AIConfPaper
← Search

Nikita Gushchin

13 accepted papers

2026

Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting

Sergei Kholkin, Grigoriy Ksenofontov, David Li, Nikita Maksimovich Kornilov, Nikita Gushchin, Alexandra Suvorikova +3
ICLR 2026poster

The Iterative Markovian Fitting (IMF) procedure, which iteratively projects onto the space of Markov processes and the reciprocal class, successfully solves the Schrödinger Bridge (SB) problem. However, an efficient practical implementation requires a heuristic modification-alternating between fitti…

Cited by 0Source ↗code ↗Scholar ↗
2026

IDLM: Inverse-distilled Diffusion Language Models

David Li, Nikita Gushchin, Dmitry Abulkhanov, Eric Moulines, Ivan Oseledets, Maxim Panov +1
ICML 2026poster

Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique originally developed to accelerate continuous diffusion models, …

Cited by 0Source ↗Scholar ↗
2026

InfoBridge: Mutual Information estimation via Bridge Matching

Sergei Kholkin, Ivan Butakov, Evgeny Burnaev, Nikita Gushchin, Alexander Korotin
ICLR 2026poster

Diffusion bridge models have recently become a powerful tool in the field of generative modeling. In this work, we leverage their power to address another important problem in machine learning and information theory, the estimation of the mutual information (MI) between two random variables. Neatly…

Cited by 0Source ↗code ↗Scholar ↗
2026

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation

Daniil Selikhanovych, David Li, Aleksei Leonov, Nikita Gushchin, Sergei Kushneriuk, Alexander Filippov +3
ICML 2026poster

Diffusion models for super-resolution (SR) produce high-quality visual results but require expensive computational costs. Despite the development of several methods to accelerate diffusion-based SR models, some (e.g., SinSR) fail to produce realistic perceptual details, while others (e.g., OSEDiff) …

Cited by 0Source ↗Scholar ↗
2026

Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)

Nikita Maksimovich Kornilov, David Li, Tikhon Mavrin, Aleksei Leonov, Nikita Gushchin, Evgeny Burnaev +2
ICLR 2026oral

While achieving exceptional generative quality, modern diffusion, flow, and other matching models suffer from slow inference, as they require many steps of iterative generation. Recent distillation methods address this by training efficient one-step generators under the guidance of a pre-trained tea…

Cited by 0Source ↗code ↗Scholar ↗
2026

Variational Entropic Optimal Transport

Roman Dyachenko, Nikita Gushchin, Kirill Sokolov, Petr Mokrov, Evgeny Burnaev, Aleksandr Korotin
ICML 2026poster

Entropic optimal transport (EOT) in continuous spaces with quadratic cost is a classical tool for solving the domain translation problem. In practice, recent approaches optimize a weak dual EOT objective depending on a single potential, but doing so is computationally not efficient due to the intrac…

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 ↗
2024

Adversarial Schrödinger Bridge Matching

Nikita Gushchin, Daniil Selikhanovych, Sergei Kholkin, Evgeny Burnaev, Alexander Korotin
NeurIPS 2024poster

The Schrödinger Bridge (SB) problem offers a powerful framework for combining optimal transport and diffusion models. A promising recent approach to solve the SB problem is the Iterative Markovian Fitting (IMF) procedure, which alternates between Markovian and reciprocal projections of continuous-ti…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2024

Energy-guided Entropic Neural Optimal Transport

Petr Mokrov, Alexander Korotin, Alexander Kolesov, Nikita Gushchin, Evgeny Burnaev
ICLR 2024poster

Energy-based models (EBMs) are known in the Machine Learning community for decades. Since the seminal works devoted to EBMs dating back to the noughties, there have been a lot of efficient methods which solve the generative modelling problem by means of energy potentials (unnormalized likelihood fun…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2024

Light and Optimal Schrödinger Bridge Matching

Nikita Gushchin, Sergei Kholkin, Evgeny Burnaev, Alexander Korotin
ICML 2024poster

Schrödinger Bridges (SB) have recently gained the attention of the ML community as a promising extension of classic diffusion models which is also interconnected to the Entropic Optimal Transport (EOT). Recent solvers for SB exploit the pervasive bridge matching procedures. Such procedures aim to re…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2023

Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark

Nikita Gushchin, Alexander Kolesov, Petr Mokrov, Polina Karpikova, Andrei Spiridonov, Evgeny Burnaev +1
NeurIPS 2023poster

Over the last several years, there has been significant progress in developing neural solvers for the Schrödinger Bridge (SB) problem and applying them to generative modelling. This new research field is justifiably fruitful as it is interconnected with the practically well-performing diffusion mode…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2023

Entropic Neural Optimal Transport via Diffusion Processes

Nikita Gushchin, Alexander Kolesov, Alexander Korotin, Dmitry P. Vetrov, Evgeny Burnaev
NeurIPS 2023oral

We propose a novel neural algorithm for the fundamental problem of computing the entropic optimal transport (EOT) plan between probability distributions which are accessible by samples. Our algorithm is based on the saddle point reformulation of the dynamic version of EOT which is known as the Schrö…

Cited by 32Source ↗PDF ↗code ↗Scholar ↗