We present speculative sampling, an algorithm for accelerating transform...
Building models that can be rapidly adapted to numerous tasks using only...
We investigate the optimal model size and number of tokens for training ...
Real-world data is high-dimensional: a book, image, or musical performan...
The performance of a language model has been shown to be effectively mod...
We enhance auto-regressive language models by conditioning on document c...
The recently-proposed Perceiver model obtains good results on several do...
We introduce a human-compatible reinforcement-learning approach to a
coo...
OpenSpiel is a collection of environments and algorithms for research in...
We propose a novel method for generating natural language sentences from...
The study of object representations in computer vision has primarily foc...