Discrete Flow Matching

• Published in: arXiv.org
• Main Authors: Gat, Itai, Remez, Tal, Shaul, Neta, Kreuk, Felix, Chen, Ricky T Q, Synnaeve, Gabriel, Adi, Yossi, Lipman, Yaron
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 22.07.2024
• Subjects: Autoregressive models; Matching; Noise prediction
• ISSN: 2331-8422

Despite Flow Matching and diffusion models having emerged as powerful generative paradigms for continuous variables such as images and videos, their application to high-dimensional discrete data, such as language, is still limited. In this work, we present Discrete Flow Matching, a novel discrete flow paradigm designed specifically for generating discrete data. Discrete Flow Matching offers several key contributions: (i) it works with a general family of probability paths interpolating between source and target distributions; (ii) it allows for a generic formula for sampling from these probability paths using learned posteriors such as the probability denoiser (\(x\)-prediction) and noise-prediction (\(\epsilon\)-prediction); (iii) practically, focusing on specific probability paths defined with different schedulers considerably improves generative perplexity compared to previous discrete diffusion and flow models; and (iv) by scaling Discrete Flow Matching models up to 1.7B parameters, we reach 6.7% Pass@1 and 13.4% Pass@10 on HumanEval and 6.7% Pass@1 and 20.6% Pass@10 on 1-shot MBPP coding benchmarks. Our approach is capable of generating high-quality discrete data in a non-autoregressive fashion, significantly closing the gap between autoregressive models and discrete flow models.