CVPR 2026 Workshop Competition
| 1:00pm-1:30pm | Workshop overview |
| 1:30pm-2:10pm | RoboTwin Track |
| 2:10pm-3:00pm | GigaWorld Track |
| 3:00pm-3:20pm | Coffee Break |
| 3:20pm-4:00pm | RoboChallenge Track |
| 4:00pm-4:40pm | PhysClaw* Track |
| 4:40pm-5:20pm | Best Paper Award |
| 5:20pm-6:00pm | QA + Closing + Networking |
The GigaBrain Challenge 2026 aims to push the boundaries of embodied intelligence. The workshop features four competition tracks focused on simulation, world models, real-world robot evaluation, and creative agentic demos for embodied AI, along with a Best Paper session showcasing outstanding research contributions. Beyond the formal program, participants will also have the opportunity to hear firsthand know-how sharing from organizers, competition winners, and researchers on key topics such as world models, VLA, embodied foundation model evaluation, simulation, and agentic systems for embodied intelligence. If you would like to connect with the embodied AI community and gain practical insights into where the field is heading, we would love to see you there in person.
Note:
The competition will conclude by May 15, 2026. No onsite competition will be held at CVPR; the workshop session will focus on awards ceremonies and presentations by winning teams.
Final rankings for all four tracks. Congratulations to the winning teams!
Evaluate VLA performance in simulation environments.
Yixian Zou, Ningyue Zhang, Shangwei Li, Zhengning Wang
University of Electronic Science and Technology of China
Yuanchang Liang, Xiaobo Wang, Shengtao Zheng, Chenxu Zhao, Ping Jiang, Minghui Wu
National University of Singapore, Shenzhen University of Advanced Technology, Sangfor Technologies Inc., Tsinghua University, Mininglamp Technology
Evaluate the performance of World Models acting as VLA evaluators.
Zhenyu Wu, Xiuwei Xu, Ziwei Wang, Jiwen Lu
Tsinghua University
Peng Zhang, Jiangyang Li, Lingjun Zhang, Changjie Wu, Xu Wang, Linzhe Shi, Hang Zhang
AMAP CV Lab
Zhengwei Hu, Hao Ke, Zhaoyang Liu, Jiahua Wang, Yang Zhong, Yuhao Yang, Xuelin Tian
Xiaomi EV
Evaluate VLA performance on real-world robots.
Lixin Huang, Kun Yu, Zhengming Zhou, Bowen Fu, Zhiying Du, Wenguo Hou, Xin Zhao, Diyun Xiang, Rui Cai
Zhi Lv, Lianghai Tian, Zhenyu Zhao, Riqiang Jin, Qi Xu, Mochen Yu, Yao Tang
Rongxu Cui, Jian Wang
Collect creative ways to use OpenClaw on embodied agents.
Shilin Ma, Chubin Zhang, Xulong Bai, Zifeng Gao, Shiyi Zhang, Yansong Tang
Tsinghua Shenzhen International Graduate School, Tsinghua University
Zhipeng Jiang, Xinyu Zhang, Hanzhang Fang, Jing Huang, Ying Zhou
New Jersey Institute of Technology; Indiana University -- Bloomington; New Jersey Institute of Technology; New Jersey Institute of Technology; Georgia Institute of Technology
Weijie Ke, Shuo Wang, Ying Wang, Pei Zhang, Haofeng Yu, Bingshan Hu
University of Shanghai for Science and Technology
We welcome submissions related to VLA, embodied foundation models, world models, and reinforcement learning. Accepted papers will be presented in the workshop and selected works will be assigned poster boards. We will select a Best Paper Award.
OpenReview SubmissionTrack 1 (Simulation) and Track 2 (World Model) begin.
OpenReview submission portal opens ( OpenReview ).
Deadline for paper submissions (timezone: AoE, UTC-12).
Track 1 & 2 conclude. Track 3 (Real Robot) begins with invited teams.
All tracks conclude. Final rankings determined.
Awards ceremony and presentations by winning teams in Denver, USA.
Horizon Robotics
Computational FREEDOM