Publications

(*) denotes equal contribution

2026

  1. arXiv
    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, and Dmitry Baranchuk
    Oct 2026
    HTML PDF Code
  2. arXiv
    Registers Matter for Pixel-Space Diffusion Transformers
    Nikita Starodubcev, Ilia Sudakov, Ilya Drobyshevskiy, Artem Babenko, and Dmitry Baranchuk
    May 2026
    HTML PDF Code
  3. ECCV
    Revisiting Autoregressive Models for Generative Image Classification
    Ilia Sudakov, Artem Babenko, and Dmitry Baranchuk
    In European Conference on Computer Vision (ECCV), Sep 2026
    HTML PDF Code
  4. CVPR Findings
    MADrive: Memory-Augmented Driving Scene Modeling
    Polina Karpikova, Daniil Selikhanovych, Kirill Struminsky, Ruslan Musaev, Maria Golitsyna, and Dmitry Baranchuk
    In Computer Vision and Pattern Recognition (CVPR), Jun 2026
    HTML PDF Dataset Website
  5. ICLR
    Rethinking Global Text Conditioning in Diffusion Transformers
    Nikita Starodubcev, Daniil Pakhomov, Zongze Wu, Ilya Drobyshevskiy, Yuchen Liu, Zhonghao Wang, Yuqian Zhou, Zhe Lin, and Dmitry Baranchuk
    In International Conference on Learning Representations, Feb 2026
    HTML PDF Code
  6. ICLR
    Scale-wise Distillation of Diffusion Models
    Nikita Starodubcev, Ilya Drobyshevskiy, Denis Kuznedelev, Artem Babenko, and Dmitry Baranchuk
    In International Conference on Learning Representations, Feb 2026
    HTML PDF Code Website
  7. ICML
    Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization
    Mikhail Persiianov, Arip Asadulaev, Nikita Andreev, Nikita Starodubcev, Dmitry Baranchuk, Anastasis Kratsios, Evgeny Burnaev, and Alexander Korotin
    In International Conference on Machine Learning, Jul 2026
    HTML PDF Code

2025

  1. NeurIPS
    Alchemist: Turning Public Text-to-Image Data into Generative Gold
    Valerii Startsev, Alexander Ustyuzhanin, Alexey Kirillov, Dmitry Baranchuk, and Sergey Kastryulin
    In Neural Information Processing Systems, Dec 2025
    HTML PDF Dataset
  2. ICML
    Inverse Bridge Matching Distillation
    Nikita Gushchin, David Li, Daniil Selikhanovych, Evgeny Burnaev, Dmitry Baranchuk, and Alexander Korotin
    In International Conference on Machine Learning, Jul 2025
    HTML PDF Code
  3. CVPR
    Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis
    Anton Voronov, Denis Kuznedelev, Mikhail Khoroshikh, Valentin Khrulkov, and Dmitry Baranchuk
    In Computer Vision and Pattern Recognition (CVPR), Jun 2025
    HTML PDF Code Website
  4. NeurIPS
    Results of the Big ANN: NeurIPS’23 competition
    Harsha Vardhan Simhadri, Martin Aumüller, Amir Ingber, Matthijs Douze, George Williams, Magdalen Dobson Manohar, Dmitry Baranchuk, Edo Liberty, Frank Liu, Ben Landrum, Mazin Karjikar, Laxman Dhulipala, Meng Chen, Yue Chen, Rui Ma, Kai Zhang, Yuzheng Cai, Jiayang Shi, Yizhuo Chen, Weiguo Zheng, Zihao Wan, Jie Yin, and Ben Huang
    In Neural Information Processing Systems, Dec 2025
    HTML PDF Code

2024

  1. NeurIPS
    Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps
    Nikita Starodubcev, Mikhail Khoroshikh, Artem Babenko, and Dmitry Baranchuk
    In Neural Information Processing Systems, Dec 2024
    HTML PDF Code Website
  2. arXiv
    Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization
    Vage Egiazarian*, Denis Kuznedelev*, Anton Voronov*, Ruslan Svirschevski, Michael Goin, Daniil Pavlov, Dan Alistarh, and Dmitry Baranchuk
    Sep 2024
    HTML PDF Code Website
  3. CVPR
    Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models
    Nikita Starodubcev, Artem Fedorov, Artem Babenko, and Dmitry Baranchuk
    In Computer Vision and Pattern Recognition (CVPR), Jun 2024
    HTML PDF Code

