activity
20242026
collaborators

6 papers

cs.LG2026

TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models

Arseny Ivanov, Sergei Kholkin, Vladislav Gromadskii +3

Log-likelihood is a standard metric for evaluating generative models. Unfortunately, in contrast to autoregressive models (ARMs), discrete diffusion models generally do not admit e…

cs.LG2026

Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting

Sergei Kholkin, Grigoriy Ksenofontov, David Li +6

The Iterative Markovian Fitting (IMF) procedure, which iteratively projects onto the space of Markov processes and the reciprocal class, successfully solves the Schrödinger Bridge…

cs.LG2026

InfoBridge: Mutual Information estimation via Bridge Matching

Sergei Kholkin, Ivan Butakov, Evgeny Burnaev +2

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 mach…

cs.LG2026

Discrete Bridges for Mutual Information Estimation

Iryna Zabarianska, Sergei Kholkin, Grigoriy Ksenofontov +2

Diffusion bridge models in both continuous and discrete state spaces have recently become powerful tools in the field of generative modeling. In this work, we leverage the discrete…

cs.LG2025

Sampling from Energy distributions with Target Concrete Score Identity

Sergei Kholkin, Francisco Vargas, Alexander Korotin

We introduce the Target Concrete Score Identity Sampler (TCSIS), a method for sampling from unnormalized densities on discrete state spaces by learning the reverse dynamics of a Co…

cs.LG2024

Adversarial Schrödinger Bridge Matching

Nikita Gushchin, Daniil Selikhanovych, Sergei Kholkin +2

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 It…