State-space models can learn in-context by gradient descent (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: State-space models can learn in-context by gradient descent

First screen, captured 2 years ago.

Looks similar

Screenshot of arxiv.org: Representing web applications as knowledge graphs

Representing web applications as knowledge graphs (arxiv.org)

66 points by PaulHoule 2 years ago | 7 comments

Screenshot of arxiv.org: Machine Learning to Computational Plasma Physics Reduced-Order Plasma Modeling

Machine Learning to Computational Plasma Physics Reduced-Order Plasma Modeling (arxiv.org)

15 points by sandwichsphinx 2 years ago | 1 comments

Screenshot of arxiv.org: Numerical Precision Affects Mathematical Reasoning Capabilities of LLMs

Numerical Precision Affects Mathematical Reasoning Capabilities of LLMs (arxiv.org)

55 points by belter 2 years ago | 39 comments

Screenshot of arxiv.org: ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference

ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference (arxiv.org)

85 points by PaulHoule 1 year ago | 6 comments

Screenshot of arxiv.org: Universal optimality of Dijkstra via beyond-worst-case heaps

Universal optimality of Dijkstra via beyond-worst-case heaps (arxiv.org)

182 points by foweltschmerz 2 years ago | 43 comments

Screenshot of arxiv.org: Antislop: A framework for eliminating repetitive patterns in language models

Antislop: A framework for eliminating repetitive patterns in language models (arxiv.org)

108 points by Der_Einzige 1 year ago | 101 comments