# Discrete Diffusion Models: A Unified Framework from Tokenization to Generation

arXiv: https://arxiv.org/abs/2607.13431 · HTML: https://mlsanity.com/paper/2607.13431/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 3 of its 534 references that are in the map.
- First posted on arXiv 15 Jul 2026.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 3 of 3)

- [FoldToken: Learning Protein Language via Vector Quantization and Beyond](https://mlsanity.com/paper/2403.09673/) (2024)
- [Protein Structure Tokenization: Benchmarking and New Recipe](https://mlsanity.com/paper/2503.00089/) (2025)
- [DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors](https://mlsanity.com/paper/2604.25050/) (2026)

## Abstract (arXiv)

Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and iterative global refinement capabilities. Unlike continuous diffusion, where the state space is fixed, DDMs are fundamentally shaped by how the discrete state space is constructed: the tokenization scheme, the vocabulary topology, and domain-specific structural alphabets. This work introduces a unified conceptual framework that views discrete diffusion models through the construction of the underlying discrete state space. Within this framework, existing formulations, including transition-matrix, masking/absorbing-state, and score/ratio-based approaches, emerge as different instantiations of a common design space. The framework further exposes common design trade-offs across training objectives, inference algorithms, scaling behavior, systems optimization, and evaluation protocols, suggesting several promising directions for future research.