Wang Y, Wang J, Zhu J, Zhai F, Zhu H, Dai Z, et al. Compression-Based Tokenization Improves Language Modeling of Hierarchical Genomic Structure [Internet]. LangTaoSha Preprint Server. 2025 [cited 2025 Dec. 20]. Available from: https://langtaosha.org.cn/index.php/lts/preprint/view/51