Bolei Zhou
@zhoubolei • 9,348 subscribers
Associate Professor at the Computer Science Department @UCLAComSci @UCLAengineering @UCLA and Chief AI Scientist at @CocoRobotics. Opinions are my own.
Videos
I took this video at IROS’26 in Pittsburgh two days ago. At first glance, it looks like an impressive autonomous humanoid making cocktail drinks. Zoom out, and you see what is really behind it. I have mixed feelings about watching this. 1. Teleoperation is getting remarkably good. Data collection is becoming more accurate, scalable, and immersive. Combined with rapidly improving AI models, I can imagine much of this eventually becoming autonomous. That is exciting, but it also makes the potential impact on human jobs feel much more immediate. 2. But what are we actually seeing in a robot demo? Without proper disclosure or reference, it can be surprisingly difficult to distinguish teleoperation from autonomy. As physical AI attracts more attention and investment, demos need to be much clearer about how much is autonomous and how much is human-controlled. 3. Even “autonomous” demos can be difficult to interpret. Is the robot actually generalizing? Or is it replaying a demonstration, following a scripted trajectory, or overfitting to one carefully prepared environment? A tabletop demo alone often can’t tell us. Maybe the important question for Physical AI is no longer just “Can the robot do it?” It is also: “How did the robot do it, and will it still work when we change the task, objects, or environment?”
Bolei Zhou44,871 görüntüleme • 26 gün önce
Last semester, I taught Reinforcement Learning class again at UCLA. Together with my amazing TAs Matthew and Caiyuan, we built a mini-project: MetaDrive Arena 🚗🤖 Students applied what they learned in class, trained RL agents, and competed on a live leaderboard. The results were incredible, with 94 agents, 2K submissions, and 130K matches. We saw tons of creativity, clever ideas, and real progress in learning. We’re now releasing it publicly to support RL education and experimentation. Try it out and train your own agent at 🔗
Bolei Zhou25,389 görüntüleme • 7 ay önce
We’ve just open-sourced JOSH, our method for 4D human–scene reconstruction in the wild. Huge credit to the first author, my PhD student Zhizheng, who will present this work at ICLR in Brazil next month 🇧🇷 🌐 Project page: 💻 Code: A trivia is that this work was finished more than one year ago, and has been rejected twice...Be resilient!
Bolei Zhou25,616 görüntüleme • 7 ay önce
--Towards Scalable Sidewalk Autonomy (2/4)-- Introducing UrbanVerse — turning city-tour videos into physics-aware, interactive simulations for scalable robot learning in NVIDIA Omniverse. 🌆 Real-world scene layouts 🧱100K+ 3D assets ICLR’26 paper and **Open-source** assets at 🔗 We thank Coco Robotics for robot support and NVIDIA Academic Grant support NVIDIA Robotics
Bolei Zhou15,081 görüntüleme • 6 ay önce
Tomorrow (Thursday morning), 9:00–10:30 AM, I'll be at Poster 326 to present our work on a new imitation learning framework, MIMIC, for training a sidewalk autopilot. Stop by if you're attending #ICRA2026 in Vienna: MIMIC (Multi-scale IMItation with Corrective expansions) trains sidewalk autopilots from teleoperation data by expanding corrective behaviors and visual diversity through generative augmentation. Project page:
Bolei Zhou11,645 görüntüleme • 4 ay önce
So proud of our UCLA VAIL students ❤️We have 4 papers accepted at ICLR 2026 (ICLR), covering topics including 3D reconstruction, simulation, robot learning, and driving scenario generation. What people don’t see: 3 of these papers were rejected before. It wasn’t easy — but resilience thrives and persistence matters ❤️ Papers are available at
Bolei Zhou10,099 görüntüleme • 9 ay önce
Daha fazla içerik yok.