Understanding contact and tactile magnitude in hand-object interaction is a key step toward physically intelligent systems, yet learning such representations is limited by the cost and restricted coverage of tactile measurements. We present Touch-JEPA, a framework for learning tactile representations from hand-object v...
Minseong Kweon, Qiao Feng, Yi-Ming Huang et al.· 0 citations
Latent Action Models (LAMs) can capture manipulation priors from action-free videos, but discrete latents usually impose a granularity bottleneck, limiting their ability to represent fine-grained action. Recent continuous alternatives mitigate this, but they are typically used as proxies for world modeling and require...
Lei Yao, Qiao Feng, Mu-Tian Tong et al.· 0 citations
PhysStream is an autoregressive model for physics-grounded image-to-video synthesis that incorporates structured scene memory and supports fine-grained motion control via sparse velocity-increment signals that encode physical quantities, letting the model learn the underlying dynamics.
Chuhao Chen, Peter Wonka, Chao-Yang Wang et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.