Scholar
Dmitry Baranchuk
Google Scholar ID: NiPmk8oAAAAJ
Yandex Research
Citations & Impact
Citations
2,200
H-index
10
i10-index
10
Publications
20
Co-authors
24
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers, including 'Scale-wise Distillation of Diffusion Models', 'Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis', 'Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps', and more. Organizes seminars, posts paper reviews, and teaches the Visual GenAI course at the Yandex School of Data Analysis.
Research Experience
- Was a research intern at Meta AI in 2022, working on large-scale vector search and retrieval-augmented LLMs, advised by Matthijs Douze and Zeki Yalniz. Interned at ETH Zurich in 2019, working with Vincent Fortuin and Stephan Mandt on generative modeling for missing data imputation.
Education
- Received his Ph.D. in Computer Science from HSE University in December 2024, advised by Artem Babenko.
Background
- Lead Research Scientist at Yandex Research. His work broadly focuses on diffusion-based models and exploring effective synergies between different generative paradigms. He is dedicated to making large-scale visual generative models more efficient and practical. Highly interested in extending the use of generative models to various downstream tasks, such as leveraging them as strong feature extractors or data engines.
