Mingxuan Yan

University of California, Riverside

profile.jpg

Hi there! I am Mingxuan Yan (pron: Ming-shwen Yen), a first-year PhD student at University of California - Riverside. 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 interest now lies in improving both data & computing efficiency of Vision-Language Models (VLMs) and Vision-Language Agents (VLAs). Previously, I conducted researches on building multimedia encoding/streaming systems for both human and mechine perceptions.

news

Jul 01, 2024 Joined TASL as a PhD student! 🤗🔬
Aug 06, 2023 One paper ‘‘Think before You Leap: Content-Aware Low-Cost Edge-Assisted Video Semantic Segmentation!’’ has been accepted by ACM Multimedia 2023! 🎉✨
Dec 02, 2022 One paper ‘‘From Ember to Blaze: Swift Interactive Video Adaptation via Meta-Reinforcement Learning’’ has been accepted by IEEE INFOCOM 2023!🎉✨

selected publications

  1. arXiv’25
    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
  2. MM’23
    Think before You Leap: Content-Aware Low-Cost Edge-Assisted Video Semantic Segmentation
    Mingxuan Yan, Wang Yi, Xiao Xuedou, and 3 more authors
    Proceedings of the ACM International Conference on Multimedia (MM), 2023
  3. INFOCOM’23
    From Ember to Blaze: Swift Interactive Video Adaptation via Meta-Reinforcement Learning
    Xuedou Xiao*, Mingxuan Yan*, Yingying Zuo, and 4 more authors
    Proceedings of the IEEE International Conference on Computer Communications (INFOCOM), 2023
    * indicates equal contribution