Tigran Galstyan
Tigran Galstyan
π PhD Candidate in Computer Science | π§ Machine Learning Researcher
π 3/11 Avan-Ariuj, Yerevan, Armenia 0022
π± +374 (91) 00-45-49 | π§ galstyantik@gmail.com
π LinkedIn | GitHub | Google Scholar
π Education
PhD in Computer Science
Institute for Informatics and Automation Problems of NAS RA
π
2020β2024 | Adviser: A. S. Dalalyan
π Thesis: βStatistical and Computational Complexity of the Feature Matching Map Detection Problemβ
Master of Science in Discrete Mathematics & Theoretical Informatics
Bachelor of Science in Computer Science & Applied Mathematics
Yerevan State University
π
2014β2020 | π
GPA: 19/20 (Both Degrees)
Physical and Mathematical Specialized School
π
Graduated 2014 | π₯ Valedictorian (Top of 140 students) | GPA: 9/10
πΌ Professional Experience
YerevanN Research Lab
π§ Machine Learning Researcher | π July 2016 β Present
π Yerevan, Armenia
- Led Aerial Vision-and-Language Navigation for UAVs using multimodal models (LLaVA, Chameleon)
Developed statistical methods for feature matching map recovery (Paper Code) - Pioneered work on domain generalization failures (Code)
- Built BioreIEx biological relation extraction system (ACL Paper)
- Created LSTM-based transliteration models (Blog)
American University of Armenia
π¨π« Adjunct Professor | π SepβDec 2021
- Taught DS115 Data Structures/Algorithms to 130 students
- Adapted Stanfordβs CS 161 curriculum for Python-based competitive programming
π Google Internships
X, the Moonshot Factory
π€ Software Engineering Intern | π JunβAug 2019 | π©πͺ Munich
- Bridged simulation-to-reality gaps for The Everyday Robot project
Google NYC
πΉ Software Engineering Intern | π AugβOct 2018 | πΊπΈ New York
- Improved YouTube captioning with contextual biassing
- Designed named entity transcription evaluation metrics
Google Switzerland
βοΈ Research Intern | π JulβSep 2017 | π¨π Zurich
- Enhanced handwriting recognition via adversarial training
π Publications
- Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution
Vardanyan E., Hunanyan S., Galstyan T., et al. (2024). ICML - Matching Map Recovery with an Unknown Number of Outliers
Minasyan A., Galstyan T., et al. (2023). AISTATS - Failure Modes of Domain Generalization Algorithms
Galstyan T., Harutyunyan H., et al. (2022). CVPR - Biorelex 1.0: Biological Relation Extraction Benchmark
Khachatrian H., Galstyan T., et al. (2019). ACL BioNLP Workshop
(10+ total publications in ICML, CVPR, EJS, and more)
π Honors & Awards
- π₯ Bronze Medal, International Olympiad in Informatics (IOI 2014)
- π₯ Bronze Medal, Zhautikov Olympiad in Informatics (2014)
- π Finalist, Google Hashcode (2017, 2018)
π Skills
| Category | Details | |βββββββ|βββββββββββββββββ| | Programming | Python (NumPy, PyTorch), LLMs, Neural Networks | | Machine Learning| Domain Generalization, Vision-Language Models | | Languages | Armenian (Native), English, Russian (Fluent) |
π References
- Arnak Dalalyan
Director at CREST, France | PhD Co-Advisor - Aram Galstyan
Distinguished Principal Scientist, USC ISI | Research Mentor