Qiuyi Li

Carbon-A annotates protein-coding genes across eukaryotic genomes using a large encoder model, achieving high accuracy and enabling the creation of a comprehensive annotation database.

scRep is a foundation model for single-cell representation learning that uses self-distillation in latent space, achieving strong performance without task-specific fine-tuning.

The paper introduces CO_SCPLOWARBONC_SCPLOW, a family of efficient DNA language models that address challenges in genomic sequence modeling by adapting LLM techniques to DNA's unique properties.

This paper introduces improved genomic language models that balance long-range context with single-nucleotide resolution, achieving better performance and efficiency than prior methods.

Generanno is a genomic foundation model optimized for metagenomic annotation, achieving superior accuracy in coding region identification and enabling pseudogene prediction and taxonomic classification without reference databases.