English
Related papers

Related papers: Optimizing Noise Schedules of Generative Models in…

200 papers

Generative models such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) are widely utilized to model the generative process of user interactions. However, these generative models suffer from intrinsic…

Information Retrieval · Computer Science 2025-06-26 Wenjie Wang , Yiyan Xu , Fuli Feng , Xinyu Lin , Xiangnan He , Tat-Seng Chua

Forecasting over graph-structured sensor networks demands models that capture both deterministic spatial trends and stochastic variability, while remaining efficient enough for repeated inference as new observations arrive. We propose…

Machine Learning · Computer Science 2026-04-02 Hanlin Dong , Arian Prabowo , Hao Xue , Ao Shuang , Tianyi Zhou , Flora D. Salim

Generative AI has received significant attention among a spectrum of diverse industrial and academic domains, thanks to the magnificent results achieved from deep generative models such as generative pre-trained transformers (GPT) and…

Information Theory · Computer Science 2023-10-06 Mehdi Letafati , Samad Ali , Matti Latva-aho

Diffusion models generate high-resolution images through iterative stochastic processes. In particular, the denoising method is one of the most popular approaches that predicts the noise in samples and denoises it at each time step. It has…

Computer Vision and Pattern Recognition · Computer Science 2024-01-22 Juno Hwang , Yong-Hyun Park , Junghyo Jo

We propose a general framework for optimizing noise schedules in diffusion models, applicable to both training and sampling. Our method enforces a constant rate of change in the probability distribution of diffused data throughout the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Shuntaro Okada , Kenji Doi , Ryota Yoshihashi , Hirokatsu Kataoka , Tomohiro Tanaka

Among likelihood-based approaches for deep generative modelling, variational autoencoders (VAEs) offer scalable amortized posterior inference and fast sampling. However, VAEs are also more and more outperformed by competing models such as…

Machine Learning · Computer Science 2021-07-01 Antoine Wehenkel , Gilles Louppe

A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data…

Computer Vision and Pattern Recognition · Computer Science 2023-10-16 Zhengxiong Luo , Dayou Chen , Yingya Zhang , Yan Huang , Liang Wang , Yujun Shen , Deli Zhao , Jingren Zhou , Tieniu Tan

Diffusion models (DMs) have become the dominant paradigm of generative modeling in a variety of domains by learning stochastic processes from noise to data. Recently, diffusion denoising bridge models (DDBMs), a new formulation of…

Machine Learning · Computer Science 2024-11-01 Guande He , Kaiwen Zheng , Jianfei Chen , Fan Bao , Jun Zhu

Discrete-time diffusion-based generative models and score matching methods have shown promising results in modeling high-dimensional image data. Recently, Song et al. (2021) show that diffusion processes that transform data into noise can…

Machine Learning · Computer Science 2021-10-01 Chin-Wei Huang , Jae Hyun Lim , Aaron Courville

Diffusion models for image generation function by progressively adding noise to an image set and training a model to separate out the signal from the noise. The noise profile used by these models is white noise -- that is, noise based on…

Computer Vision and Pattern Recognition · Computer Science 2025-07-09 Andrew Randono

Using statistical physics methods, we study generative diffusion models in the regime where the dimension of space and the number of data are large, and the score function has been trained optimally. Our analysis reveals three distinct…

Machine Learning · Computer Science 2025-01-08 Giulio Biroli , Tony Bonnaire , Valentin de Bortoli , Marc Mézard

The design of mean and variance schedules for the perturbed signal is a fundamental challenge in generative models. While score-based and Schr\"odinger bridge-based models require careful selection of the stochastic differential equation to…

Sound · Computer Science 2025-09-10 Taihui Wang , Rilin Chen , Tong Lei , Andong Li , Jinzheng Zhao , Meng Yu , Dong Yu

Diffusion models achieve remarkable generation quality but suffer from computational intensive sampling due to suboptimal step discretization. While existing works focus on optimizing denoising directions, we address the principled design…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Jianning Pei , Han Hu , Shuyang Gu

Diffusion and flow matching models have achieved remarkable success in text-to-image generation. However, these models typically rely on the predetermined denoising schedules for all prompts. The multi-step reverse diffusion process can be…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Zilyu Ye , Zhiyang Chen , Tiancheng Li , Zemin Huang , Weijian Luo , Guo-Jun Qi

Diffusion models generate data by learning to reverse a forward process, where samples are progressively perturbed with Gaussian noise according to a predefined noise schedule. From a geometric perspective, each noise schedule corresponds…

Image and Video Processing · Electrical Eng. & Systems 2025-10-21 Teng Zhang , Hongxu Jiang , Kuang Gong , Wei Shao

A generative model based on a continuous-time normalizing flow between any pair of base and target probability densities is proposed. The velocity field of this flow is inferred from the probability current of a time-dependent density that…

Machine Learning · Computer Science 2023-03-10 Michael S. Albergo , Eric Vanden-Eijnden

Procedural noise is a fundamental component of computer graphics pipelines, offering a flexible way to generate textures that exhibit "natural" random variation. Many different types of noise exist, each produced by a separate algorithm. In…

Existing music generation models are mostly language-based, neglecting the frequency continuity property of notes, resulting in inadequate fitting of rare or never-used notes and thus reducing the diversity of generated samples. We argue…

Sound · Computer Science 2024-08-06 Shipei Liu , Xiaoya Fan , Guowei Wu

Diffusion models (DMs) have revolutionized generative learning. They utilize a diffusion process to encode data into a simple Gaussian distribution. However, encoding a complex, potentially multimodal data distribution into a single…

Machine Learning · Computer Science 2024-07-04 Yilun Xu , Gabriele Corso , Tommi Jaakkola , Arash Vahdat , Karsten Kreis

Variational Autoencoders and Generative Adversarial Networks remained the state-of-the-art (SOTA) generative models until 2022. Now they are superseded by diffusion-based models. Efforts to improve traditional models have stagnated as a…

Machine Learning · Computer Science 2026-03-10 Tuhin Subhra De