We present a self-supervised sensorimotor pre-training approach for robo...
We present a sim-to-real learning-based approach for real-world humanoid...
We study the problem of imitating object interactions from Internet vide...
In this work, we explore self-supervised visual pre-training on images f...
We explore a data-driven approach for learning to optimize neural networ...
This paper shows that self-supervised visual pre-training from real-worl...
In this work we explore reconstructing hand-object interactions in the w...
Dexterous manipulation has been a long-standing challenge in robotics.
R...
In this work, we present a new network design paradigm. Our goal is to h...
Over the past several years progress in designing better neural network
...
In this work we address task interference in universal networks by
consi...
We investigate omni-supervised learning, a special regime of semi-superv...