Record · corpus.blog/posts/01a08c65-d521-7375-9c07-52c067c50db2

Scanned Pixels Beat OCR Text for Medical Document Retrieval

yonigottesman.github.io · published 1 March 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at yonigottesman.github.io Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
Links from this post: 22
Words captured: 2,093

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://huggingface.co/nvidia/nemotron-colembed-vl-8b-v2

huggingface.co

https://huggingface.co/spaces/vidore/vidore-leaderboard

huggingface.co

https://arxiv.org/abs/2407.01449

arxiv.org

https://github.com/yonigottesman/visual-retrieval

github.com

https://physionet.org/content/mimiciii/1.4/

physionet.org

https://arxiv.org/abs/2601.08620

arxiv.org

https://arxiv.org/html/2601.08620v1

arxiv.org

https://github.com/yonigottesman/visual-retrieval/blob/master/generate_queries.py

github.com

https://storage.googleapis.com/visual-retrieval/review_queries.html

storage.googleapis.com

https://github.com/yonigottesman/visual-retrieval/blob/32decb03f8a37e6ac8c6070c8569e417991ba23c/generate_queries.py

github.com

https://github.com/yonigottesman/visual-retrieval/blob/master/create_pdfs.py

github.com

https://vllm.ai/

vllm.ai

https://huggingface.co/deepseek-ai/DeepSeek-OCR

huggingface.co

https://github.com/yonigottesman/visual-retrieval/blob/428d52f840762d76402b97024e16b58d9ed17dc2/batch_ocr.py

github.com

https://github.com/yonigottesman/visual-retrieval/blob/master/cached_deduped.json

github.com

https://huggingface.co/Qwen/Qwen3-VL-Embedding-8B

huggingface.co

https://huggingface.co/Qwen/Qwen3-Embedding-8B

huggingface.co

https://huggingface.co/google/embeddinggemma-300m

huggingface.co

https://github.com/yonigottesman/visual-retrieval/tree/master/generate_embeddings

github.com

https://github.com/yonigottesman/visual-retrieval/blob/32decb03f8a37e6ac8c6070c8569e417991ba23c/generate_embeddings/single_embedding_similarities.py

github.com

https://github.com/yonigottesman/visual-retrieval/blob/32decb03f8a37e6ac8c6070c8569e417991ba23c/generate_embeddings/nemotron_similarities.py

github.com

https://storage.googleapis.com/visual-retrieval/search.html?v=2

storage.googleapis.com