Newest papers

Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience

Tianqi Liu, Hanfei Zhao, Qifeng Liang, Hui En Pang, Jiarui Xu, S Mu, 邱鹏昊, YingSheng Zhang, Jun Wang, Ziang Cao, Mingze Sun, Yukang Cao, Fangzhou Hong, Zhaoxi Chen, Ziwei Liu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26855 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

Os modelos de interação do mundo permitem que os agentes de dados encarnados antecipem as consequências da ação, mas a modelação conjunta de locomoção e manipulação em vários modos de execução permanece desafiadora devido a espaços de ação heterogêneos e supervisão multimodal limitada. Nós apresentamos o Ropedia W0, o primeiro modelo de fundação do mundo de locomoção-manipulação egocêntrica que abrange humanos e robôs com vários modos de execução. Nós curamos Xp-Data, que inclui 10k horas de dados egocêntricos humanos e 3k horas de avaliação de dados de robôs com anotações multimodais unificadas e controle de qualidade sistemático. Uma representação cinemática unificada codifica a locomoção através de poses de câmera e manipulação

Machine translation (Meta M2M100); the English original follows.

Abstract

World models enable embodied agents to anticipate action consequences, yet jointly modeling locomotion and manipulation across diverse embodiments remains challenging due to heterogeneous action spaces and limited multimodal supervision. We present Ropedia W0, the first egocentric loco-manipulation world foundation model spanning humans and robots with diverse embodiments. We curate Xp-Data, comprising 10k hours of egocentric human data and 3k hours of robot data with unified multimodal annotations and systematic quality control. A unified kinematic representation encodes locomotion through camera poses and manipulation through projected skeletons, with robot skeletons combining embodiment-specific forward kinematics with extensive manual keypoint annotation and correction. We also introduce Xp-Teleop, a long-horizon loco-manipulation benchmark based on high-quality dexterous humanoid teleoperation data. Evaluations demonstrate state-of-the-art performance across five cross-embodiment benchmarks (DreamDojo, $Ψ_0$, $ω$-HOME, Xp-Teleop, and AgiBot) and on held-out human egocentric video, from zero-shot inference to few-shot and full-data post-training. Scaling human pre-training data improves performance on both human and robot evaluations. After distillation, our model supports real-time, minute-long rollouts, enabling live VR interaction. Applications in policy evaluation, model-based planning, and world-action modeling further demonstrate the model's utility for embodied decision-making.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Artificial intelligence, Robot, Humanoid robot, Kinematics, Action (physics)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange