Alignment or Integration? Rethinking Multimodal Fusion in DNA-language Foundation Models

Abstract

Fusing DNA foundation models with large language models (LLMs) for DNA-language reasoning raises a fundamental question: at what level should genomic sequences and natural language interact? Most existing approaches encode DNA sequences and text separately and rely on embedding-level alignment to connect the two modalities. Such late-stage fusion compresses rich genomic sequences into fixed representations, limiting the model's ability to reason over fine-grained, token-level genomic structure. In this work, we propose two new methods for DNA-language fusion, i.e., a semantic alignment method SeqCLIP and a vocabulary-level integration method OneVocab. SeqCLIP strengthens embedding-level alignment via sequence-level contrastive pre-training, and OneVocab directly integrates genomic $k$-mers into the language model's existing vocabulary. Comprehensive experiments on classification and reasoning tasks show that, while various alignment strategies improve embedding-level fusion, early vocabulary-level integration yields more expressive and effective representations for DNA-language modeling.