Understanding Transformers via N-gram Statistics(arxiv.org)110 points by pona-a 1 year ago | 13 comments
Atlas: Learning to Optimally Memorize the Context at Test Time(arxiv.org)27 points by og_kalu 1 year ago | 2 comments
TPDE: A Fast Adaptable Compiler Back-End Framework(arxiv.org)43 points by npalli 1 year ago | 12 comments
LLMs are more persuasive than incentivized human persuaders(arxiv.org)109 points by flornt 1 year ago | 87 comments
Comparing Parallel Functional Array Languages: Programming and Performance(arxiv.org)80 points by vok 1 year ago | 15 comments