Log inSign up
user avatar

Geng Chen

@gengchen
Master student @UCSDJacobs | Prev Undergrad @sjtu1896, visitor @Stanford and @Tsinghua_IIIS | Working on Embodied AI & Robot Learning.
San Diego, CA
jc043.github.io
Joined May 2022
442
Following
398
Followers
RepliesMedia
  • Pinned
    user avatar
    Geng Chen
    @gengchen
    Mar 15, 2025
    Can we build a robot policy foundation model🤖 that incorporates 3D observations? 🚀Introducing FP3, a first 3D foundation policy for robotic manipulation. Using only 80 demonstrations, FP3 can solve a new task with over 90% success rates in the wild! Let's dive in! 🧵1/N
    Image
    00:00
  • user avatar
    Geng Chen
    @gengchen
    Jun 2
    Excited to announce that FP3 has been selected as an ICRA 2026 Best Paper Award Finalist on Robot Learning! 🎉 Unfortunately, I won’t be able to attend in person in Vienna, but our advisor @gao_young will be presenting the work today. Please stop by if you are at ICRA! 📍
    user avatar
    Geng Chen
    @gengchen
    Feb 1
    Glad to share that our paper FP3 has been accepted to #ICRA2026! 🎉Huge thanks to my co-authors and collaborators, it's been a long ride. In FP3, we demonstrate that 3D perception is a strong ingredient for learning robot foundation models. It’s been about 1 year since we
  • user avatar
    Geng Chen
    @gengchen
    Apr 26
    A hierarchical policy is essential for long-horizon tasks!
    user avatar
    Isabella Liu
    @Isabella__Liu
    Apr 24
    VLA/VAs are doing well on short skills like pick-and-place. But real tasks rarely stop after one action, they require 1) many interdependent steps, 2) progress tracking, and 3) recovery from mistakes. In our paper LoHo-Manip, we address long-horizon manipulation with
    Image
    00:00
  • user avatar
    Geng Chen
    @gengchen
    Mar 23
    Strongly bullish on scaling human data for robotics! Feel excited to help a bit in this ambitious project.
    user avatar
    Danfei Xu
    @danfei_xu
    Mar 23
    Introducing EgoVerse: an ecosystem for robot learning from egocentric human data. Built and tested by 4 research labs + 3 industry partners, EgoVerse enables both science and scaling 1300+ hrs, 240 scenes, 2000+ tasks, and growing Dataset design, findings, and ecosystem 🧵
    Image
    00:00
  • user avatar
    Geng Chen
    @gengchen
    Feb 11
    Turning UMI-recorded end-effector trajectories into manipulation-ready humanoid whole-body actions is definitely challenging. Congrats to @RuiqianNai and team for delivering such impressive results!