Haofan Wang

School Email: haofanw (at) alumni.cmu.edu
Personal Email: haofanwang.ai (at) gmail.com
Research Interests
  • Multi-Modality Generative Model
  • Controllable and Personalized Generation
  • Generative, Agentic and Shippable AI Product
Biography

Haofan Wang (王浩帆) is a Member of Technical Staff at Lovart AI, working primarily on generative and agentic models. He works at InstantX Team for open-sourcing generative models. Previously, he worked at Xiaohongshu and Kuaishou's MMU (Kolors Team). He obtained master degree from Carnegie Mellon University. He visited the Image and Video Understanding Laboratory (IVUL) at KAUST in 2020 and the DATA Lab at Texas A&M University in 2019. He studied at UC Berkeley in 2017 as a visiting student and worked as a research assistant at Berkeley RISE Lab on the Clipper project. He also spent time OpenMined, RealAI, Everspry, Horizon Robotics, and the Institute of Software at the Chinese Academy of Sciences. His highlighted works include EasyControl, InstantStyle, InstantID, and Score-CAM.

Selected Publications (Full List)
[motion]
PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design
Jiazhe Wei, Ken Li, Tianyu Lao, Haofan Wang, Liang Wang, Caifeng Shan, and Chenyang Si. This work was finished while the first author was interning at Lovart.
[Project Page] [Paper] [Code]
[motion]
EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer
Yuxuan Zhang, Yirui Yuan, Yiren Song, Haofan Wang, Jiaming Liu
[Project Page] [Paper] [Code] [HF]
[motion]
InstantStyle : Free Lunch towards Style-Preserving in Text-to-Image Generation
Haofan Wang*, Qixun Wang, Xu Bai, Zekui Qin, and Anthony Chen. * means corresponding author.
[Project Page] [Paper] [Code]
[motion]
InstantID : Zero-shot Identity-Preserving Generation in Seconds
Qixun Wang, Xu Bai, Haofan Wang*, Zekui Qin, and Anthony Chen. * means corresponding author.
[Project Page] [Paper] [Code] [News]
[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
[Code] [Paper] [Slides] [News]
Teaching
  • Guest Lecture of CS5260: Neural Networks and Deep Learning II, Spring 2024, National University of Singapore
  • Teaching Assistant of 18-793 Image and Video Processing, Prof: Aswin C Sankaranarayanan, Summer 2020, Carnegie Mellon University
    • Professional Services
  • Journal Reviewer: IJCV, TMM, TKDD, AI Communications
  • Conference Reviewer: SIGGRAPH, NeurIPS, ICLR, ICML, CVPR, ICCV, ECCV, ACMMM, XAI4CV@CVPR, PRCV
    • Career Trajectory

    Kuaishou (2021-2022) → Xiaohongshu (2022-2024) → Lovart AI (2024-)

    Misc

    Piano (Roland HP704), Scuba Diving (AOW), Snowboarding (Basic), Photographer (Sony RX100M5, Osmo Pocket3)

    Travel Map

    Australia (Sydney, Gold Coast, Queensland), Thailand (Bangkok), Sinapore, Malaysia (Kuala Lumpur, Kota Kinabalu, Semporna), Vietnam (Phú Quốc), South Korea (Jeju, Seogwipo), Japan (Tokyo, Hakone, Osaka, Kyoto, Nara), United States (Mountain View, Pittsburgh, Las Vegas, San Francisco, College Station, Berkeley, Los Angeles, Riverside)

    Favourite Youtubers

    linksphotograph