Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models
Paper • 2609.12641 • Published • 80
xy
xy0123
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models upvoted a paper 12 months ago
Revealing the Implicit Noise-based Imprint of Generative ModelsOrganizations
None yet
upvoted a paper about 1 month ago