user avatar
Bolei Zhou
Coco Robotics
@zhoubolei
Associate Professor at the Computer Science Department @UCLAComSci @UCLAengineering @UCLA and Chief AI Scientist at @CocoRobotics
Los Angeles
Joined October 2010
Posts
  • user avatar
    No accepted papers, I am still happy to announce we open-source GenForce, an efficient PyTorch library for generative modeling. StyleGAN and PG-GAN are perfectly reproduced. We also collect a zoo of 60+ pretrained StyleGAN models, with Colab to play. github.com/genforce/genfo…
    00:00
  • user avatar
    Two NeurIPS'20 rejections are accepted to CVPR'21 as Orals, including the following work of unsupervised learning of steerable dimension in GANs (genforce.github.io/sefa/). Should thank all NeurIPS adversary reviewers for making this a better work. Be more resilient and optimistic
    00:00
  • user avatar
    I will move to UCLA Computer Science early next year to continue my academic journey. I am grateful for the enormous support from many smart and energetic people as collaborators, colleagues, and peers. Look forward to the exciting new chapter with @UCLAengineering @CS_UCLA
  • user avatar
    I've officially become an Associate Professor with tenure at @UCLA @UCLAengineering as we kick off the new academic year on July 1! Deepest gratitude to my mentors, my amazing students, and wonderful collaborators. Incredible journey so far—more exciting research ahead! 🚀
  • user avatar
    received a student’s CV where only rejections are listed in the Publication. Well, I actually like it! Going through the submission cycle and feeling the academic setback twice already makes the undergrad stand out than most of the peers
  • user avatar
    Our recent @CVPR 25 paper develops a Vid2Sim method that turns a video captured by mobile phone into an interactive environment represented by Gaussian Splatting to train RL agent for urban navigation. Incredible @ZiyangXie_ leaded the project. Webpage: metadriverse.github.io/vid2sim/
    00:00
  • user avatar
    Our NeurIPS '25 Spotlight paper presents an *online* preference learning or RLHF method that enables agents to learn from human feedback in real-time — a step toward safer and more aligned AI for robots. Led by Haoyuan Cai and Zhenghao Peng Webpage: metadriverse.github.io/ppl/
    00:00
  • user avatar
    We release a new urban simulator, MetaUrban, to support research on AI agents for micromobility. The work will be presented at #ICLR2025, and the demo code can run on any laptop. Webpage: metadriverse.github.io/metaurban/ Code: github.com/metadriverse/m… Paper: arxiv.org/pdf/2407.08725
    00:00
  • user avatar
    Our recent #ICLR2022 work develops an efficient Human-in-the-loop learning method called HACO (Human-AI CoPilot), to mentor agents interactively to act and drive while preserving their own curiosity and exploration. Paper and code are available at decisionforce.github.io/HACO/
    00:00
  • user avatar
    🚦 Excited introducing Urban-Sim — our new simulator presented at #CVPR2025 as a highlight paper! ⚡️ Fast training with IsaacSim backend 🏙️ Diverse 3D assets for rich urban scenes 🤖 Towards generalizable robots in dynamic urban environments. Webpage: metadriverse.github.io/urban-sim/
    00:00
  • user avatar
    As many conferences are coming in the summer, here I share some of the academic posters my collaborators and I have designed as a reference, with both PDF and PPT templates available. Hope to see your awesome posters soon!
  • user avatar
    #ICLR2025 My lab members, Zhizheng and Joe, will present our work on learning to generate diverse pedestrians by watching web videos this week in Singapore. Let's fill the ghost town house with people in simulations! Webpage: genforce.github.io/PedGen/ Code: github.com/genforce/PedGen
    00:00
  • user avatar
    Honored to be part of the big family. Go Bruins 🎉 !
    We are thrilled to have Bolei Zhou @zhoubolei join our faculty @CS_UCLA in January. Welcome to @UCLA! samueli.ucla.edu/ucla-samueli-w…
  • user avatar
    Our project on Reinforcement Learning for versatile exoskeleton controllers is published in Nature. I hope there is more AI assistive technology to augment humans in the physical world. The project is led by NCSU Hao Su's group and the paper is rdcu.be/dKCZV
    00:00