Haofan Wang

Work Email: wanghaofan (at) xiaohongshu.com
School Email: haofanw (at) alumni.cmu.edu
Personal Email: haofanwang.ai (at) gmail.com
Research Interests
  • Cross-Modal Learning
  • Conditional Human Motion Generation
  • Controllable AI Content Generation
Biography

Haofan Wang (王浩帆) is a senior research engineer at Xiaohongshu. Before that, he worked as research assistant at Accountable System Lab (ASL) and received master degree from Carnegie Mellon University in December, 2020. His current research interests are primarily on AIGC, especially modality-conditional content generation and prediction (highlighted ongoing projects are MotionMAE and OpenDance-3D). If you are also interested in those topics or seeking for an internship, please drop an email. He also contributes to open source libraries, including ColossalAI and diffusers. Some of the earlier works he co-authored are Score-CAM.

He worked as a research engineer at MMU of Kuaishou Technology from December 2020 to February 2022. He was a research intern at Image and Video Understanding Laboratory (IVUL), King Abdullah University of Science and Technology (KAUST) from August 2020 to Jan 2021, advised by Prof. Bernard Ghanem, collaborating with Guohao Li. He was a visiting student at DATA Lab, Texas A&M University from July 2019 to October 2019, advised by Prof. Xia (Ben) Hu, collaborating with Mengnan Du and Fan Yang. He studied at UC Berkeley from August 2017 to December 2017 as a visiting student, and worked as undergraduate research assistant at Berkeley RISE Lab, collaborating with Corey Zumar on Clipper. He also spent time at OpenMined, RealAI, Everspry, Horizon Robotics and Institute of Software Chinese Academy of Sciences.

  • [Update:1/11/2023]. Our team has opening positions for full-time job and research interns. Hiring! Click here for details!
  • Selected Publications (Full List)
    [dance]
    [elict]
    [elict]
    Weijiang Yu*, Haofan Wang*, Guohao Li, Nong Xiao, and Bernard Ghanem. * means equal contribution.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , 2023
    [Coming Soon]
    [smooth]
    Jue Wang*, Haofan Wang*, Weijia Wu, Jincan Deng, Yu Lu, Xiaofeng Guo, and Debing Zhang. * means equal contribution.
    ICML 2022 Pre-training Workshop
    [Paper] [Code] [Citation: 11]
    [smooth]
    Zifan Wang, Haofan Wang, Shakul Ramkumar, Matt Fredrikson, Piotr Mardziel, and Anupam Datta
    NeurIPS 2020, Poster
    [Paper] [Poster] [Code] [Citation: 29]
    [Score-CAM]
    IEEE CVPR 2020 Workshop on Fair, Data Efficient and Trusted Computer Vision
    [Project Page] [Paper] [Slides] [News] [Citation: 531]
    [HeadPose]
    Haofan Wang, Zhenghua Chen, and Yi Zhou
    ArXiv 1901.06778
    [Project Page] [Paper] [Citation: 12]
    Teaching
  • TA of 18-793 Image and Video Processing, Prof: Aswin C Sankaranarayanan, Summer 2020, Carnegie Mellon University
  • Professional Services
  • Journal Reviewer: IJCV, TMM, AI Communications
  • Conference Reviewer: NeurIPS (2021,2022), ICLR (2022,2023), ICML (2022,2023), ECCV (2022), CVPR (2023)
  • Career Trajectory

    DMU (Bachelor) --> CMU (Master) --> Kuaishou (Software Engineer) --> Xiaohongshu (Senior Software Engineer) --> What's NeXT?

    Misc

    Piano Level 7 (Yamaha YU118DN, Roland HP704), Amateur photographer (Sony RX100M5), Janpanese novice, US Stock player