Visual reinforcement learning (RL) has shown promise in continuous control tasks. Despite
its progress, current algorithms are still unsatisfactory in virtually every aspect of the …

Recently, people have shown that large-scale pre-training from internet-scale data is the key
to building generalist models, as witnessed in NLP. To build embodied generalist agents …

Video instance segmentation requires classifying segmenting and tracking every object
across video frames. Unlike existing approaches that rely on masks boxes or category labels …

Dyna-style model-based reinforcement learning contains two phases: model rollouts to
generate sample for policy learning and real environment exploration using current policy …

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

We present Premier-TACO, a multitask feature representation learning approach designed
to improve few-shot policy learning efficiency in sequential decision-making tasks. Premier …

Recently, various pre-training methods have been introduced in vision-based
Reinforcement Learning (RL). However, their generalization ability remains unclear due to …

Can we endow visuomotor robots with generalization capabilities to operate in diverse open-
world scenarios? In this paper, we propose\textbf {Maniwhere}, a generalizable framework …

Generalization capabilities, or rather a lack thereof, is one of the most important unsolved
problems in the field of robot learning, and while several large scale efforts have set out to …

Learning representations for reinforcement learning (RL) has shown much promise for
continuous control. We propose an efficient representation learning method using only a self …