AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Rethinking Genomic Modeling Through Optical Character Recognition

Hongxin Xiang, Pengsen Ma, Yunkang Cao, Di Yu, Haowen Chen, Xinyu Yang, xiangxiang Zeng

ICML 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Medical vision-language models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace linear probe with lightweight MLP headOpticalDNA · DNALONGBENCH eQTL averageAUROC: 0.852 -> 0.867Improved
OpticalDNA pretraining on top of DeepSeek-OCR backbone (ablation)DeepSeek-OCR · DNALONGBENCH eQTL averageAUROC: +5.37% relativeImproved
OpticalDNA pretraining vs DeepSeek-OCR on Thyroid tissue (ablation)DeepSeek-OCR · eQTL ThyroidAUROC: +16.86%Improved
OpticalDNA pretraining vs DeepSeek-OCR on SNSES tissue (ablation)DeepSeek-OCR · eQTL SNSESAUROC: +14.30%Improved
OpticalDNA DNA-specific pretraining for DNA transcription at full length (HG38) (ablation)DeepSeek-OCR · HG38 transcription, 100% GT prefixExact Match (%): 1.2 -> 79.6Improved
OpticalDNA DNA-specific pretraining for DNA transcription at 10% prefix (HG38) (ablation)DeepSeek-OCR · HG38 transcription, 10% GT prefixExact Match (%): 8.6 -> 97.3Improved
OpticalDNA pretraining for rice transcription at full length (ablation)DeepSeek-OCR · Rice transcription, 100% GT prefixExact Match (%): 1.2 -> 74.9Improved
increase rendering resolution from 512 to 1280 (more tokens per page) (ablation)OpticalDNA · eQTL averageAUROC: 0.849 -> 0.849No clear effect
render DNA as 2D image document instead of 1D sequence at 10,000 tokens (ablation)shared Transformer backbone · eQTL 9 tissuesAUROC: 0.558 -> 0.626Improved
use 2D CNN (TinyNet-E) instead of best 1D CNN (CNN1D-small) (ablation)CNN backbones · eQTL 9 tissuesAUROC: 0.649 -> 0.786Improved
use 2D TinyNet-E instead of 1D CNN family for training time (ablation)CNN backbones · eQTLEpoch time (s): 386.6-636.8 -> 66.9Improved
scale 1D CNN from base to xl (ablation)1D CNN · eQTL 9 tissuesAUROC: 0.643 -> 0.578Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy