Every major technical invention resurfaces the dual-use dilemma – the ne...
Recent studies on transformer-based language models show that they can a...
The fluency and factual knowledge of large language models (LLMs) height...
A growing ecosystem of large, open-source foundation models has reduced ...
While large pre-trained language models are powerful, their predictions ...
Even the largest neural networks make errors, and once-correct predictio...
While large pre-trained models have enabled impressive results on a vari...
We study the problem of learning a range of vision-based manipulation ta...
Massive datasets have proven critical to successfully applying deep lear...
We consider the problem of planning views for a robot to acquire images ...
We present a method to represent 3D objects using higher order functions...
A major challenge in reinforcement learning for continuous state-action
...
We present a novel method enabling robots to quickly learn to manipulate...
We propose a method of aligning a source image to a target image, where ...
Off-Policy reinforcement learning (RL) is an important class of methods ...