Why can't transformers learn multiplication?(arxiv.org)139 points by PaulHoule 1 year ago | 80 comments
Machine Learning to Computational Plasma Physics Reduced-Order Plasma Modeling(arxiv.org)15 points by sandwichsphinx 2 years ago | 1 comments
Representing web applications as knowledge graphs(arxiv.org)66 points by PaulHoule 2 years ago | 7 comments
ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference(arxiv.org)85 points by PaulHoule 1 year ago | 6 comments
State-space models can learn in-context by gradient descent(arxiv.org)75 points by dsalaj 2 years ago | 17 comments
Universal optimality of Dijkstra via beyond-worst-case heaps(arxiv.org)182 points by foweltschmerz 2 years ago | 43 comments