Siyan Zhao's Homepage

prof_pic.jpg

Hello! I’m a second-year PhD student in Computer Science at the University of California, Los Angeles. I am fortunate to be advised by Professor Aditya Grover.

My primary research interest lies in endowing machine learning algorithms with human-like reasoning and planning capabilities. Currently, I am particularly drawn to sequential decision-making, large language models, reinforcement learning, and generative models. Previously, I have worked on 3D perception and planning for autonomous driving.

Prior to joining UCLA, I obtained my bachelor’s degree from the Engineering Science, Machine Intelligence program at the University of Toronto, where I am fortunate to be advised by Prof. Animesh Garg, Prof. Bradly Stadie and Prof. Jimmy Ba at the Vector Institute.


publications and preprints

  1. Preprint
    Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models
    Siyan Zhao*, Daniel Israel*, Guy Van den Broeck, and Aditya Grover
    preprint, 2024
    arXiv Code
  2. ICLR 2024
    Group Preference Optimization: Few-Shot Alignment of Large Language Models
    Siyan Zhao, John Dang, and Aditya Grover
    International Conference on Learning Representations (ICLR), 2024
    arXiv Code Website
  3. NeurIPS 2023
    Decision Stacks: Flexible Reinforcment Learning Via Modular Generative Models
    Siyan Zhao, and Aditya Grover
    In Advances in Neural Information Processing Systems (NeurIPS), 2023
    arXiv Code Website
  4. ICRA 2022
    Object Insertion Based Data Augmentation for Semantic Segmentation
    Yuan Ren, Siyan Zhao, and Bingbing Liu
    IEEE International Conference on Robotics and Automation (ICRA), 2022
    PDF
  5. Preprint
    One Demonstration Imitation Learning
    Bradly C. Stadie*, Siyan Zhao*, Qiqi Xu, Bonnie Li, and Lunjun Zhang
    preprint, 2020
    PDF