5 papers
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…
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…
Entering the Era of Discrete Diffusion Models: A Benchmark for Schrödinger Bridges and Entropic Optimal Transport
Xavier Aramayo Carrasco, Grigoriy Ksenofontov, Aleksei Leonov +2
The Entropic Optimal Transport (EOT) problem and its dynamic counterpart, the Schrödinger bridge (SB) problem, play an important role in modern machine learning, linking generativ…
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…
Categorical Schrödinger Bridge Matching
Grigoriy Ksenofontov, Alexander Korotin
The Schrödinger Bridge (SB) is a powerful framework for solving generative modeling tasks such as unpaired domain translation. Most SB-related research focuses on continuous data…