Yidong Ouyang

Yidong Ouyang 

Yidong Ouyang
Ph.D. Candidate
Department of Statistics & Data Science
University of California, Los Angeles
Email / CV / Github / Google Scholar

About

Hey, I am Yidong Ouyang, a Ph.D. candidate at UCLA, where I am advised by George Michailidis. Prior to this, I earned my MPhil from CUHK Shenzhen, where I was advised by Liyan Xie. My research interests lie in generative models, especially diffusion and flow models.

Research Experience

  • Google AI Innovation and Research — Student Researcher, Acceleration of Video Generation Model
    Apr 2026 – Jul 2026, Mountain View

  • Google AI Innovation and Research — Research Intern, Acceleration of Diffusion Language Model
    Jan 2026 – Apr 2026, Mountain View

  • Amazon AWS Bedrock — Applied Scientist Intern, Multimodal Masked Diffusion Model
    Jun 2025 – Sep 2025, Arlington

Selected Publications (full list)

  1. dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
    Zhengyan Wan, Yidong Ouyang, Panwen Hu, Qiang Sun
    [arxiv] [code]

  2. Corrected Samplers for Discrete Flow Models
    Zhengyan Wan, Yidong Ouyang, Liyan Xie, Fang Fang, Hongyuan Zha, Guang Cheng
    International Conference on Machine Learning (ICML), 2026
    [arxiv] [code]

  3. Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
    Zhengyan Wan*, Yidong Ouyang*, Liyan Xie, Fang Fang, Hongyuan Zha, Guang Cheng
    International Conference on Learning Representations (ICLR), 2026
    [arxiv] [code]

  4. Transfer Learning for Diffusion Models
    Yidong Ouyang, Liyan Xie, Hongyuan Zha, Guang Cheng
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
    [arxiv] [code]

Talks & Reading Groups

Some of the workshops and reading groups I have given:

Teaching

  • Teaching Assistant, Stats 100C Linear Models, UCLA, 2026

  • Teaching Assistant, Stats 10 Introduction to Statistical Reasoning, UCLA, 2025

  • Teaching Assistant, DDA4010 Bayesian Statistics, CUHKSZ, 2022

  • Teaching Assistant, STA3020 Statistical Inference, CUHKSZ, 2021

Service

  • Conference reviewer: NeurIPS 2023–2025, ICLR 2024–2026, ICML 2024–2026, AAAI 2025, AISTATS 2025

  • Journal reviewer: TNNLS, TKDE

Page views (today / total)