This paper improves the speed of generating text and images in vision-language models by adapting the way the model proposes tokens, and it could be useful to developers who want to build faster and more accurate models for applications like image captioning or text-to-image synthesis.
Firehose
Filtered to Papers, tagged “speculative decoding” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives