PhD candidate in generative AI
Hello, I'm a PhD student in computer science at Constructor University, Bremen, where my research is focused on generative and diffusion models for discrete data such as proteins and text. I completed my Bachelor's and Master's degrees in computer science at Lomonosov Moscow State University in 2024. Here, I share my professional notes and personal insights from my ongoing research. My hope is that they will be a valuable resource for other researchers and enthusiasts in the field.
LDLM jointly trains the encoder, diffusion model, and decoder with a simple four-part recipe, achieving stronger text generation at 2–13× faster sampling than prior diffusion LMs.
RLD adapts latent diffusion to antibody design by learning redistributed latent spaces, enabling high-quality conditional generation across organisms and chain types.
By smoothing the diffusion process on token embeddings, this technique helps generate more coherent and natural-sounding text, leading to better user experiences in conversational AI.
This work offers a highly efficient one-step generation process, significantly reducing the computational cost and time required for solving image-to-image translation problems.
The method provides guided and efficient remasking for masked language models that drastically enhances quality and speed of text and code generation.
This benchmark provides crucial tools for developing and evaluating protein generation models, leading to advances in drug design and biological engineering.
COSMOS enables high-quality and over 2× faster text generation by performing diffusion entirely within a highly compressed, semantically smooth latent space.
This approach uses established language model encoding techniques to generate new protein sequences, accelerating the discovery of novel functional proteins for biotechnology and therapeutics.
In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025
By shedding light on how diffusion models operate within the semantic space of text embeddings, this research improves the theoretical foundation and practical performance of text generation models.
AIR refines discrete-diffusion antibody humanization at inference time, steering sequences toward higher humanness while preserving binding-relevant properties without retraining.
2025–2029 (expected)
Advised by Professor Dmitry Vetrov.
Constructor University Bremen, Germany
2022–2024
Moscow State University
2020–2022
Yandex School of Data Analysis, Moscow
2018–2022
Moscow State University
2022–2026
Investigated diffusion probabilistic models for text generation in natural-language and de novo protein design. Trained diffusion language models (up to 7B parameters) using configurations up to 32 GPUs. Results published in four accepted A*-ranked conference papers.
2021–2022
Created a self-supervised detector that flags AI-upscaled videos via contrastive learning.
2021
Built an internal diagnostic tool that scans Alice voice-assistant logs to surface conversational ambiguities and other dialog-routing errors, giving engineers a fast, searchable queue of issues to fix.
2020
Developed a benchmarking toolkit that analyzes and compares full-reference, neural-network video-quality metrics.