paper-with-me

Papers

Score-based generative diffusion with "active" correlated noise sources

2024-11-11 · Alexandra Lamtyugina, Agnish Kumar Behera, Aditya Nandy, Carlos Floyd, Suriyanarayanan Vaikuntanathan

Diffusion models exhibit robust generative properties by approximating the underlying distribution of a dataset and synthesizing data by sampling from the approximated distribution. In this work, we explore how the generative performance may be be modulated if noise sources with temporal correlations -- akin to those used in the field of active matter -- are used for the destruction of the data in the forward process. Our numerical and analytical experiments suggest that the corresponding reverse process may exhibit improved generative properties.

📄 PDF Abstract BibTeX arXiv:2411.07233

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PTQD: Accurate Post-Training Quantization for Diffusion Models

2023-05-18 · NeurIPS 2023 11 · Yefei He, Luping Liu, Jing Liu, Weijia Wu 외

Diffusion models have recently dominated image synthesis tasks. However, the iterative denoising process is expensive in computations at inference time, making diffusion models less practical for low-latency and scalable…

DenoisingImage GenerationQuantization

CARD: Correlation Aware Restoration with Diffusion

2025-12-04 · Niki Nezakati, Arnab Ghosh, Amit Roy-Chowdhury, Vishwanath Saragadam arxiv

Denoising diffusion models have achieved state-of-the-art performance in image restoration by modeling the process as sequential denoising steps. However, most approaches assume independent and identically distributed (i…

Image Restoration

Guided Trajectory Optimization with Sparse Scaling for Test-Time Diffusion

2026-05-21 · Gang Dai, Yining Huang, Yiming Xia, Guohao Chen 외 arxiv

The efficient Test-Time Scaling (TTS) paradigm offers a promising perspective for enhancing the generation performance of diffusion models. However, current solutions are limited to a static, pre-defined noise pool and s…

Blue noise for diffusion models

2024-02-07 · Xingchang Huang, Corentin Salaün, Cristina Vasconcelos, Christian Theobalt 외

Most of the existing diffusion models use Gaussian noise for training and sampling across all time steps, which may not optimally account for the frequency contents reconstructed by the denoising network. Despite the div…

Denoising

From Independent to Correlated Diffusion: Generalized Generative Modeling with Probabilistic Computers

2026-03-30 · Nihal Sanjay Singh, Mazdak Mohseni-Rajaee, Shaila Niazi, Kerem Y. Camsari arxiv

Diffusion models have emerged as a powerful framework for generative tasks in deep learning. They decompose generative modeling into two computational primitives: deterministic neural-network evaluation and stochastic sa…