Denis Kuznetsov

2 accepted papers

2026

GENEB: Why Genomic Models Are Hard to Compare

Daria Ledneva, Mikhail Nuridinov, Denis Kuznetsov

ICML 2026poster

Progress in genomic foundation models is difficult to assess due to fragmented benchmarks, incompatible evaluation protocols, and task-specific reporting. As a result, claims of superiority or generality across models are often not directly comparable. We introduce GENEB, a large-scale diagnostic be…

Cited by 0 Source ↗Scholar ↗

2026

LDARNet: DNA Adaptive Representation Network with Learnable Tokenization for Genomic Modeling

Daria Ledneva, Denis Kuznetsov

ICML 2026poster

Genomic foundation models increasingly adopt large language model architectures, yet almost universally rely on fixed tokenization schemes such as $k$-mers or BPE, which impose arbitrary sequence boundaries and may obscure biologically relevant structure. Although recent work has demonstrated the fe…

Cited by 0 Source ↗Scholar ↗