Generative pre-trained models have demonstrated remarkable effectiveness in language
and vision domains by learning useful representations. In this paper, we extend the scope of …

Learning from demonstration is a powerful method for teaching robots new skills, and having
more demonstration data often improves policy learning. However, the high cost of collecting …

Scaling deep learning to massive, diverse internet data has yielded remarkably general
capabilities in visual and natural language understanding and generation. However, data …

World models can foresee the outcomes of different actions, which is of paramount
importance for autonomous driving. Nevertheless, existing driving world models still have …

In this work, we present an approach to construct a video-based robot policy capable of
reliably executing diverse tasks across different robots and environments from few video …

We present GR-2, a state-of-the-art generalist robot agent for versatile and generalizable
robot manipulation. GR-2 is first pre-trained on a vast number of Internet videos to capture …

The evolution of video generation from text, starting with animating MNIST numbers to
simulating the physical world with Sora, has progressed at a breakneck speed over the past …

Building generalist agents that can accomplish many goals in rich open-ended
environments is one of the research frontiers for reinforcement learning. A key limiting factor …

We address the challenge of acquiring real-world manipulation skills with a scalable
framework. We hold the belief that identifying an appropriate prediction target capable of …

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 …