RoboTok is an internet‑scale data engine that retrieves human manipulation videos from the web to train dexterous robot policies. It learns a latent motion space from 3D hand trajectories in actor‑centered reference frames, allowing manipulation behaviors to be compared across different viewpoints, scenes, and occlusions while remaining compact for efficient search. Experiments show RoboTok retrieves more relevant demonstrations and improves downstream robot task success compared to existing retrieval methods.
arXiv:2606. 10614v1 Announce Type: cross Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real robots.
arXiv:2606. 11628v1 Announce Type: cross Abstract: The most widely-adopted robot learning pipelines today learn skills from robot demonstrations or structured human data, which are expensive to collect and tied to specific embodiments.
arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
arXiv:2608. 14028v1 Announce Type: cross Abstract: Dexterous manipulation is a fundamental capability for embodied intelligence, but scaling it remains difficult because robot demonstrations are expensive to collect and action spaces vary across embodiments.
arXiv:2606. 06627v1 Announce Type: cross Abstract: Human video datasets used for cotraining robot manipulation policies largely consist of curated demonstrations where motions are orchestrated to resemble robot behavior and 3D hand poses are captured with specialized hardware.
arXiv:2505. 04999v2 Announce Type: replace-cross Abstract: Learning robot control policies from demonstrations typically requires action-labeled expert data, which is expensive to collect through teleoperation.
GeoLAM is a framework that learns geometry‑grounded latent actions from unlabeled human videos. It uses future‑frame reconstruction with a frozen geometric feature hierarchy and motion supervision from a 4D geometry teacher to capture 3D displacement, image‑plane motion, and surface‑orientation changes. After pretraining, the representation serves as transition targets for a world‑action model trained on robot demonstrations, enabling denoised latent actions and executable action chunks without requiring hand‑pose annotations or future‑video generation during deployment.
Generalizable robot manipulation requires policies that can anticipate how visual scenes evolve while executing language instructions. While recent Vision-Language-Action models benefit from large-scale pretraining, their predominantly static pretraining objectives provide limited supervision for physical dynamics and temporal causality, leaving control-relevant knowledge to be learned from downstream robot demonstrations.
arXiv:2606. 28813v1 Announce Type: cross Abstract: Human videos are a scalable source of supervision for robot manipulation, as they are abundant and naturally capture rich object interactions.
HumanEgo is a framework that enables zero‑shot robot learning from short egocentric human videos by converting each demonstration into an entity‑level hand‑object interaction representation and training a flow‑matching policy with dense auxiliary objectives. The method is robot‑data‑free, hardware‑agnostic, and data‑efficient, achieving 92.5 % success on four real‑world tasks with only 30 minutes of human video per task and outperforming matched‑time robot teleoperation by 41 %. HumanEgo also robustly transfers zero‑shot across new robots, cameras, and environments, and is released as an open‑source tool for learning robot policies directly from human data.
Scaling robot learning requires large-scale, diverse demonstrations, yet real-world data collection via teleoperation remains prohibitively expensive and time-consuming. While video diffusion models offer a promising avenue for data scaling, existing generative approaches are often limited to superficial visual augmentation, or suffer from embodiment hallucinations that yield physically infeasible motions.
World models offer a promising route toward robot planning by enabling agents to imagine and verify the consequences of actions before execution. However, current video-based world models often struggle to capture the physical constraints that govern manipulation, particularly contact.