English
Related papers

Related papers: A Coordinate Free Formulation of Effective Diffusi…

200 papers

Riemannian diffusion models draw inspiration from standard Euclidean space diffusion models to learn distributions on general manifolds. Unfortunately, the additional geometric complexity renders the diffusion transition term inexpressible…

Machine Learning · Computer Science 2023-11-01 Aaron Lou , Minkai Xu , Stefano Ermon

As one of the most popular and sought-after generative models in the recent years, diffusion models have sparked the interests of many researchers and steadily shown excellent advantage in various generative tasks such as image synthesis,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Zhiyuan Ma , Yuzhu Zhang , Guoli Jia , Liangliang Zhao , Yichao Ma , Mingjie Ma , Gaofeng Liu , Kaiyan Zhang , Jianjun Li , Bowen Zhou

Diffraction-free optical beams propagate freely without change in shape and scale. Monochromatic beams that avoid diffractive spreading require two-dimensional transverse profiles, and there are no corresponding solutions for profiles…

Optics · Physics 2017-11-02 H. Esat Kondakci , Ayman F. Abouraddy

The aim of this paper is to present a first evaluation of a dynamic partition strategy associated to the recently proposed asynchronous distributed computation scheme based on the D-iteration approach. The D-iteration is a fluid diffusion…

Distributed, Parallel, and Cluster Computing · Computer Science 2012-03-13 Dohy Hong

We solve the anisotropic diffusion equation in 2D, where the dominant direction of diffusion is defined by a vector field which does not conform to a Cartesian grid. Our method uses operator splitting to separate the diffusion perpendicular…

Numerical Analysis · Mathematics 2023-03-29 Dean Muir , Kenneth Duru , Matthew Hole , Stuart Hudson

Let $\mathcal{K}\subset R^d$, $d\ge2$, be a smooth, bounded domain satisfying $0\in\mathcal{K}$, and let $f(t),\ t\ge0$, be a smooth, continuous, nondecreasing function satisfying $f(0)>1$. Define $D_t=f(t)\mathcal{K}\subset R^d$. Consider…

Probability · Mathematics 2016-01-13 Ross G. Pinsky

We discuss the distribution of various estimators for extracting the diffusion constant of single Brownian trajectories obtained by fitting the squared displacement of the trajectory. The analysis of the problem can be framed in terms of…

Statistical Mechanics · Physics 2015-05-28 Denis Boyer , David S. Dean

A kind of spatial fractional diffusion equations in this paper are studied. Firstly, an L1 formula is employed for the spatial discretization of the equations. Then, a second order scheme is derived based on the resulting semi-discrete…

Numerical Analysis · Mathematics 2020-01-08 Yong-Liang Zhao , Pei-Yong Zhu , Xian-Ming Gu , Xi-Le Zhao , Huan-Yan Jian

The general covariance of the diffusion equation is exploited in order to explore the curvature effects appearing on brownian motion over a d-dimensional curved manifold. We use the local frame defined by the so called Riemann normal…

Statistical Mechanics · Physics 2015-05-18 Pavel Castro-Villarreal

Analysis of signal fluctuations of a locally fixed probe, caused by molecules diffusing under the probe, can be used to determine diffusion coefficients. Theoretical treatments so far have been limited to point-like particles or to…

Statistical Mechanics · Physics 2015-06-18 Susanne Hahne , Philipp Maass

We present Surf-D, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Previous methods explored shape generation with different representations and they suffer from limited…

Computer Vision and Pattern Recognition · Computer Science 2024-07-25 Zhengming Yu , Zhiyang Dou , Xiaoxiao Long , Cheng Lin , Zekun Li , Yuan Liu , Norman Müller , Taku Komura , Marc Habermann , Christian Theobalt , Xin Li , Wenping Wang

Drivable Free-space prediction is a fundamental and crucial problem in autonomous driving. Recent works have addressed the problem by representing the entire non-obstacle road regions as the free-space. In contrast our aim is to estimate…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Keshav Gupta , Tejas S. Stanley , Pranjal Paul , Arun K. Singh , K. Madhava Krishna

We propose a new class of generative diffusion models, called functional diffusion. In contrast to previous work, functional diffusion works on samples that are represented by functions with a continuous domain. Functional diffusion can be…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Biao Zhang , Peter Wonka

We propose a seamless multiscale method which approximates the macroscopic behavior of the passive advection-diffusion equations with steady incompressible velocity fields with multi-spatial scales. The method uses decompositions of the…

Numerical Analysis · Mathematics 2016-06-22 Yoonsang Lee , Bjorn Engquist

Discrete diffusion has become a leading framework for generative modeling in various applications including language, vision, and biology. Existing convergence theory, however, exhibits fundamental limitations. KL-based analyses diverge…

Machine Learning · Computer Science 2026-05-19 Kelvin Kan , Xingjian Li , Benjamin J. Zhang , Tuhin Sahai , Stanley Osher , Markos A. Katsoulakis

The invariance for the equation of fast diffusion in the 2D coordinate space has been proved, and its reduction to the 1D (with respect to the spatial variable) analog is demonstrated. On the basis of these results, new exact…

Mathematical Physics · Physics 2007-05-23 E. I. Semenov

The effective diffusivity of Brownian tracer particles confined in periodic micro-channels is smaller than the microscopic diffusivity due to entropic trapping. Here, we study diffusion in two-dimensional periodic channels whose…

Statistical Mechanics · Physics 2019-05-29 M. Mangeat , T. Guérin , D. S. Dean

Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. However, rather than merely generating designs that are natural, we often aim to optimize downstream reward functions while…

This paper is devoted to the study of some nonlinear parabolic equations with discontinuous diffusion intensities. Such problems appear naturally in physical and biological models. Our analysis is based on variational techniques and in…

Analysis of PDEs · Mathematics 2021-02-09 Dohyun Kwon , Alpár Richárd Mészáros

We consider a sequence of idealized measurements of time-separation $\Delta t$ onto a discrete one-dimensional disordered system. A connection with Markov chains is found. For a rapid sequence of measurements, a diffusive regime occurs and…

Disordered Systems and Neural Networks · Physics 2009-10-31 J. C. Flores