Iaroslav Sergeevich Koshelev — accepted AI-conference papers

2026

Entering the Era of Discrete Diffusion Models: A Benchmark for Schrödinger Bridges and Entropic Optimal Transport

Xavier Aramayo Carrasco, Grigoriy Ksenofontov, Aleksei Leonov, Iaroslav Sergeevich Koshelev, Alexander Korotin

ICLR 2026poster

The Entropic Optimal Transport (EOT) problem and its dynamic counterpart, the Schrödinger bridge (SB) problem, play an important role in modern machine learning, linking generative modeling with optimal transport theory. While recent advances in discrete diffusion and flow models have sparked growin…

Cited by 0 Source ↗code ↗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 0 Source ↗code ↗Scholar ↗

2024

A Modular Conditional Diffusion Framework for Image Reconstruction

Magauiya Zhussip, Iaroslav Sergeevich Koshelev, Stamatios Lefkimmiatis

NeurIPS 2024poster

Diffusion Probabilistic Models (DPMs) have been recently utilized to deal with various blind image restoration (IR) tasks, where they have demonstrated outstanding performance in terms of perceptual quality. However, the task-specific nature of existing solutions and the excessive computational cost…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization

Stamatios Lefkimmiatis, Iaroslav Sergeevich Koshelev

ICLR 2023poster

In this work we introduce a novel optimization algorithm for image recovery under learned sparse and low-rank constraints, which are parameterized with weighted extensions of the $\ell_p^p$-vector and $\mathcal{S}_p^p$ Schatten-matrix quasi-norms for $0\!<p\!\le1$, respectively. Our proposed algorit…

Cited by 11 Source ↗PDF ↗Scholar ↗