Text embeddings are useful features in many applications such as semanti...
Diffusion models have recently been shown to generate high-quality synth...
We show how to derive state-of-the-art unsupervised neural machine
trans...
Recent work has demonstrated substantial gains on many NLP tasks and
ben...
Traditional Reinforcement Learning (RL) algorithms either predict reward...
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge,
p...
Efficient exploration is an unsolved problem in Reinforcement Learning. ...
Rapid learning requires flexible representations to quickly adopt to new...