Log inSign up
Chuang Gan
249 posts
user avatar
Chuang Gan
@gan_chuang
Faculty Member at UMass Amherst; Principal researcher at MIT-IBM Watson AI Lab; Homepage: embodied-agi.cs.umass.edu
Joined June 2020
498
Following
10.2K
Followers

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    Chuang Gan
    @gan_chuang
    Jun 24
    We open-source Action Images — a new representation that translates 7-DoF robot actions into interpretable images. Video models are emerging as powerful robotic foundation models, but a key challenge remains: how can we seamlessly integrate robot policies into video models?
    00:00
    18K
  • user avatar
    Chuang Gan
    @gan_chuang
    Nov 14, 2024
    I’m hiring multiple research interns at the MIT-IBM lab to work on advanced LLM reasoning! The application process is simple—just send me your favorite published paper. Only one😀!!
    147K
  • user avatar
    Chuang Gan
    @gan_chuang
    Feb 5, 2025
    LLM can perform autoregressive search! LLM can perform autoregressive search! LLM can perform autoregressive search! Introducing Satori, a new framework for advancing LLM reasoning through deep thinking without a strong teacher model! We achieve this through a two-phase
    79K
  • user avatar
    Chuang Gan
    @gan_chuang
    Jun 27, 2025
    VLM can think visually without generating pixels! VLM can think visually without generating pixels! VLM can think visually without generating pixels! 📢 We introduce Machine Mental Imagery (Mirage): a new framework that enables VLM to imagine using latent visual
    89K
  • user avatar
    Chuang Gan
    @gan_chuang
    May 13, 2025
    🚀 Introducing Articulate Anymesh – now open-sourced! An automated framework behind our Genesis simulator, capable of transforming any rigid 3D mesh into its articulated counterpart using an open-vocabulary manner! Given a 3D mesh, our framework uses VLMs + visual prompting to
    00:00
    36K
  • user avatar
    Chuang Gan
    @gan_chuang
    Dec 18, 2024
    We’re excited to announce the official release of our Genesis Simulator! github.com/Genesis-Embodi… Since 2018, I decided to shift my research focus from vision to embodied AI, driven by a fascination with creating general-purpose agents capable of interacting with the physical
    user avatar
    Zhou Xian
    @zhou_xian_
    Dec 18, 2024
    Everything you love about generative models — now powered by real physics! Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics
    00:00
    62K
  • user avatar
    Chuang Gan
    @gan_chuang
    Dec 18, 2024
    I've decided to take a final screenshot of this empty project page. This is the most exciting and ambitious project of my career, and it's been in the works for two years. You can probably guess what this tweet signifies! Building a 3D world simulator is central to my deep
    34K
  • user avatar
    Chuang Gan
    @gan_chuang
    Jan 21, 2024
    Can LLM engage actively in 3D environments and dynamically gather multisensory interactive data, including g visual, audio, tactile, and thermal? Introducing MultiPLY, a multisensory embodied LLM that seamlessly connects words, actions, and perceptions! vis-www.cs.umass.edu/multiply
    00:00
    100K
  • user avatar
    Chuang Gan
    @gan_chuang
    Mar 15, 2024
    Introduce 3D-VLA, a 3D Generative World Model! Humans use mental models to predict and plan for the future. Similarly, 3D-VLA achieves this by linking 3D perception, future prediction, and action executions through a generative world model. vis-www.cs.umass.edu/3dvla
    00:00
    57K
  • user avatar
    Chuang Gan
    @gan_chuang
    Jun 20, 2025
    World Simulator, reimagined — now alive with humans, robots, and their vibrant society unfolding in 3D real-world geospatial scenes across the globe! 🚀 One day soon, humans and robots will co-exist in the same world. To prepare, we must address: 1️⃣ How can robots cooperate or
    00:00
    90K
  • user avatar
    Chuang Gan
    @gan_chuang
    Nov 10, 2024
    ICLR implemented a new rule this year, requiring authors who submit more than three papers to serve as reviewers. For the first time, I found many renowned professors in the reviewer pool. Interestingly, their scores tend to be higher than those of other reviewers.
    34K
  • user avatar
    Chuang Gan
    @gan_chuang
    Nov 3, 2023
    Excited to release RoboGen! Generative AI + Differentiable Physics Simulations could empower automated robotic skill learning at scale! Project page: robogen-ai.github.io GitHub: github.com/Genesis-Embodi… Great efforts led by my amazing interns @YufeiWang25 @zhou_xian_
    user avatar
    AK
    @_akhaliq
    Nov 3, 2023
    RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation paper page: huggingface.co/papers/2311.01… present RoboGen, a generative robotic agent that automatically learns diverse robotic skills at scale via generative simulation. RoboGen
    00:00
    82K
  • user avatar
    Chuang Gan
    @gan_chuang
    Oct 23, 2025
    Meta has given up on driving foundational innovations in robotic learning...
    36K
  • user avatar
    Chuang Gan
    @gan_chuang
    May 6, 2022
    #ICLR22 Is it possible to create digital twins by just watching videos alone? Please check out our RISP framework that allows solving this challenging inverse problem by integrating deep representation learning with differentiable simulation and rendering!
    00:00