Search papers, labs, and topics across Lattice.
3
0
5
17
Randomly sampling tasks in offline RL hurts zero-shot generalization, but extracting task vectors directly from the dataset boosts performance by 20%.
Robots can now understand human intentions with near-human accuracy thanks to a new video-language model that reasons about goals like a human.
Stop hand-designing subgoals: HD-ExpIt uses environment feedback to iteratively refine hierarchical diffusion policies, teaching the planner to generate subgoals that the controller can actually achieve.
