Rendering DNA as OCR-style page images and training a vision-language model on reading/grounding/retrieval/completion tasks outperforms sequence-based genomic models on tested benchmarks with ~20x fewer effective tokens.
Dnalongbench: a benchmark suite for long-range dna prediction tasks
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Rethinking Genomic Modeling Through Optical Character Recognition
Rendering DNA as OCR-style page images and training a vision-language model on reading/grounding/retrieval/completion tasks outperforms sequence-based genomic models on tested benchmarks with ~20x fewer effective tokens.