Yeti Z. Gurbuz — accepted AI-conference papers

2026

Minibatch Optimal Transport and Perplexity Bound Estimation in Discrete Flow Matching

Etrit Haxholli, Yeti Z. Gurbuz, Oğul Can, Eli Waxman

ICML 2026poster

Discrete flow matching, a recent framework for modeling categorical data, has shown competitive performance with autoregressive models. However, unlike continuous flow matching, the rectification strategy cannot be applied due to the stochasticity of discrete paths, necessitating alternative methods…

Cited by 0 Source ↗Scholar ↗

2025

Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language Models

Etrit Haxholli, Yeti Z. Gurbuz, Oğul Can, Eli Waxman

ICLR 2025poster

While continuous diffusion models excel in modeling continuous distributions, their application to categorical data has been less effective. Recent work has shown that ratio-matching through *score-entropy* within a continuous-time discrete Markov chain (CTMC) framework serves as a competitive alter…

Cited by 0 Source ↗PDF ↗Scholar ↗