Inocras and KAIST Introduce DNAChunker, a Learnable Tokenization Model for DNA Language Models
Model matches the accuracy of leading 1.2 billion-parameter DNA language models while using only 172 million parameters SAN DIEGO and SEOUL, South Korea, June 22, 2026 — Inocras, a bioinformatics-led company […] The post Inocras and KAIST Introduce DNAChunker, a Learnable Tokenization Model for DNA Language Models appeared first on AIwire.