About Me

I am Kaixuan Huang (黄凯旋), a Ph.D. student in Electrical and Computer Engineering Department at Princeton University. I am fortunate to be advised by Professor Mengdi Wang. Before that, I received B.S. in Mathematics and B.S. in Computer Science from Peking University. I was advised by Prof. Zhihua Zhang while doing undergraduate research. In 2019, I visited Georgia Tech as a research intern, supervised by Prof. Tuo Zhao. In 2020, I visited Tsinghua University as a research intern, supervised by Prof. Longbo Huang. I also worked closely with Prof. Jason Lee.

My research interest is RL for foundation models (e.g., offline learning/online reward improvement for diffusion models/language models) and foudation models for RL (LLM/VLM agents). I am open to possible cooperations or visiting opportunities. If you are interested, please contact me by email or wechat.


  • 03/2024: I started my internship at Google DeepMind!

Selected Publications

  • Embodied LLM Agents Learn to Cooperate in Organized Teams

    Xudong Guo, Kaixuan Huang, Jiale Liu, Wenhui Fan, Natalia Vélez, Qingyun Wu, Huazheng Wang, Thomas L. Griffiths, Mengdi Wang
    arXiv preprint [link]

  • Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

    Boyi Wei*, Kaixuan Huang*, Yangsibo Huang*, Tinghao Xie, Xiangyu Qi, Mengzhou Xia, Prateek Mittal, Mengdi Wang, Peter Henderson
    arXiv preprint [link] [Code]

  • A 5' UTR Language Model for Decoding Untranslated Regions of mRNA and Function Predictions

    Yanyi Chu*, Dan Yu*, Yupeng Li, Kaixuan Huang, Yue Shen, Le Cong, Jason Zhang, Mengdi Wang
    Nature Machine Intelligence (2024) [link]

  • Visual Adversarial Examples Jailbreak Large Language Models

    Xiangyu Qi*, Kaixuan Huang*, Ashwinee Panda, Peter Henderson, Mengdi Wang, Prateek Mittal
    AAAI 2024 ( Oral ) ICML2023 Adv ML workshop. (Oral) [link] [Code]

  • Scaling In-Context Demonstrations with Structured Attention

    Tianle Cai*, Kaixuan Huang*, Jason D. Lee, Mengdi Wang
    ICML 2023 Workshop on Efficient Systems for Foundation Models. [link]

  • Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement

    Hui Yuan, Kaixuan Huang, Chengzhuo Ni, Minshuo Chen, Mengdi Wang
    In Advances in Neural Information Processing Systems (NeurIPS), 2023. [link] [Code]

  • Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data

    Minshuo Chen*, Kaixuan Huang*, Tuo Zhao, Mengdi Wang
    In International Conference on Machine Learning (ICML), 2023. [link]

  • Fast Federated Learning in the Presence of Arbitrary Device Unavailability

    Xinran Gu*, Kaixuan Huang*, Jingzhao Zhang, Longbo Huang
    In Advances in Neural Information Processing Systems (NeurIPS), 2021. [link]

  • Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective

    Kaixuan Huang*, Yuqing Wang*, Molei Tao, Tuo Zhao
    In Advances in Neural Information Processing Systems (NeurIPS), 2020. [link]

  • On the Convergence of FedAvg on Non-IID Data

    Xiang Li*, Kaixuan Huang*, Wenhao Yang*, Shusen Wang, Zhihua Zhang
    In International Conference on Learning Representations (ICLR), 2020. (Oral Presentation) [link]


I love classical music and I practice playing piano 40 hours a day.

I implemented a tiny [tool] to help me filter out interesting daily arXiv papers.

My philosophical thoughts: (1) the interplay between network model structures and data intrinsic structures, and the generalization and extrapolation behaviors of the neural networks — this resembles how humans’ scientific discoveries match the real physical world, which has been investiaged by great philosophiers such as Immanuel Kant. The forms of human perception, knowledge, reasoning, and decision-making have also been studied by fields outside computer science.

Kaixuan's Github chart

Contact Info

Email: kaixuanh AT princeton DOT edu

Wechat: [QR Code]