Diffusion models have quickly become the go-to paradigm for generative
m...
Can continuous diffusion models bring the same performance breakthrough ...
Programming is a powerful and ubiquitous problem-solving tool. Developin...
Beam search is the go-to method for decoding auto-regressive machine
tra...
We propose a novel hierarchical agent architecture for multi-agent
reinf...
As datasets continue to increase in size and multi-core computer
archite...
Due to their simplicity and excellent performance, parallel asynchronous...
We propose SEARNN, a novel training algorithm for recurrent neural netwo...
We describe ASAGA, an asynchronous parallel version of the incremental
g...