Log inSign up
Image
user avatar
David Chan
@_dmchan
Postdoc at @berkeley_ai studying contextual grounding in multimodal AI. These are the voyages of the... Crap. I don't have a name for my own ship...
Berkeley, CA
dchan.cc
Joined November 2009
145
Following
190
Followers
RepliesMedia
  • user avatar
    David Chan
    @_dmchan
    Jun 27
    There’s still time to submit to this awesome workshop some friends are organizing on embodied interaction at COLM this year - super excited for the speakers, and would love to see everyone there!
  • user avatar
    David Chan
    @_dmchan
    Jun 19
    Some really awesome work out of our lab! Congrats team :)
    user avatar
    Dantong Niu
    @Dantong_Niu
    Jun 19
    Excited to share T-Rex: Tactile-Reactive Dexterous Manipulation 🦖🤖 Touch is fundamental to human dexterity, yet most Vision-Language-Action (VLA) models either ignore tactile feedback or lack the ability to react to high-frequency contact signals. In this work, we tackle both
    Image
    00:00
  • user avatar
    David Chan
    @_dmchan
    Mar 3
    Our deadline is only one week away! Don't forget to submit!
    user avatar
    Edson Araujo
    @edsonroteia
    Feb 13
    The 5th edition of the MMFM Workshop is coming to @CVPR 2026! "What is Next in Multimodal Foundation Models?" exploring the frontiers of vision, language, and beyond. June 2026 | Denver, CO Details in thread 👇
    Image
  • user avatar
    David Chan
    @_dmchan
    Jan 26
    Some awesome new work from our group which explores the multimodal capabilities of interactive agents!
    user avatar
    Zirui "Colin" Wang
    @zwcolin
    Jan 26
    🎮 We release VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents (w/ @junyi42 @aomaru_21490) 🌐 With 17 environments across multiple domains, we show systematically the brittleness of VLMs in visual interaction, and what training leads to. 🧵[1/8]
    Image
    00:00
  • user avatar
    David Chan
    @_dmchan
    Oct 25, 2025
    I’m not sure what they get out of this, but I’m here for it!
    user avatar
    Vaibhav (VB) Srivastav
    @reach_vb
    Oct 25, 2025
    Chinese doordash dropping MIT license foundation video models??? “We introduce LongCat-Video, a foundational video generation model with 13.6B parameters, delivering strong performance across Text-to-Video, Image-to-Video, and Video-Continuation generation tasks.”

  • See @_dmchan's full profile

    Sign up
    Log in