#machine learning
Apr 2026
EvoLen: Evolution-Guided Tokenization for DNA Language Model
EvoLen is a tokenizer that combines evolutionary stratification with length-aware decoding to better preserve motif-scale functional sequence units and demonstrates that tokenization introduces a critical inductive bias and that incorporating evolutionary information yields more biologically meaningful and interpretable sequence representations.
Nan Huang, Xiaoxiao Zhou, Junxia Cui et al.
· arXiv.org · 0 citations