research lab

YerevaNN /jɛɾɛvɑnˈɛn/ is a non-profit computer science and mathematics research lab based in Yerevan, Armenia.


  • Machine learning algorithms
    • Characterization of the failure modes of domain generalization algorithms [preprint], accepted at CVPR'22 (with USC ISI).
    • WARP: a parameter-efficient method for transfer learning in NLP. Published in ACL'21 (with USC ISI)
    • Theoretical analysis of the detection of the feature matching map in presence of outliers [preprint] (with ENSAE-CREST)
    • Robust classification under class-dependent domain shift [preprint] (with USC ISI). Presented at ICML 2020 UDL Workshop
    • A novel robust estimator of the mean of a multivariate Gaussian distribution. Published in Annals of Statistics. (with ENSAE-CREST)
    • T-Corex: a novel method for temporal covariance estimation using information theoretic apparatus [preprint] [code] (with USC ISI)
  • Machine learning for biomedical data
  • Development of Armenian treebanks
    • Eastern Armenian treebank as part of the Universal Dependencies project [data (52K tokens)] [website] [code]
    • An end-to-end syntax parser for Armenian [code] [demo]
    • Collaboration with Marat Yavrumyan and Anna Danielyan from Yerevan State University. Partially funded by ANSEF and ISTC.
  • Student projects
Visit our blog and GitHub for more.


Hrant Khachatrian / Github / Google Scholar
Karen Hambardzumyan / Github / Google Scholar
Tigran Galstyan / Github / Google Scholar
Ani Vanyan / Github
Hovhannes Tamoyan / Github
Khazhak Galstyan / Github
Ani Tevosyan / Github
Knarik Mheryan / Github
Gayane Chilingaryan / Github
Arto Maranjyan / Google Scholar
Past members: Hrayr Harutyunyan, Gor Arakelyan, Martin Mirakyan, Ashot Matevosyan, Arshak Minasyan YerevaNN is hiring! The easiest way to join YerevaNN is to start working on one of the projects listed on MLEVN Project Ideas Page. Our guide to deep learning might be useful (last updated in December, 2016)

The handwritten digits in the background are generated by deep convolutional generative adversarial networks [paper] [code]