Harshvardhan Sharma

Comparative Benchmarking of Probabilistic, Recurrent, and Self-Attention Models for Autoregressive Genomic Sequence Modeling

Transformer-based language models have achieved remarkable success in natural language processing, and their structural parallels with DNA sequences, both being linear strings over a finite alphabet, motivate their application to genomics. Although discriminative genomic language models such as DNABERT have been expl...