The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
arXiv:2611.08477v1 Announce Type: new Abstract: Modern video models possess strong visual priors, yet do not natively represent human action in metric 3D space. We present EgoGeneralist, which adapts...
The paper introduces P³-WAM, a unified world action model for egocentric dexterous manipulation that integrates 3D perception, action-conditioned prediction, and goal-directed planning. It operates in three modes—Perceive, Predict, and Plan—using a mixture-of-transformers architecture that shares base weights and adapts to modality-specific inputs. Experiments demonstrate that unified training improves performance across all three capabilities, outperforming specialized baselines on 3D hand reconstruction and action-conditioned video prediction while producing more instruction‑adherent manipulation videos.
arXiv:2610.27946v1 Announce Type: new Abstract: Egocentric action transfer aims to decouple the semantic action from egocentric observations and reproduce them in new visual contexts, enabling scalab...
EgoGen is a synthetic data generator designed for egocentric perception tasks, producing accurate ground‑truth training data by simulating natural human movements that steer virtual cameras. Its core is a human motion synthesis model that uses egocentric visual inputs to sense 3D environments, combined with collision‑avoiding motion primitives and a two‑stage reinforcement learning approach for closed‑loop perception and movement. The system eliminates the need for pre‑defined global paths, works in dynamic settings, and supports tasks such as mapping, localization, camera tracking, and human mesh recovery from first‑person views.
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.
arXiv:2506.07886v4 Announce Type: replace Abstract: Understanding multimodal signals in egocentric vision, such as RGB video, depth, camera poses, and gaze, is essential for applications in augmented...