Log inSign up
Image
user avatar
Haozhi Qi
@HaozhiQ
Incoming Assistant Professor @UChicagoCS | Researcher @ Amazon FAR Ph.D. @berkeley_ai
San Francisco, CA
haozhi.io
Joined February 2019
1,032
Following
4,167
Followers
RepliesMedia
  • Pinned
    user avatar
    Haozhi Qi
    @HaozhiQ
    Nov 26, 2025
    I will join UChicago CS @UChicagoCS as an Assistant Professor in late 2026, and I’m recruiting PhD students in this cycle (2025 - 2026). My research focuses on AI & Robotics - including dexterous manipulation, humanoids, tactile sensing, learning from human videos, robot
    Image
  • user avatar
    Haozhi Qi
    @HaozhiQ
    11h
    Another belated update: the recording of our RSS 2026 Workshop is now available! Check it out! Huge thanks again to all attendees, speakers, and co-organizers! youtu.be/fN9L5T60I3c
    user avatar
    Haozhi Qi
    @HaozhiQ
    May 26
    🤖 Excited to announce the 4th Workshop on Dex Manipulation. How time flies! Join us and submit your work to our workshop! Speakers, schedule, call for papers, and more details are available: shorturl.at/APhXq Deadline: June 22, 2026 (AoE) See you in Sydney! #RSS2026
    Image
  • user avatar
    Haozhi Qi
    @HaozhiQ
    Jul 16
    Check out @yunhaif’s latest work on human-to-robot dexterous manipulation. There has been quite a lot of excitement around using human data to scale robot learning, especially for dexterous manipulation. But many existing results still focus on pick-and-place, which does not
    user avatar
    Yunhai Feng
    @yunhaif
    Jul 16
    Can robots learn contact-rich tool use, like operating a pair of scissors✂️ or turning a screwdriver🪛, from human data? Introducing REGRIND: a minimalist retargeting-guided RL recipe for dexterous manipulation. 🌐 yunhaifeng.com/REGRIND/ 📄 Paper + code on the site! 🧵👇
    Image
    00:00
    Image
    00:00
  • user avatar
    Haozhi Qi
    @HaozhiQ
    Jun 26
    As robotics increasingly learns from human data, one critical modality remains largely missing: force. Videos can show what the hand does, but not how hard it pushes. This limits what robots can learn about finer force-sensitive manipulation. How can we capture this information
    user avatar
    Zhi (Leo) Wang
    @TX_Leo_Wang
    Jun 26
    1/🧠Humans are the best robot data source — but video alone misses one thing: force. 2/🙁Tactile gloves capture force — but they're costly and block the real touch manipulation depends on. 3/💪Maybe the future of touch lives on your wrist: surface EMG reads the muscles that cause
    Image
    00:00