AIConfPaper
← Search

Dmitry Baranchuk

16 accepted papers

2026

Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization

Mikhail Persiianov, Arip Asadulaev, Nikita Andreev, Nikita Starodubcev, Dmitry Baranchuk, Anastasis Kratsios +2
ICML 2026poster

Learning conditional distributions $\pi^\star(\cdot|x)$ is a central problem in machine learning, which is typically approached via supervised methods with paired data $(x,y) \sim \pi^\star$. However, acquiring paired data samples is often challenging, especially in problems such as domain translati…

Cited by 0Source ↗Scholar ↗
2026

Revisiting Global Text Conditioning in Diffusion Transformers

Nikita Starodubcev, Daniil Pakhomov, Zongze Wu, Ilya Drobyshevskiy, Yuchen Liu, Zhonghao Wang +3
ICLR 2026poster

Diffusion transformers typically incorporate textual information via (i) attention layers and (ii) a modulation mechanism using a pooled text embedding. Nevertheless, recent approaches discard modulation-based text conditioning and rely exclusively on attention. In this paper, we address whether mod…

Cited by 0Source ↗code ↗Scholar ↗
2026

Scale-wise Distillation of Diffusion Models

Nikita Starodubcev, Ilya Drobyshevskiy, Denis Kuznedelev, Artem Babenko, Dmitry Baranchuk
ICLR 2026poster

Recent diffusion distillation methods have achieved remarkable progress, enabling high-quality ${\sim}4$-step sampling for large-scale text-conditional image and video diffusion models (DMs). However, further reducing the number of sampling steps becomes more and more challenging, suggesting that e…

Cited by 0Source ↗code ↗Scholar ↗
2025

Alchemist: Turning Public Text-to-Image Data into Generative Gold

Valerii Startsev, Alexander Ustyuzhanin, Alexey Kirillov, Dmitry Baranchuk, Sergey Kastryulin
NeurIPS 2025poster

Pre-training equips text-to-image (T2I) models with broad world knowledge, but this alone is often insufficient to achieve high aesthetic quality and alignment. Consequently, supervised fine-tuning (SFT) is crucial for further refinement. However, its effectiveness highly depends on the quality of…

Cited by 0Source ↗Scholar ↗
2025

Inverse Bridge Matching Distillation

Nikita Gushchin, David Li, Daniil Selikhanovych, Evgeny Burnaev, Dmitry Baranchuk, Alexander Korotin
ICML 2025poster

Learning diffusion bridge models is easy; making them fast and practical is an art. Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. However, like many modern diffusion and flow models, DBMs suffer from the problem of slow i…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Results of the Big ANN: NeurIPS’23 competition

Harsha Vardhan simhadri, Martin Aumüller, Matthijs Douze, Dmitry Baranchuk, Amir Ingber, Edo Liberty +15
NeurIPS 2025poster

The 2023 Big ANN Challenge, held at NeurIPS 2023, focused on advancing the state-of-the-art in indexing data structures and search algorithms for practical variants of Approximate Nearest Neighbor (ANN) search that reflect its the growing complexity and diversity of workloads. Unlike prior challenge…

Cited by 0Source ↗code ↗Scholar ↗
2024

Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps

Nikita Starodubcev, Mikhail Khoroshikh, Artem Babenko, Dmitry Baranchuk
NeurIPS 2024poster

Diffusion distillation represents a highly promising direction for achieving faithful text-to-image generation in a few sampling steps. However, despite recent successes, existing distilled models still do not provide the full spectrum of diffusion abilities, such as real image inversion, which enab…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models

Nikita Starodubcev, Dmitry Baranchuk, Artem Fedorov, Artem Babenko
CVPR 2024poster

Knowledge distillation methods have recently shown to be a promising direction to speedup the synthesis of large-scale diffusion models by requiring only a few inference steps. While several powerful distillation methods were recently proposed the overall quality of student samples is typically lowe…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2023

Distributed Inference and Fine-tuning of Large Language Models Over The Internet

Alexander Borzunov, Max Ryabinin, Artem Chumachenko, Dmitry Baranchuk, Tim Dettmers, Younes Belkada +2
NeurIPS 2023poster

Large language models (LLMs) are useful in many NLP tasks and become more capable with size, with the best open-source models having over 50 billion parameters. However, using these 50B+ models requires high-end hardware, making them inaccessible to most researchers. In this work, we investigate met…

Cited by 56Source ↗PDF ↗Scholar ↗
2023

TabDDPM: Modelling Tabular Data with Diffusion Models

Akim Kotelnikov, Dmitry Baranchuk, Ivan Rubachev, Artem Babenko
ICML 2023poster

Denoising diffusion probabilistic models are becoming the leading generative modeling paradigm for many important data modalities. Being the most prevalent in the computer vision community, diffusion models have recently gained some attention in other domains, including speech, NLP, and graph-like d…

Cited by 323Source ↗PDF ↗Scholar ↗
2022

Graph-based Nearest Neighbor Search in Hyperbolic Spaces

Liudmila Prokhorenkova, Dmitry Baranchuk, Nikolay Bogachev, Yury Demidovich, Alexander Kolpakov
ICLR 2022poster

The nearest neighbor search (NNS) problem is widely studied in Euclidean space, and graph-based algorithms are known to outperform other approaches for this task. However, hyperbolic geometry often allows for better data representation in various domains, including graphs, words, and images. In this…

Cited by 1Source ↗PDF ↗Scholar ↗
2022

Label-Efficient Semantic Segmentation with Diffusion Models

Dmitry Baranchuk, Andrey Voynov, Ivan Rubachev, Valentin Khrulkov, Artem Babenko
ICLR 2022poster

Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of diffusion models has made them an appealing tool in several a…

Cited by 644Source ↗PDF ↗code ↗Scholar ↗
2020

GP-VAE: Deep Probabilistic Time Series Imputation

Vincent Fortuin, Dmitry Baranchuk, Gunnar Raetsch, Stephan Mandt
AISTATS 2020poster

Multivariate time series with missing values are common in areas such as healthcare and finance, and have grown in number and complexity over the years. This raises the question whether deep learning methodologies can outperform classical data imputation methods in this domain. However, naive applic…

Cited by 359Source ↗PDF ↗code ↗Scholar ↗
2018

Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors

Dmitry Baranchuk, Artem Babenko, Yury Malkov
ECCV 2018poster

This work addresses the problem of billion-scale nearest neighbor search. The state-of-the-art retrieval systems for billion-scale databases are currently based on the inverted multi-index, the recently proposed generalization of the inverted index structure. The multi-index provides a very fine-gra…

Cited by 113Source ↗PDF ↗code ↗Scholar ↗