English
Related papers

Related papers: Generative Lines Matching Models

200 papers

The efficient construction of accurate channel knowledge maps (CKMs) is crucial for unleashing the full potential of environment-aware wireless networks, yet it remains a difficult ill-posed problem due to the sparsity of available…

Information Theory · Computer Science 2026-01-13 Ziyu Huang , Yong Zeng , Shen Fu , Xiaoli Xu , Hongyang Du

Recently, Generative Adversarial Networks (GANs) have emerged as a popular alternative for modeling complex high dimensional distributions. Most of the existing works implicitly assume that the clean samples from the target distribution are…

Machine Learning · Statistics 2019-02-14 Mohammadreza Soltani , Swayambhoo Jain , Abhinav Sambasivan

Linear mixed models (LMMs) are a powerful and established tool for studying genotype-phenotype relationships. A limiting assumption of LMMs is that the residuals are Gaussian distributed, a requirement that rarely holds in practice.…

Genomics · Quantitative Biology 2014-08-10 Nicolo Fusi , Christoph Lippert , Neil D. Lawrence , Oliver Stegle

Masked Diffusion Models (MDMs) offer flexible, non-autoregressive generation, but this freedom introduces a challenge: final output quality is highly sensitive to the decoding order. We are the first to formalize this issue, attributing the…

Computation and Language · Computer Science 2025-12-25 Ziyu Chen , Xinbei Jiang , Peng Sun , Tao Lin

Time-unconditional generative models learn time-independent denoising vector fields. But without time conditioning, the same noisy input may correspond to multiple noise levels and different denoising directions, which interferes with the…

Machine Learning · Computer Science 2026-02-04 Zimo Wang , Ishit Mehta , Haolin Lu , Chung-En Sun , Ge Yan , Tsui-Wei Weng , Tzu-Mao Li

Score-based generative models have excellent performance in terms of generation quality and likelihood. They model the data distribution by matching a parameterized score network with first-order data score functions. The score network can…

Machine Learning · Statistics 2022-06-28 Cheng Lu , Kaiwen Zheng , Fan Bao , Jianfei Chen , Chongxuan Li , Jun Zhu

Straightening the probability flow of the continuous-time generative models, such as diffusion models or flow-based models, is the key to fast sampling through the numerical solvers, existing methods learn a linear path by directly…

Machine Learning · Computer Science 2024-02-16 Jongmin Yoon , Juho Lee

Deep generative models such as diffusion and flow matching are powerful machine learning tools capable of learning and sampling from high-dimensional distributions. They are particularly useful when the training data appears to be…

High Energy Physics - Phenomenology · Physics 2026-04-30 Zachary Bogorad , Ibrahim Elsharkawy , Yonatan Kahn , Andrew J. Larkoski , Noam Levi

Denoising diffusions are state-of-the-art generative models exhibiting remarkable empirical performance. They work by diffusing the data distribution into a Gaussian distribution and then learning to reverse this noising process to obtain…

Machine Learning · Statistics 2024-02-20 Joe Benton , Yuyang Shi , Valentin De Bortoli , George Deligiannidis , Arnaud Doucet

Score-based generative models achieve state-of-the-art sampling performance by denoising a distribution perturbed by Gaussian noise. In this paper, we focus on a single deterministic denoising step, and compare the optimal denoiser for the…

Machine Learning · Computer Science 2026-03-18 Eliot Beyler , Francis Bach

Normalizing flows are exact-likelihood generative neural networks which approximately transform samples from a simple prior distribution to samples of the probability distribution of interest. Recent work showed that such generative models…

Machine Learning · Statistics 2020-10-27 Jonas Köhler , Leon Klein , Frank Noé

Diffusion models learn to denoise data and the trained denoiser is then used to generate new samples from the data distribution. In this paper, we revisit the diffusion sampling process and identify a fundamental cause of sample quality…

Machine Learning · Computer Science 2024-11-05 Yunshu Wu , Yingtao Luo , Xianghao Kong , Evangelos E. Papalexakis , Greg Ver Steeg

Imperfect score-matching leads to a shift between the training and the sampling distribution of diffusion models. Due to the recursive nature of the generation process, errors in previous steps yield sampling iterates that drift away from…

Machine Learning · Computer Science 2023-02-20 Giannis Daras , Yuval Dagan , Alexandros G. Dimakis , Constantinos Daskalakis

Denoising diffusion probabilistic models (DDPM) are a class of generative models which have recently been shown to produce excellent samples. We show that with a few simple modifications, DDPMs can also achieve competitive log-likelihoods…

Machine Learning · Computer Science 2021-02-22 Alex Nichol , Prafulla Dhariwal

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…

Machine Learning · Computer Science 2024-11-06 Itai Gat , Tal Remez , Neta Shaul , Felix Kreuk , Ricky T. Q. Chen , Gabriel Synnaeve , Yossi Adi , Yaron Lipman

Inspired by the success of Convolutional Neural Networks (CNNs) for supervised prediction in images, we design the Deconvolutional Generative Model (DGM), a new probabilistic generative model whose inference calculations correspond to those…

Computer Vision and Pattern Recognition · Computer Science 2019-12-10 Tan Nguyen , Nhat Ho , Ankit Patel , Anima Anandkumar , Michael I. Jordan , Richard G. Baraniuk

Generative Models (GMs) have attracted considerable attention due to their tremendous success in various domains, such as computer vision where they are capable to generate impressive realistic-looking images. Likelihood-based GMs are…

Machine Learning · Computer Science 2023-12-22 Ba-Hien Tran , Giulio Franzese , Pietro Michiardi , Maurizio Filippone

We present rectified flow, a surprisingly simple approach to learning (neural) ordinary differential equation (ODE) models to transport between two empirically observed distributions \pi_0 and \pi_1, hence providing a unified solution to…

Machine Learning · Computer Science 2022-09-08 Xingchao Liu , Chengyue Gong , Qiang Liu

Iterative generative models such as Flow Matching and Diffusion models have demonstrated strong test-time scaling behavior, where additional inference computation can improve generation quality. In contrast, Drift Models offer efficient…

Machine Learning · Computer Science 2026-05-19 Chenrui Ma , Xi Xiao , Lin Zhao , Tianyang Wang , Ferdinando Fioretto , Yanning Shen

Rectified Flows learn ODE vector fields whose trajectories are straight between source and target distributions, enabling near one-step inference. We show that this straight-path objective conceals fundamental failure modes: under…

Machine Learning · Computer Science 2025-10-22 Teodora Reu , Sixtine Dromigny , Michael Bronstein , Francisco Vargas