Siyan Zhao

prof_pic2.jpg

I’m a 4th-year PhD student in Computer Science at UCLA. I am fortunate to be advised by Professor Aditya Grover.

My primary research interest lies in endowing machines with human-like reasoning and efficiency. My recent research focuses on:

Prior to UCLA, I obtained my bachelor’s degree from the Engineering Science (Machine Intelligence program) at the University of Toronto. Before my PhD, I worked on 3D perception and RL algorithms for autonomous driving agents.

recent updates

[09/2025] d1 is accepted at NeurIPS 2025 as spotlight.
[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 presentation.
[09/2024] Probing the Decision Boundaries of In-context Learning in LLMs was accepted at NeurIPS 2024 and also won the best paper award at the Foundation Model Interventions Workshop, NeurIPS 2024.
[08/2024] Excited to receive the 2024 Amazon Fellowship.

selected works (all)

  1. Preprint
    Inpainting-Guided Policy Optimization for Diffusion Large Language Models
    Siyan Zhao, Mengchen Liu, Jing Huang, Miao Liu, Chenyu Wang, Bo Liu, Yuandong Tian, Guan Pang, Sean Bell, Aditya Grover, and Feiyu Chen
    preprint, 2025
  2. NeurIPS 2025
    d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning
    Siyan Zhao*, Devaansh Gupta*, Qinqing Zheng, and Aditya Grover
    NeurIPS, 2025
    Spotlight, 3.2% acceptance rate
  3. 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
  4. NeurIPS 2025
    MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants
    Hritik Bansal, Daniel Israel*, Siyan Zhao*, Shufan Li, Tung Nguyen, and Aditya Grover
    NeurIPS, 2025
  5. 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
  6. 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
  7. ICLR 2024
    Group Preference Optimization: Few-Shot Alignment of Large Language Models
    Siyan Zhao, John Dang, and Aditya Grover
    ICLR, 2024
  8. NeurIPS 2023
    Decision Stacks: Flexible Reinforcment Learning Via Modular Generative Models
    Siyan Zhao, and Aditya Grover
    NeurIPS, 2023

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