A compact hybrid GDN+attention model distilled from Nucleotide Transformer v2 outperforms similarly sized models and, on several tasks, its 500x larger teacher.
A sequence-based global map of regulatory activity for deciphering human genetics.Nature genetics, 54(7):940–949, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence Modeling
A compact hybrid GDN+attention model distilled from Nucleotide Transformer v2 outperforms similarly sized models and, on several tasks, its 500x larger teacher.