Qi Yan

prof_pic.jpg

My name is Qi Yan (颜齐). I am a Ph.D. student in the Electrical and Computer Engineering department at the University of British Columbia, co-supervised by Prof. Renjie Liao and Prof. Lele Wang. I am broadly interested in machine learning, self-driving, and robotics.

Previously: I interned at Borealis AI in 2023, where I worked with Jiawei He, Lili Meng, and Tristan Sylvain on using language models for event forecasting. I obtained my master’s degree in Mechanical Engineering at EPFL in 2022, where I worked with Prof. Alexandre Alahi, Dr. Iordan Doytchinov, and Prof. Bertrand Merminod on robot trajectory planning and visual localization. I received my bachelor’s degree in engineering (honors) at Shanghai Jiao Tong University in 2019.

Please refer to my curriculum vitae if you are interested.

News

Sep 18, 2025 Our paper Neural MJD and RETRO SYNFLOW were accepted to NeurIPS 2025!
Aug 18, 2025 Updated two blog posts on permutation invariant graph generation and conditional generative models for motion prediction.
Jul 08, 2025 Our paper Joint Generative Modeling of Grounded Scene Graphs and Images via Diffusion Models was accepted to Transactions on Machine Learning Research (TMLR)!
Jun 16, 2025 Our paper TrajFlow: Multi-modal Motion Prediction via Flow Matching was accepted to IROS 2025!
Feb 26, 2025 Our paper MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation was accepted to CVPR 2025!

Selected Publications [full list]

  1. NeurIPS
    RETRO SYNFLOW: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis
    Robin Yadav, Qi Yan, Guy Wolf, Avishek Joey Bose, and Renjie Liao
    NeurIPS, 2025.
    arXiv
  2. NeurIPS
    Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Prediction
    Yuanpei Gao, Qi Yan, Yan Leng, and Renjie Liao
    NeurIPS, 2025.
    arXiv Code
  3. TMLR
    Joint Generative Modeling of Grounded Scene Graphs and Images via Diffusion Models
    Bicheng Xu, Qi Yan, Renjie Liao, Lele Wang, and Leonid Sigal
    Transactions on Machine Learning Research, 2025.
    arXiv Code
  4. IROS
    TrajFlow: Multi-modal Motion Prediction via Flow Matching
    Qi Yan, Brian Zhang, Yutong Zhang, Daniel Yang, Joshua White, Di Chen, Jiachao Liu, Langechuan Liu, Binnan Zhuang, Shaoshuai Shi, and Renjie Liao
    Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2025.
    arXiv Blog Code Website
  5. CVPR
    MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation
    Yuxiang Fu, Qi Yan, Lele Wang, Ke Li, and Renjie Liao
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025.
    arXiv Blog Code Website
  6. TMLR
    SwinGNN: Rethinking Permutation Invariance in Diffusion Models for Graph Generation
    Qi Yan, Zhengyang Liang, Yang Song, Renjie Liao, and Lele Wang
    Transactions on Machine Learning Research, 2024.
    arXiv Blog Code
  7. ICLR
    AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval
    Qi Yan, Raihan Seraj, Jiawei He, Lili Meng, and Tristan Sylvain
    International Conference on Learning Representations, 2024.
    arXiv Code

Visitors