1. X
  2. Chenhao Li @ RLC 2026
Log inSign up
Chenhao Li @ RLC 2026
1,000 posts
Chenhao Li @ RLC 2026 profile banner
user avatar

Chenhao Li @ RLC 2026

@breadli428
AI & Robotics student @GoogleDeepMind | Doctoral fellow @ETH_AI_Center, @leggedrobotics | Prev. @MIT, @ETH_en, @MPI_IS.
Zurich, Switzerland
breadli428.github.io
Joined December 2014
460
Following
7,542
Followers
RepliesRepliesMediaMedia
  • Pinned
    user avatar
    Chenhao Li @ RLC 2026
    @breadli428
    Jun 24
    I decided to review and explicitly post about the limitations of all my previous papers because I believe this is the fundamental driving force behind research, especially in this era of PRs and bubbles.
  • user avatar
    Chenhao Li @ RLC 2026
    @breadli428
    20h
    I’m at Reinforcement Learning Conference in Montreal this week! 🇨🇦 Come to our Model-Based RL workshop tomorrow! Our speakers are cool!!
    user avatar
    Chenhao Li @ RLC 2026
    @breadli428
    Apr 22
    📢 Call for Papers! #RLC2026 🇨🇦 🌎 We are now inviting contributions to the Workshop on Model-based RL in the Era of Generative World Models at @RL_Conference in Montreal, Canada! 🇨🇦 🔗 Webpage worldmodels-rlc.github.io 📄 Submit paper now! openreview.net/group?id=rl-co… 🧵Format
    Image
  • user avatar
    Chenhao Li @ RLC 2026
    @breadli428
    21h
    Everyone working on sim-to-real robotics should try this out!
    user avatar
    koray kavukcuoglu
    Google
    @koraykv
    Aug 13
    Replying to @koraykv
    3.7 Flash brings a big jump in agentic performance and coding accuracy. To demonstrate, we set up a 3-agent team to autonomously train a robotics control model from scratch. We hope you like 3.7 Flash, and you can read more here: blog.google/innovation-and…
    Image
    00:00
  • user avatar
    Chenhao Li @ RLC 2026
    @breadli428
    Aug 10
    🎯 Limitations: In a setup with sufficient real data, the benefit of using sim as model prior is limited. MBRL on real robots either has simplified dynamics (kinematics in this paper), or limited performance gain (Robotic World Model) due to the max domain gap it can handle.
    user avatar
    Chenhao Li @ RLC 2026
    @breadli428
    Oct 31, 2025
    🚀Introducing our new work: Learning More With Less: Sample-Efficient Model-Based RL for Loco-Manipulation ➡️sites.google.com/view/learning-… 🤖We show how model-based RL can learn complex robot dynamics efficiently — even on black-box hardware like Boston Dynamics Spot.
    Image
    00:00
  • user avatar
    Chenhao Li @ RLC 2026
    @breadli428
    Aug 8
    This is absolutely the best experience for me too @GoogleDeepMind! People are extremely approachable and open to talk, even if I am just interning. The transparency built by @Google can be rare to see in even academic labs.
    user avatar
    Yoonseok Yang
    @yoonseok_yang
    Aug 7
    Replying to @yoonseok_yang
    I thought the 1:1 with Jeff Dean was going to be the interesting part. I was wrong. What happened the next day is something I’ll probably remember for the rest of my career. I posted the photo in my Google team chat and everyone in the office lost it. "Wait, you met Jeff

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement