cv
Research Interests
- I am a PhD candidate in AI at Queen Mary University of London. My research focuses on understanding intermediate representations in foundation models and developing methods to analyse and steer model behaviour. I am particularly interested in representation learning, interpretability, and control of generative systems. I have a strong background in machine learning and mathematics, along with prior research experience in industry.
Education
-
2022 — presentPh.D. , Queen Mary University of London
London, UK. DeepMind studentship. Supervised by Prof. Greg Slabaugh and Dr. Martin Benning.
-
2017 — 2019M.Sc. , Moscow Institute of Physics and Technology
Moscow, Russian Federation. Specialized in machine learning and data analysis.
GPA 7.1/10
Thesis title: Use of Domain Adaptation to expand the scope of Generative Models
-
2013 — 2017B.Sc. , Moscow Institute of Physics and Technology
Moscow, Russian Federation. Specialized in mathematics and machine learning.
GPA 8.4/10, magna cum laude
Thesis title: Multi-Objective Deep Reinforcement Learning in Seq2Seq Machine Translation
Experience
-
2024 — 2025Research Intern , Huawei Noah's Ark, London, UK
Researched intermediate representations in vision-language generative models and developed methods for steering generation and image-processing behaviour. First-authored three papers during the internship, including one accepted to ICLR 2026.
-
2021 — 2022Data & AI Scientist , Philips Innovation Labs, Moscow, Russia
Developed novel AI-based techniques for Philips medical-device software. Founded and led a research reading group focused on recent advances in AI for medicine.
-
2020 — 2021Researcher , Huawei Russian Research Institute, Moscow, Russia
Led research on AI-based face recognition, improving overall pipeline performance by 2.5%. Coordinated a Huawei–MIPT collaboration on domain adaptation methods for face recognition, including research review and project communication.
-
2018 — 2020Research Assistant , LAMBDA lab, Moscow, Russia
Conducted research on generative models for high-energy physics. Designed and implemented an original pipeline for synthetic particle-event generation. Co-authored two scientific papers, including one published in an ICLR workshop.
-
2017Research Intern , Yandex, Moscow, Russia
Applied reinforcement learning to optimize metrics for a seq2seq vocalization task. Combined multiple seq2seq models using ideas from the Actor-Mimic algorithm and showed that RL improved model quality. This work formed part of my bachelor's thesis.
Selected Publications
-
2026
Georgii Aparin, Tatiana Gaintseva. A Geometric Account of Activation Steering through Angle-Norm Decomposition. arxiv preprint. [paper]
Additional Training
-
2026ARENA 8.0 , London, UK
AI safety research engineering programme focused on mechanistic interpretability, model evaluations, reinforcement learning, and alignment-relevant ML engineering.
-
2025LogML Summer School , London, UK
Contributed to the research project "Representational Alignment for Universal Spaces", which won the Best Project Award at LogML 2025. The resulting work was accepted to the ICLR Re4-Align 2026 workshop.
-
2016 — 2018Master's level program , Yandex School of Data Analysis
Moscow, Russian Federation. Completed coursework in machine learning, deep learning, applied statistics, and big data.
Selected Teaching
-
2024 — presentLecturer and curriculum designer , Nebius Academy, London
Preparing and delivering lectures, practical sessions, and homework assignments on LLM fundamentals.
-
2022 — 2023Lecturer and curriculum designer , Deep Learning Course, Moscow State University
Designed a structure for an "Introduction to Deep Learning" course. Prepared and delivered lectures, practical sessions, and homework assignments.
-
2019 — 2022Teaching Assistant , Yandex School of Data Analysis (YSDA)
Led seminars, prepared and reviewed students' homework of deep learning classes.
-
2017 — 2022Lecturer and curriculum designer , Deep Learning School (DLS), Moscow Institute of Physics and Technology
Co-founder, lead curriculum designer and lecturer. Designed curricula for courses on AI fundamentals. Prepared and delivered lectures, practical sessions, and homework assignments.
Competitions and Awards
-
2017
Skills
-
Programming
- Python, PyTorch, NumPy, pandas, scikit-learn, Git
-
Machine Learning
- Deep learning, transformers, large language models, diffusion models, generative models, reinforcement learning, representation learning
-
Technical Focus
- Interpretability, analysis of intermediate representations, steering and control of foundation models, AI safety
-
Mathematical Background
- Linear algebra, probability theory, differential geometry, statistics, optimization