2023

  1. ICCV
    DeDrift: Robust Similarity Search under Content Drift
    Dmitry Baranchuk, Matthijs Douze, Yash Upadhyay, and I. Zeki Yalniz
    In International Conference on Computer Vision (ICCV), Oct 2023
    HTML PDF
  2. ICML
    TabDDPM: Modelling Tabular Data with Diffusion Models
    Akim Kotelnikov, Dmitry Baranchuk, Ivan Rubachev, and Artem Babenko
    In International Conference on Machine Learning, Jul 2023
    HTML PDF Code
  3. NeurIPS
    Distributed Inference and Fine-tuning of Large Language Models Over The Internet
    Alexander Borzunov, Max Ryabinin, Artem Chumachenko, Dmitry Baranchuk, Tim Dettmers, Younes Belkada, Pavel Samygin, and Colin A Raffel
    In Neural Information Processing Systems, Dec 2023
    HTML PDF Code Website
  4. ACL Demo
    Petals: Collaborative Inference and Fine-tuning of Large Models
    Alexander Borzunov*, Dmitry Baranchuk*, Tim Dettmers*, Max Ryabinin*, Younes Belkada*, Artem Chumachenko, Pavel Samygin, and Colin Raffel
    In Association for Computational Linguistics (System Demonstrations), Jul 2023
    HTML PDF Code Website
  5. arXiv
    Towards Real-time Text-driven Image Manipulation with Unconditional Diffusion Models
    Nikita Starodubcev, Dmitry Baranchuk, Valentin Khrulkov, and Artem Babenko
    arXiv preprint arXiv:2304.04344, Apr 2023
    HTML PDF

2022

  1. ICLR
    Label-Efficient Semantic Segmentation with Diffusion Models
    Dmitry Baranchuk, Andrey Voynov, Ivan Rubachev, Valentin Khrulkov, and Artem Babenko
    In International Conference on Learning Representations, May 2022
    HTML PDF Code Website
  2. NeurIPS Competition
    Results of the NeurIPS’21 Challenge on Billion-Scale Approximate Nearest Neighbor Search
    Harsha Vardhan Simhadri, George Williams, Martin Aumüller, Matthijs Douze, Artem Babenko, Dmitry Baranchuk, Qi Chen, Lucas Hosseini, Ravishankar Krishnaswamny, Gopal Srinivasa, Suhas Jayaram Subramanya, and Jingdong Wang
    In NeurIPS 2021 Competitions and Demonstrations Track, Dec 2022
    HTML PDF Code
  3. ICLR
    Graph-based Nearest Neighbor Search in Hyperbolic Spaces
    Liudmila Prokhorenkova, Dmitry Baranchuk, Nikolay Bogachev, Yury Demidovich, and Alexander Kolpakov
    In International Conference on Learning Representations, May 2022
    HTML PDF

2021

  1. INNF@ICML
    Distilling the Knowledge from Conditional Normalizing Flows
    Dmitry Baranchuk, Vladimir Aliev, and Artem Babenko
    In ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, Jul 2021
    HTML PDF Code
  2. AutoML@ICML
    Discovering Weight Initializers with Meta Learning
    Dmitry Baranchuk, and Artem Babenko
    In ICML Workshop on Automated Machine Learning (AutoML), Jul 2021
    HTML PDF Code

2020

  1. AISTATS
    GP-VAE: Deep Probabilistic Time Series Imputation
    Vincent Fortuin*, Dmitry Baranchuk*, Gunnar Raetsch, and Stephan Mandt
    In International Conference on Artificial Intelligence and Statistics, Aug 2020
    HTML PDF Code

2019

  1. ICML
    Learning to Route in Similarity Graphs
    Dmitry Baranchuk, Dmitry Persiyanov, Anton Sinitsin, and Artem Babenko
    In International Conference on Machine Learning, Jun 2019
    HTML PDF Code
  2. arXiv
    Towards Similarity Graphs Constructed by Deep Reinforcement Learning
    Dmitry Baranchuk, and Artem Babenko
    Nov 2019
    HTML PDF Code

2018

  1. ECCV
    Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors
    Dmitry Baranchuk, Artem Babenko, and Yury Malkov
    In European Conference on Computer Vision (ECCV), Sep 2018
    HTML PDF Code