Real-world videos provide rich demonstrations of manipulation, but turning them into reusable robot skills requires visually aligned environments, executable physical interactions, and mechanisms for learning from experience. We introduce Real2Gym, an agentic Real2Sim2Real framework that turns human and robot demonstra...
Ke-Rui Ren, Ying Xu, Kai-Wen Song et al.· 1 citation
GeoVerse is a framework that synthesizes world-consistent novel views by performing generation within the geometric latent space of a pretrained 3D foundation model and injecting appearance priors from a video generative model via a ControlNet-style adapter.
Ke-Rui Ren, Tao Lu, Lin-Ning Xu et al.· 0 citations
Skel-WAM is introduced, a world action model that bridges differences between human and robot motion through a unified hand-skeleton motion interface, and demonstrates that a shared skeletal interface enables joint learning across human and robot data and expands robot task coverage through complementary human demonstr...
Ze-Tao Cai, Ya-Ping Li, Yi-Qun Wang et al.· 0 citations
An efficient generative framework designed to improve in-the-wild robustness under diverse real capture conditions and demonstrate strong perceptual quality, semantic fidelity, and temporal consistency on unseen videos, as well as improved robustness in downstream 3D reconstruction under severe motion blur.
