Haofan Wang

School Email: haofanw (at) alumni.cmu.edu
Personal Email: haofanwang.ai (at) gmail.com
Research Interests
  • Contrastive Learning
  • Cross-Modal Pre-training
  • Self-Supervised Learning
  • Interpretable Machine Learning
Biography

Haofan Wang (王浩帆) is a software engineer at MMU of Kuaishou Technology. He graduated from Carnegie Mellon University in December 2020, advised by Dr. Piotr (Peter) Mardziel. Previously, he worked as a research intern with Prof. Bernard Ghanem at KAUST (2020 Summer) and Prof. Xia (Ben) Hu at Texas A&M University (2019 Summer). He obtained undergraduate degree from Dalian Maritime University in June 2019 and exchanged at UC Berkeley (worked at RISE Lab, Clipper Group) in 2017 Fall. He also worked at OpenMined, RealAI, Everspry, Horizon Robotics and Institute of Software Chinese Academy of Sciences.

I'm always open to (remote) research collaboration related to cross-modal understanding and pre-training. Our team also hires software engineer (all levels) and research interns all over the year. Drop me an email if you are interested!

Selected Publications (Full List)
[smooth]
ECLIP: Efficient Contrastive Language-Image Pretraining via Ensemble Confidence Learning and Masked Language Modeling
Jue Wang, Haofan Wang*, Weijia Wu, Jincan Deng, Weijiang Yu, Debing Zhang,
Under Review, * means equal contribution.
[Paper] [Code]
[smooth]
Smoothed Geometry for Robust Attribution
Zifan Wang, Haofan Wang, Shakul Ramkumar, Matt Fredrikson, Piotr Mardziel, and Anupam Datta
NeurIPS 2020, Poster
[Paper] [Poster] [Code] [Citation: 11]
[Score-CAM]
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
Haofan Wang, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding Piotr Mardziel and Xia (Ben) Hu
IEEE CVPR 2020 Workshop on Fair, Data Efficient and Trusted Computer Vision
[Project Page] [Paper] [Slides] [News] [Citation: 216]
[HeadPose]
Hybrid Coarse-fine Classification for Head Pose Estimation
Haofan Wang, Zhenghua Chen, and Yi Zhou,
ArXiv 1901.06778
[Project Page] [Paper] [Citation: 6]
Talks
  • [06/2021] MMU, Kuaishou. An Overview of Large Scale Pre-Training
    • Teaching
  • TA of 18-793 Image and Video Processing, Prof: Aswin C Sankaranarayanan, Summer 2020, Carnegie Mellon University
    • Professional Services
  • Conference Reviewer: NeurIPS'21, ICLR'22, ICML'22
    • Collaborators
  • Industry: Debing Zhang(Xiaohongshu), Chunhui Liu(Kuaishou), Shentong Mo(Baidu Research), Tushar Semwal(Microsoft)
  • Academia: Zifan Wang(CMU), Jiachen Lian(UC Berkeley), Guohao Li(KAUST), Mengnan Du(TAMU), Weijiang Yu(SYSU), Yu Lu(UTS)
    • Trajectory

    DMU (Bachelor) --> CMU (Master) --> Kuaishou (Software Engineer) --> TBD (Ph.D) --> What's NeXT?