Deep supervised learning algorithms typically require a large volume of labeled data to
achieve satisfactory performance. However, the process of collecting and labeling such data …

Deep reinforcement learning (RL) has emerged as a promising approach for autonomously
acquiring complex behaviors from low-level sensor observations. Although a large portion of …

We study how vision-language models trained on Internet-scale data can be incorporated
directly into end-to-end robotic control to boost generalization and enable emergent …

By transferring knowledge from large, diverse, task-agnostic datasets, modern machine
learning models can solve specific downstream tasks either zero-shot or with small task …

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

We study how vision-language models trained on Internet-scale data can be incorporated
directly into end-to-end robotic control to boost generalization and enable emergent …

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 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 …

We study how visual representations pre-trained on diverse human video data can enable
data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a …

In this work, we explore self-supervised visual pre-training on images from diverse, in-the-
wild videos for real-world robotic tasks. Like prior work, our visual representations are pre …