Mingxuan Yan

Georgia Institute of Technology

profile.jpg

Hi there! I am Mingxuan Yan (pron: Ming-shwen Yen), a PhD student at Georgia Institute of Technology I am currently a member of TASL under the supervision of Prof. Jiachen Li. Before that, I obtained my bachelor’s degree at Wuhan University of Technology, following a master’s degree at Huazhong University of Science and Technology.

My research interests lie in efficient and scalable robot learning and policy deployment.

news

Oct 07, 2026 Check out our new work AXIS-Bench: What Matters in Quality-Aware VLA Pretraining — A Benchmark and Empirical Study! 🎉
Sep 19, 2025 Our paper “RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks” is accepted to NeurIPS 2025! 🎉🎉🎉
Jun 26, 2025 Our paper “UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving” is accepted to ICCV 2025! 🎉🎉🎉
Jul 01, 2024 Joined TASL as a PhD student! 🤗🔬

selected publications

  1. arXiv’26
    What Matters in Quality-Aware VLA Pretraining: A Benchmark and Empirical Study
    What Matters in Quality-Aware VLA Pretraining: A Benchmark and Empirical Study
    Mingxuan Yan, Litian Gong, Dihong Huang, and 19 more authors
    arXiv, 2026
  2. NeurIPS’25
    RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks
    RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks
    Mingxuan Yan, Yuping Wang, Zechun Liu, and 1 more author
    NeurIPS, 2025
  3. ICCV’25
    UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Drivings
    UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Drivings
    Yuping Wang, Xiangyu Huang, Xiaokang Sun, and 4 more authors
    ICCV, 2025
  4. arXiv’25
    DetVPCC: RoI-based Point Cloud Sequence Compression for 3D Object Detection
    DetVPCC: RoI-based Point Cloud Sequence Compression for 3D Object Detection
    Mingxuan Yan, Ruijie Zhang, Xuedou Xiao, and 1 more author
    arXiv preprint arXiv:2502.04804, 2025