paper-with-me

Papers

Deterministic Discrete Denoising

2025-09-25 · Hideyuki Suzuki, Wataru Kurebayashi, Hiroshi Yamashita arxiv

We propose a deterministic denoising algorithm for discrete-state diffusion models. The key idea is to derandomize the generative reverse Markov chain by introducing a variant of the herding algorithm, which induces deterministic state transitions driven by weakly chaotic dynamics. It serves as a direct replacement for the stochastic denoising process, without requiring retraining or continuous state embeddings. We demonstrate consistent improvements in both efficiency and sample quality on text and image generation tasks. In addition, the proposed algorithm yields improved solutions for diffusion-based combinatorial optimization. Thus, herding-based denoising is a simple yet promising approach for enhancing the generative process of discrete diffusion models. Furthermore, our results reveal that deterministic reverse processes, well established in continuous diffusion, can also be effective in discrete state spaces.

📄 PDF Abstract BibTeX arXiv:2509.20896

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

MissHDD: Hybrid Deterministic Diffusion for Hetrogeneous Incomplete Data Imputation

2025-11-18 · Youran Zhou, Mohamed Reda Bouadjenek, Sunil Aryal arxiv

Incomplete data are common in real-world tabular applications, where numerical, categorical, and discrete attributes coexist within a single dataset. This heterogeneous structure presents significant challenges for exist…

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall

2025-10-22 · Mingyu Jo, Jaesik Yoon, Justin Deschenaux, Caglar Gulcehre 외 arxiv

Discrete diffusion models offer a promising alternative to autoregressive generation through parallel decoding, but they suffer from a sampling wall: once categorical sampling occurs, rich distributional information coll…

Text Generation

Generalized Denoising Diffusion Codebook Models (gDDCM): Tokenizing images using a pre-trained diffusion model

2025-11-17 · Fei Kong arxiv

Denoising diffusion models have emerged as a dominant paradigm in image generation. Discretizing image data into tokens is a critical step for effectively integrating images with Transformer and other architectures. Alth…

Image Generation

R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery

2021-07-12 · Rongkai Zhang, Jiang Zhu, Zhiyuan Zha, Justin Dauwels 외

State-of-the-art image denoisers exploit various types of deep neural networks via deterministic training. Alternatively, very recent works utilize deep reinforcement learning for restoring images with diverse or unknown…

BenchmarkingDeep Reinforcement LearningDenoisingImage Denoising+4

A Latent Space of Stochastic Diffusion Models for Zero-Shot Image Editing and Guidance

2023-01-01 · ICCV 2023 1 · Chen Henry Wu, Fernando de la Torre

Diffusion models generate images by iterative denoising. Recent work has shown that by making the denoising process deterministic, one can encode real images into latent codes of the same size, which can be used for …

Denoising