Bio

I am a ML Research Resident in the Visual GenAI team at Yandex Research, where I work on accelerating diffusion models and improving their generation quality under the supervision of Dmitry Baranchuk and Artem Babenko. At the same time, I am pursuing a Master's degree in Computer Science at HSE University and studying at the Yandex School of Data Analysis.

I am looking for PhD opportunities for 2027.


Previously, I was a Research Intern at the Centre of Deep Learning and Bayesian Methods at HSE University, working on face swapping with diffusion models and GANs, supervised by Aibek Alanov. I received my Bachelor's degree in Applied Mathematics and Computer Science from HSE University.

News

Research Interests

Diffusion Models for Vision and Language (Distillation, Efficient Sampling, Post-Training); LLM Efficiency and Architectures.

Publications

Representation-Space MMD for Diffusion Language Models
Ilya Drobyshevskiy*, Ilia Sudakov*, Maksim Semenov, Denis Kuznedelev, Maksim Ignatov, Pavel Temirchev, Nikita Balagansky, Viacheslav Meshchaninov, Nikita Gushchin, Dmitry Baranchuk
Preprint, 2026
Early version accepted for an oral presentation at the NeurIPS 2026 DiffuLM workshop.
Registers Matter for Pixel-Space Diffusion Transformers
Nikita Starodubcev, Ilia Sudakov*, Ilya Drobyshevskiy*, Artem Babenko, Dmitry Baranchuk
Preprint, 2026
Rethinking Global Text Conditioning in Diffusion Transformers
Nikita Starodubcev, Daniil Pakhomov, Zongze Wu, Ilya Drobyshevskiy, Yuchen Liu, Zhonghao Wang, Yuqian Zhou, Zhe Lin, Dmitry Baranchuk
ICLR 2026
Scale-wise Distillation of Diffusion Models
Nikita Starodubcev, Ilya Drobyshevskiy, Denis Kuznedelev, Artem Babenko, Dmitry Baranchuk
ICLR 2026
* Equal contribution