I’m a Machine Learning Researcher passionate about solving problems at the intersection of statistical learning, computer vision and optimization. Currently I spend my time as a PostDoc in L2S Centralesupélec University, developing theoretical foundations for various ML solutions. I completed my Ph.D. degree in Computer Science from the Institute for Informatics and Automation Problems of NAS RA with the specialization “Statistical and Computational Complexity of the Feature Matching Map Detection Problem”. My research journey started with competitive programming (Bronze Medal at IOI 2014) and evolved through collaborations with Google’s teams in NYC, Zurich, and Munich, where I worked on everything from YouTube’s captioning system to robotics projects. My work has been published at venues like ICML, AISTATS, and CVPR.

Publications

Conference Papers

1. Teaching Visual Language Models to Navigate using Maps
   Nurijanyan, N., Tamazyan, H., Galstyan, T. (2025)
   7th Robot Learning Workshop: Towards Robots with Human-Level Abilities

2. Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution
   Vardanyan, E., Minasyan, A., Hunanyan, S., Galstyan, T., Dalalyan, A. (2023)
   Proceedings of the 41st International Conference on Machine Learning, PMLR, 235, 49203-49225

3. Matching Map Recovery with an Unknown Number of Outliers
   Minasyan, A., Galstyan, T., Hunanyan, S., Dalalyan, A. (2023)
   International Conference on Artificial Intelligence and Statistics, 891-906
   Publisher: PMLR

4. Failure modes of domain generalization algorithms
   Galstyan, T., Harutyunyan, H., Khachatrian, H., Steeg, G.V., Galstyan, A. (2022)
   Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 19077-19086

5. BioRelEx 1.0: Biological relation extraction benchmark
   Khachatrian, H., Nersisyan, L., Hambardzumyan, K., Galstyan, T., Hakobyan, A., Arakelyan, A., Rzhetsky, A., Galstyan, A. (2019)
   Proceedings of the 18th bionlp workshop and shared task, 176-190

Journal Articles

1. Optimality of the Least Sum of Logarithms in the Problem of Matching Map Recovery in the Presence of Noise and Outliers
   Galstyan, T., Minasyan, A. (2023)
   Armenian Journal of Mathematics, 15(5), 1-9

2. Comparison of data matching methods on biomedical datasets
   Galstyan, T. (2022)
   Vestnik of Russian-Armenian University, 1(2), 46-58

3. Optimal detection of the feature matching map in presence of noise and outliers
   Galstyan, T., Minasyan, A., Dalalyan, A.S. (2022)
   Electronic Journal of Statistics, 16(2), 5720-5750

4. On random weighted sum of positive semi-definite matrices
   Galstyan, T.V., Minasyan, G. (2020)
   Proceedings of Yerevan State University, Physical and Mathematical Sciences, 54(2), 96-100

5. On the Tradeoff Between Accuracy and Fairness in Representation Learning
   Galstyan, T., Khachatrian, H. (2020)
   Vestnik of Russian-Armenian University, 1, 35-46

Preprints

1. Robust classification under class-dependent domain shift
   Galstyan, T., Khachatrian, H., Steeg, G.V., Galstyan, A. (2020)
   arXiv preprint arXiv:2007.05335
   arXiv