GenomicsbioRxivPreprint
BioToken and BioFM - Biologically-Informed Tokenization Enables Accurate and Efficient Genomic Foundation Models
Александр Владимирович Медведев, Karthik Viswanathan, Praveenkumar Kanithi…·Shadab Khan
This paper introduces BioToken and BioFM, biologically-informed genomic models that improve performance and efficiency in genomic tasks by incorporating biological context into tokenization.
3 citations