Large language models excel at a wide range of complex tasks. However,
e...
Recent advances in robot learning have shown promise in enabling robots ...
In recent years, much progress has been made in learning robotic manipul...
Model-based reinforcement learning (RL) methods are appealing in the off...
We present a framework for building interactive, real-time, natural
lang...
Recent works have shown how the reasoning capabilities of Large Language...
Perceptual understanding of the scene and the relationship between its
d...
Reinforcement learning (RL) agents are widely used for solving complex
s...
We find that across a wide range of robot policy learning scenarios, tre...
We investigate the visual cross-embodiment imitation setting, in which a...
Self-supervised learning algorithms based on instance discrimination tra...
Many modern approaches to offline Reinforcement Learning (RL) utilize
be...
Rearranging and manipulating deformable objects such as cables, fabrics,...
Robotic manipulation can be formulated as inducing a sequence of spatial...
We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm...
We present an approach for estimating the period with which an action is...
Fully convolutional deep correlation networks are integral components of...
When performing imitation learning from expert demonstrations, distribut...
As synthetic imagery is used more frequently in training deep models, it...
We introduce a self-supervised representation learning method based on t...
We propose learning from teleoperated play data (LfP) as a way to scale ...
The Generative Adversarial Imitation Learning (GAIL) framework from Ho &...
In this work we explore a new approach for robots to teach themselves ab...
This paper presents KeypointNet, an end-to-end geometric reasoning frame...
We present a box-free bottom-up approach for the tasks of pose estimatio...
We propose a method for multi-person detection and 2-D pose estimation t...
Efficient simulation of the Navier-Stokes equations for fluid flow is a ...
Current state-of-the-art classification and detection algorithms rely on...
Current state-of-the-art classification and detection algorithms rely on...
Recent state-of-the-art performance on human-body pose estimation has be...
In this work, we propose a novel and efficient method for articulated hu...
This paper proposes a new hybrid architecture that consists of a deep
Co...
This paper introduces a new architecture for human pose estimation using...