🤖 Introducing RoboTok, the “TikTok for robots.” Just as TikTok recommends videos to people, RoboTok recommends relevant human demonstrations for robot learning. Robot learning needs broad and diverse demonstrations, but collecting robot data is expensive. RoboTok is an internet-scale data engine that uses web video as a scalable and continuously growing source of demonstrations for dexterous manipulation learning. Given one human demonstration video as a query, RoboTok retrieves other web videos with similar underlying manipulation motions. Rather than matching videos by labels or visual appearance, RoboTok compares how the hands move over time. 💡 The key idea is to represent each video with canonicalized 3D hand trajectories. Each trajectory is expressed in an estimated actor-centered reference frame, so the movement is described relative to the person rather than the camera. This makes similar manipulation behaviors easier to compare across different viewpoints and scenes, even when the actor is partly occluded. In our experiments, RoboTok retrieved more manipulation-relevant demonstrations than existing robot-data retrieval methods. When those videos were used to guide robot training, the simulated robots completed manipulation tasks more successfully. I’m sincerely grateful to Howard Qian and Kaiyu Hang for leading this project. I also want to thank Yiting Chen, Kejia Ren, Podshara Chanrungmaneekul, Gaotian Wang, Bowen Wen @bowenwen_me, and Chen Wei @_Chen_Wei_ for their guidance and collaboration. Project site: rice-robotpi-lab.github.io/R… Paper: arxiv.org/abs/2609.03199 Code: github.com/Rice-RobotPI-Lab/… Data and models: huggingface.co/Rice-RobotPI-…