We have 3 of 18 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
P predictive visual latents are established as a foundation for effective WAM learning from task-specific demonstrations and for transferring future-modeling knowledge acquired from broader in-the-wild videos.
WNM-3D, a generative World Navigation Model with 3D scene conditioning for continuous VLN, is presented, showing that WNM-3D outperforms strong VLM-based navigation policies and its 2D-conditioned counterpart in closed-loop navigation.
KineBench is an IDM-free closed-loop benchmark for EWMs, built upon an explicit kinematic grounding pipeline, and reveals task-complexity-bounded nonlinear scaling in embodied video generation, providing empirical guidance for future data-scaling strategies.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
