Robot learning of manipulation skills is hindered by the scarcity of diverse, unbiased
datasets. While curated datasets can help, challenges remain in generalizability and real …

Robot learning has emerged as a promising tool for taming the complexity and diversity of
the real world. Methods based on high-capacity models, such as deep networks, hold the …

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 …

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 …

To build general robotic agents that can operate in many environments, it is often imperative
for the robot to collect experience in the real world. However, this is often not feasible due to …

The ability to specify robot commands by a non-expert user is critical for building generalist
agents capable of solving a large variety of tasks. One convenient way to specify the …

Prompt-based learning has emerged as a successful paradigm in natural language
processing, where a single general-purpose language model can be instructed to perform …

In recent years, instruction-tuned Large Multimodal Models (LMMs) have been successful at
several tasks, including image captioning and visual question answering; yet leveraging …

Key challenges for the deployment of reinforcement learning (RL) agents in the real world
are the discovery, representation and reuse of skills in the absence of a reward function. To …

Representation learning approaches for robotic manipulation have boomed in recent years.
Due to the scarcity of in-domain robot data, prevailing methodologies tend to leverage large …