This repo curates research papers on bridging biological sequence language models (genomic & protein language) with natural language models, including representation alignment, transformation, and multimodal fusion techniques.

🌟 If you'd like to add a paper or resource, feel free to submit a pull request or open an issue.

• Table of Content
• Papers
  • The Platonic Representation Hypothesis
  • Multimodal Biological Reasoning Model
• Related Resources
  • Related Surveys
  • Related Repositories
• Acknowledgement

The following logo represents:

paper publisher with paper link

code link

related article link

model link

• (vec2vec) Harnessing the universal geometry of embeddings

  

  • All AI Models Might Be The Same

• The platonic representation hypothesis

  

• BIOREASON: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model

  

This repo is inspired by the Awesome Bio-Foundation Models project.