Large policies pretrained on diverse robot datasets have the potential to transform robotic
learning: instead of training new policies from scratch, such generalist robot policies may be …

Imitation learning from a large set of human demonstrations has proved to be an effective
paradigm for building capable robot agents. However, the demonstrations can be extremely …

In supervised learning, the question of data quality and curation has been sidelined in
recent years in favor of increasingly more powerful and expressive models that can ingest …

We introduce GROOT, an imitation learning method for learning robust policies with object-
centric and 3D priors. GROOT builds policies that generalize beyond their initial training …

Learning to solve tasks from a sparse reward signal is a major challenge for standard
reinforcement learning (RL) algorithms. However, in the real world, agents rarely need to …

We present Neural Signal Operated Intelligent Robots (NOIR), a general-purpose, intelligent
brain-robot interface system that enables humans to command robots to perform everyday …

Deep generative models (DGMs) have demonstrated great success across various domains,
particularly in generating texts, images, and videos using models trained from offline data …

Enabling robots to learn novel visuomotor skills in a data-efficient manner remains an
unsolved problem with myriad challenges. A popular paradigm for tackling this problem is …

A rich representation is key to general robotic manipulation, but existing approaches to
representation learning require large amounts of multimodal demonstrations. In this work we …

We tackle the problem of developing humanoid loco-manipulation skills with deep imitation
learning. The difficulty of collecting task demonstrations and training policies for humanoids …