Rethinking Genomic Modeling Through Optical Character Recognition
Abstract
Recent genomic foundation models largely adopt large language model architectures that treat DNA as a one-dimensional token sequence. However, exhaustive sequential reading is structurally misaligned with sparse and discontinuous genomic semantics, leading to wasted computation on low-information background and preventing understanding-driven compression for long contexts. Here, we present OpticalDNA, a vision-based framework that reframes genomic modeling as Optical Character Recognition (OCR)-style document understanding. OpticalDNA renders DNA into structured visual layouts and trains an OCR-capable vision--language model with a \emph{visual DNA encoder} and a \emph{document decoder}, where the encoder produces compact, reconstructible visual tokens for high-fidelity compression. Building on this representation, OpticalDNA defines prompt-conditioned objectives over core genomic primitives-reading, region grounding, subsequence retrieval, and masked span completion-thereby learning layout-aware DNA representations that retain fine-grained genomic information under a reduced effective token budget. Across diverse genomic benchmarks, OpticalDNA consistently outperforms recent baselines; on sequences up to 450k bases, it achieves the best overall performance with nearly fewer effective tokens, and surpasses models with up to more activated parameters while tuning only 256k \emph{trainable} parameters.
Cite
@article{arxiv.2602.02014,
title = {Rethinking Genomic Modeling Through Optical Character Recognition},
author = {Hongxin Xiang and Pengsen Ma and Yunkang Cao and Di Yu and Haowen Chen and Xinyu Yang and Xiangxiang Zeng},
journal= {arXiv preprint arXiv:2602.02014},
year = {2026}
}