Please come and join our VGI workshop! We'd love to discuss the future of Visual Intelligence with you and explore its potential as the next major trend in AI.
#CVPR2026@CVPR
🚀 RoboManipBaselines (RMB) v3 released
An open-source framework for imitation learning in robotic manipulation.
🔗 data → training → rollout
🌍 sim + real robots
🧩 vision / 3D / tactile / language
🚀 π0 / GR00T (VLA)
🎥 https://t.co/P3nb3FlGH9
We've released the ICCV 2025 Report!
https://t.co/WoQKQqQnTz
Compiled during ICCV in collaboration with LIMIT.Lab, cvpaper.challenge, and Visual Geometry Group (VGG), this report offers meta insights into the trends and tendencies observed at this year's conference.
#ICCV2025
We organized the "Cambridge Computer Vision Workshop" at the University of Cambridge together with @elliottszwu, @gatheluck, and LIMIT.Lab! It was a fantastic workshop featuring presentations, networking, and discussions.
https://t.co/6uLy3aCLvr
Thanks to a unified internal design, switching between robots, imitation learning methods, action/observation data, and teleoperation devices is now seamless! Supports simulation of mobile manipulators and dual-arm humanoids - significantly expanding the range of use cases!
We've released Version 2 of RoboManipBaselines - a unified software platform to benchmark the latest imitation learning methods (SARNN, ACT, DiffusionPolicy) on both simulated and real-world robots!
We have released RoboManipBaselines, software that allows you to easily try and validate state-of-the-art imitation learning (SARNN, ACT, and DiffusionPolicy) on simulations and real-world robots! Some training datasets and trained models are also available!