← Search

Kirill Vishniakov

4 accepted papers

2026

BioToken and BioFM – Biologically-Informed Tokenization Enables Accurate and Efficient Genomic Foundation Models

ICML 2026poster

Existing genomic foundation models (GFMs) typically treat DNA as raw nucleotide sequences, often overlooking the regulatory context required to interpret genetic variation accurately. We introduce BioToken, a tokenization framework that directly encodes variants and biological annotations into genom…

Cited by 0SourceScholar
2026

Genomic Foundationless Models: Pretraining Does Not Promise Performance

ICLR 2026poster

The success of Large Language Models has inspired the development of Genomic Foundation Models (GFMs) through similar pretraining techniques. However, the relationship between pretraining performance and effectiveness in downstream ge- nomic tasks remains unclear. Additionally, the high computationa…

Cited by 0SourcecodeScholar
2024

ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy

ICML 2024poster

Modern computer vision offers a great variety of models to practitioners, and selecting a model from multiple options for specific applications can be challenging. Conventionally, competing model architectures and training protocols are compared by their classification accuracy on ImageNet. However,…

2024

Initializing Models with Larger Ones

ICLR 2024spotlight

Weight initialization plays an important role in neural network training. Widely used initialization methods are proposed and evaluated for networks that are trained from scratch. However, the growing number of pretrained models now offers new opportunities for tackling this classical problem of wei…