Optical context compression is just (bad) autoencoding (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Optical context compression is just (bad) autoencoding

First screen, captured 10 months ago.

Looks similar

Screenshot of arxiv.org: Benchmarking vision-language models on OCR in dynamic video environments

Benchmarking vision-language models on OCR in dynamic video environments (arxiv.org)

135 points by ashu_trv 1 year ago | 57 comments

Screenshot of arxiv.org: LoMA: Lossless Compressed Memory Attention

LoMA: Lossless Compressed Memory Attention (arxiv.org)

90 points by PaulHoule 2 years ago | 8 comments

Screenshot of arxiv.org: Google Predicts the Flu Again

Google Predicts the Flu Again (arxiv.org)

7 points by tgoog 2 years ago | 6 comments

Screenshot of arxiv.org: SmolDocling: An ultra-compact VLM for end-to-end multi-modal document conversion

SmolDocling: An ultra-compact VLM for end-to-end multi-modal document conversion (arxiv.org)

48 points by prats226 1 year ago | 8 comments

Screenshot of arxiv.org: Meissonic, High-Resolution Text-to-Image Synthesis on consumer graphics cards

Meissonic, High-Resolution Text-to-Image Synthesis on consumer graphics cards (arxiv.org)

51 points by jinqueeny 2 years ago | 3 comments

Screenshot of arxiv.org: PaLI-3 Vision Language Models

PaLI-3 Vision Language Models (arxiv.org)

158 points by maccaw 3 years ago | 22 comments