Speed Is All You Need: On-Device Acceleration of Large Diffusion Models (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Speed Is All You Need: On-Device Acceleration of Large Diffusion Models

First screen, captured 3 years ago.

Looks similar

Screenshot of arxiv.org: Addition Is All You Need for Energy-Efficient Language Models

Addition Is All You Need for Energy-Efficient Language Models (arxiv.org)

298 points by InvisibleUp 2 years ago | 110 comments

Screenshot of arxiv.org: Large Language Models as Optimizers. +50% on Big Bench Hard

Large Language Models as Optimizers. +50% on Big Bench Hard (arxiv.org)

89 points by og_kalu 3 years ago | 32 comments

Screenshot of arxiv.org: Magicoder: Source Code Is All You Need

Magicoder: Source Code Is All You Need (arxiv.org)

161 points by tosh 2 years ago | 58 comments

Screenshot of arxiv.org: Neural Network Diffusion

Neural Network Diffusion (arxiv.org)

199 points by vagabund 2 years ago | 74 comments

Screenshot of arxiv.org: Copy is all you need

Copy is all you need (arxiv.org)

116 points by mottiden 3 years ago | 70 comments

Screenshot of arxiv.org: Fast KV Compaction via Attention Matching

Fast KV Compaction via Attention Matching (arxiv.org)

59 points by cbracketdash 8 months ago | 14 comments