We investigate the challenge of parametrizing policies for reinforcement...
Large Language Models (LLMs) significantly benefit from Chain-of-Thought...
We study generalizable policy learning from demonstrations for complex
l...
In this work, we aim to learn dexterous manipulation of deformable objec...
We present MovingParts, a NeRF-based method for dynamic scene reconstruc...
Generalizable manipulation skills, which can be composed to tackle
long-...
Effective planning of long-horizon deformable object manipulation requir...
Training long-horizon robotic policies in complex physical environments ...
Modeling and manipulating elasto-plastic objects are essential capabilit...
Differentiable physics has recently been shown as a powerful tool for so...
We consider the problem of sequential robotic manipulation of deformable...
We present a method to learn compositional predictive models from image
...
In this paper, we focus on the simulation of active stereovision depth
s...
Learning generalizable manipulation skills is central for robots to achi...
Simulated virtual environments serve as one of the main driving forces b...
Current graph neural networks (GNNs) lack generalizability with respect ...
We address the problem of discovering 3D parts for objects in unseen
cat...
An agent that has well understood the environment should be able to appl...
We introduce associative embedding, a novel method for supervising
convo...