Can we collect robot dexterous hand data directly with human hand? Introducing DexUMI: 0 teleoperation and 0 re-targeting dexterous hand data collection system → autonomously complete precise, long-horizon and contact-rich tasks Project Page: dex-umi.github.io

Congratulations to BAIR researchers Kevin Zakka Qiayuan Liao Arthur Allshire Carlo Sferrazza Koushil Sreenath Pieter Abbeel and Google collaborators for winning the Outstanding Demo Paper Award at RSS 2025! playground.mujoco.org

We are excited to host the 3rd Workshop on Dexterous Manipulation at RSS tomorrow! Join us at OHE 122 starting at 9:00 AM! See you there!

I'll be presenting our HuB poster at the RSS WCBM workshop tomorrow at Epstein Plaza—poster board #4. Come by and chat if you're interested!

Come chat humanoids with us! 🤖✨ Catch the holdmybeer poster at #RSS WCBM workshop, 10:30–11:30!

Full episode dropping soon! Geeking out with Tong Zhang Boyuan Zheng on HuB: Learning Extreme Humanoid Balance hub-robot.github.io Co-hosted by Chris Paxton Michael Cho - Rbt/Acc

Recording of my talk "From Sim2Real 1.0 to 4.0 for Humanoid Whole-Body Control and Loco-Manipulation" (at ICRA&CVPR workshops and Caltech): youtu.be/AGNcw4qnimk?si… Slides: drive.google.com/file/d/1h5MxNH…

Full episode dropping soon! Geeking out with Tong Zhang Boyuan Zheng on HuB: Learning Extreme Humanoid Balance hub-robot.github.io Co-hosted by Chris Paxton Michael Cho - Rbt/Acc

Action chunking is a great idea in robotics: by getting a model to produce a short sequence of actions, it _just works better_ for some mysterious reason. Now it turns out this can help in RL too, and it's a bit clearer why: action chunks help explore and help with backups. 🧵👇

Everyone knows action chunking is great for imitation learning. It turns out that we can extend its success to RL to better leverage prior data for improved exploration and online sample efficiency! colinqiyangli.github.io/qc/ The recipe to achieve this is incredibly simple. 🧵 1/N

We now open-source a general sim2sim/sim2real deployment codebase for FALCON: github.com/LeCAR-Lab/FALC…, supporting both Unitree SDK and Booster SDK !

After sharing our preprint on the Future of Work with AI Agents, we received strong interest in the WORKBank database. Today, we’re excited to release it publicly—along with a visualization tool to explore occupational and sector-level insights🧵

Have you seen Walt Disney Imagineering's BDX Droid, Grek? Watch Grek in action on stage and see how Disney Research, @GoogleDeepmind and @NVIDIAOmniverse work together to bring next-generation robots to life.

ROBOTERA Unveils L7: Next-Generation Full-Size Bipedal Humanoid Robot with Powerful Mobility and Dexterous Manipulation！ #ROBOTERA #HumanoidRobot #Robot #EmbodiedIntelligence

The 4th workshop on Dexterous Manipulation is officially calling for papers!!! Come showcase your work and mingle with our brilliant speaker lineups, with opportunities to win cash prizes 💸 and free LEAP hands 🤖 We look forward to seeing you at Seoul! ;)

July has been a big month for Viser! - Released v1.0.0😊 - We did some writing Some demos👇

📢 Excited to sharing a little late update (before it is no longer news): I’ll be joining UT Austin Computer Science at UT Austin as an Assistant Professor! I'm recruiting PhD students from Computer Science at UT Austin in the Fall 2025 cycle and also looking for RAs/interns! More info see chenfengx.com

#ioi2025 contest is over. Singapore preliminary result is 2 gold medals and 2 silver medals. Congratulation to all 4 students. What an amazing comeback by Brian to win a gold medal. Did not expect such a safe strat can produce this amazing comeback. Extraordinary young boy.

🚀 Excited to share our #CoRL2025 paper! See you in Korea 🇰🇷!🎉 We present ParticleFormer, a Transformer-based 3D world model that learns from point cloud perception and captures complex dynamics across multiple objects and material types ! 🌐 Project website:

🔥 Proud to present our SIGGRAPH 2025 Journal paper — DiffuseCLoC: Guided Diffusion for Physics-Based Character Look-Ahead Control🚀 A single, generalist control policy that solves diverse tasks at test-time, no fine-tuning needed. 🎥 Proj Page: diffusecloc.github.io/website 🧵Thread👇