Large, high-capacity models trained on diverse datasets have shown remarkable successes
on efficiently tackling downstream applications. In domains from NLP to Computer Vision …

Large, high-capacity models trained on diverse datasets have shown remarkable successes
on efficiently tackling downstream applications. In domains from NLP to Computer Vision …

Learning rewards from expert videos offers an affordable and effective solution to specify the
intended behaviors for reinforcement learning (RL) tasks. In this work, we propose Diffusion …

This paper provides a structured and practical roadmap for practitioners to integrate learning
from demonstration (LfD) into manufacturing tasks, with a specific focus on industrial …

Foundation models (FMs), large deep learning models pre-trained on vast, unlabeled
datasets, exhibit powerful capabilities in understanding complex patterns and generating …

Robots can use visual imitation learning (VIL) to learn manipulation tasks from video
demonstrations. However, translating visual observations into actionable robot policies is …

In this work, we aim to learn a unified vision-based policy for multi-fingered robot hands to
manipulate a variety of objects in diverse poses. Though prior work has shown benefits of …

Large, high-capacity models trained on diverse datasets have shown remarkable successes
on efficiently tackling downstream applications. In domains from NLP to Computer Vision …

Humans inherently possess generalizable visual representations that empower them to
efficiently explore and interact with the environments in manipulation tasks. We advocate …

Eye-in-hand cameras have shown promise in enabling greater sample efficiency and
generalization in vision-based robotic manipulation. However, for robotic imitation, it is still …