Siyan Zhao

prof_pic2.jpg

I’m a third-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 scaling reasoning in large language models, aligning them with human preferences, efficient inference, and diffusion-based LLMs.

Previously, I 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.

Recent Updates

[05/2025] Gave invited talks on “Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning” at ASAP seminar, HKU NLP Group, UCSD Hao AI Lab, and NVIDIA!
[02/2025] PrefEval is accepted to ICLR 2025 as Oral!
[01/2025] Prepacking is accepted to AISTATS 2025!
[09/2024] Probing the Decision Boundaries of In-context Learning in LLM is accepted at NeurIPS 2024!
[08/2024] Excited to receive the 2024 Amazon Fellowship.
[01/2024] Group Preference Optimization got accepted at ICLR 2024!
[10/2023] Decision Stacks got accepted at NeurIPS 2023!

Publications and Preprints

  1. Preprint
    d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning
    Siyan Zhao*, Devaansh Gupta*, Qinqing Zheng, and Aditya Grover
    preprint, 2025
  2. ICLR 2025
    Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
    Siyan Zhao, Mingyi Hong, Yang Liu, Devamanyu Hazarika, and Kaixiang Lin
    ICLR, 2025
    Oral Presentation, 1.8% acceptance rate
  3. Preprint
    MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants
    Hritik Bansal, Daniel Israel*, Siyan Zhao*, Shufan Li, Tung Nguyen, and Aditya Grover
    preprint, 2024
  4. NeurIPS 2024
    Probing the Decision Boundaries of In-context Learning in Large Language Models
    Siyan Zhao, Tung Nguyen, and Aditya Grover
    NeurIPS, 2024
    Best Paper Runner-Up at the NeurIPS 2024 MINT Workshop
  5. AISTATS 2025
    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
    AISTATS, 2025
  6. ICLR 2024
    Group Preference Optimization: Few-Shot Alignment of Large Language Models
    Siyan Zhao, John Dang, and Aditya Grover
    ICLR, 2024
  7. NeurIPS 2023
    Decision Stacks: Flexible Reinforcment Learning Via Modular Generative Models
    Siyan Zhao, and Aditya Grover
    NeurIPS, 2023
  8. ICRA 2022
    Object Insertion Based Data Augmentation for Semantic Segmentation
    Yuan Ren, Siyan Zhao, and Bingbing Liu
    ICRA, 2022
  9. Preprint
    One Demonstration Imitation Learning
    Bradly C. Stadie*, Siyan Zhao*, Qiqi Xu, Bonnie Li, and Lunjun Zhang
    preprint, 2020

Invited Talks

Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning
📄 Slides
2025-05 HKU NLP Labs
2025-05 UCSD Hao AI Lab
2025-05 NVIDIA