, Ang Li*, Ethan Che*, Tianyi Peng, Jing Dong, and Hongseok Namkoong
    Advances in Neural Information Processing Systems (NeurIPS), 2024
    📄 Paper GitHub Code