publications

2025

  1. biotoken.png
    BioToken and BioFM - Biologically-Informed Tokenization Enables Accurate and Efficient Genomic Foundation Models
    Aleksey Medvedev, Karthik Viswanathan, Praveenkumar Kanithi, Kirill Vishniakov, Prateek Munjal, Clément Christophe, Marco AF Pimentel, Ronnie Rajan, and Shadab Khan
    bioRxiv, 2025
    bioRxiv Code
  2. arXiv
    Gene42: Long-Range Genomic Foundation Model With Dense Attention
    Kirill Vishniakov, Boulbaba Ben Amor, Engin Tekin, Nancy ElNaker, Karthik Viswanathan, and  others
    arXiv preprint, 2025
    arXiv

2024

  1. gfm.png
    Genomic Foundationless Models: Pretraining Does Not Promise Performance
    Kirill Vishniakov, Karthik Viswanathan, Aleksandr Medvedev, Praveenkumar Kanithi, Marco AF Pimentel, Ronnie Rajan, and Shadab Khan
    bioRxiv, 2024
    bioRxiv Code
  2. beyond-inet.png
    ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy
    Kirill Vishniakov, Zhiqiang Shen, and Zhuang Liu
    In ICML, 2024
    arXiv Code Project Page Twitter
  3. weight_selection.png
    Initializing Models with Larger Ones
    Zhiqiu Xu, Yanjie Chen, Kirill Vishniakov, Yida Yin, Zhiqiang Shen, Trevor Darrell, Lingjie Liu, and Zhuang Liu
    In ICLR, Spotlight Top 5%, 2024
    arXiv Code

2022

  1. mixmask.jpg
    MixMask: Revisiting Masking Strategy for Siamese ConvNets
    Kirill Vishniakov, Eric Xing, and Zhiqiang Shen
    arXiv preprint, 2022
    arXiv
  2. sensorium.jpg
    Retrospective on the SENSORIUM 2022 competition
    Konstantin F Willeke, Paul G Fahey, Mohammad Bashiri, Laura Hansel, Christoph Blessing, Konstantin-Klemens Lurz, Max F Burg, Santiago A Cadena, Zhiwei Ding, Kayla Ponder, and 21 more authors
    In NeurIPS 2022 Competition Track, 2022

2021

  1. imprecise_shap.jpg
    An Imprecise SHAP as a Tool for Explaining the Class Probability Distributions under Limited Training Data
    Lev Utkin, Andrei Konstantinov, and Kirill Vishniakov
    arXiv preprint, 2021
    arXiv