English
Related papers

Related papers: IDF++: Analyzing and Improving Integer Discrete Fl…

200 papers

Normalizing flows are a promising tool for modeling probability distributions in physical systems. While state-of-the-art flows accurately approximate distributions and energies, applications in physics additionally require smooth energies…

Machine Learning · Statistics 2021-12-01 Jonas Köhler , Andreas Krämer , Frank Noé

Modeling continuous-time dynamics from sparse and irregularly-sampled time series remains a fundamental challenge. Neural controlled differential equations provide a principled framework for such tasks, yet their performance is highly…

Machine Learning · Computer Science 2026-04-03 YongKyung Oh , Dong-Young Lim , Sungil Kim

We present a novel implicit porous flow solver using SPH, which maintains fluid incompressibility and is able to model a wide range of scenarios, driven by strongly coupled solid-fluid interaction forces. Many previous SPH porous flow…

Graphics · Computer Science 2025-12-08 Timna Böttcher , Stefan Rhys Jeske , Lukas Westhofen , Jan Bender

Over the last few years, machine learning unlocked previously infeasible features for compression, such as providing guarantees for users' privacy or tailoring compression to specific data statistics (e.g., satellite images or audio…

Information Theory · Computer Science 2026-03-25 Gergely Flamich

Continuous diffusion models are commonly acknowledged to display a deterministic probability flow, whereas discrete diffusion models do not. In this paper, we aim to establish the fundamental theory for the probability flow of discrete…

Machine Learning · Computer Science 2023-11-08 Pengze Zhang , Hubery Yin , Chen Li , Xiaohua Xie

Conditional Flow Matching (CFM) models can generate high-quality samples from a non-informative prior, but they can be slow, often needing hundreds of network evaluations (NFE). To address this, we propose Implicit Dynamical Flow Fusion…

Machine Learning · Computer Science 2025-05-28 Mohammad R. Rezaei , Milos R. Popovic , Milad Lankarany , Rahul G. Krishnan

Constant-time programming is a countermeasure to prevent cache based attacks where programs should not perform memory accesses that depend on secrets. In some cases this policy can be safely relaxed if one can prove that the program does…

Cryptography and Security · Computer Science 2023-06-22 Cristian Ene , Laurent Mounier , Marie-Laure Potet

In this study we have developed a flexible and efficient numerical scheme for the simulation of three-dimensional incompressible flows in spherical coordinates. The main idea, inspired by a similar strategy as (Verzicco, R., Orlandi, P.,…

Fluid Dynamics · Physics 2020-10-28 L. Santelli , P. Orlandi , R. Verzicco

We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the reverse process, we optimize an advantage-weighted forward-process prediction loss. This…

Machine Learning · Computer Science 2026-05-26 Branislav Kveton , Anup Rao , Subhojyoti Mukherjee , Krishna Kumar Singh , Viet Dac Lai

Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target distributions over compositional objects. A key limitation of GFlowNets until this time has been that…

An improved understanding of the divergence-free constraint for the incompressible Navier--Stokes equations leads to the observation that a semi-norm and corresponding equivalence classes of forces are fundamental for their nonlinear…

Numerical Analysis · Mathematics 2019-04-18 Nicolas R. Gauger , Alexander Linke , Philipp W. Schroeder

An adaptive model for the description of flows in highly heterogeneous porous media is developed in~\cite{FP21,FP23}. There, depending on the magnitude of the fluid's velocity, the constitutive law linking velocity and pressure gradient is…

Numerical Analysis · Mathematics 2024-05-06 Alessio Fumagalli , Francesco S. Patacchini

A transformation that relates a compressible wall-bounded turbulent flow with non-uniform fluid properties to an equivalent incompressible flow with uniform fluid properties is derived and validated. The transformation accounts for both…

Fluid Dynamics · Physics 2023-10-05 Asif Manzoor Hasan , Johan Larsson , Sergio Pirozzoli , Rene Pecnik

Entropy stable schemes can be constructed with a specific choice of the numerical flux function. First, an entropy conserving flux is constructed. Secondly, an entropy stable dissipation term is added to this flux to guarantee dissipation…

Computational Physics · Physics 2017-11-17 Dominik Derigs , Andrew R. Winters , Gregor J. Gassner , Stefanie Walch

We consider a two-phase Darcy flow in a fractured and deformable porous medium for which the fractures are described as a network of planar surfaces leading to so-called hybrid-dimensional models. The fractures are assumed open and filled…

Numerical Analysis · Mathematics 2021-08-17 Francesco Bonaldi , Konstantin Brenner , Jérôme Droniou , Roland Masson , Antoine Pasteau , Laurent Trenty

Ordinary differential equation (ODE) based generative models have emerged as a powerful approach for producing high-quality samples in many applications. However, the ODE-based methods either suffer the discretization error of numerical…

Computer Vision and Pattern Recognition · Computer Science 2025-04-30 Jingjing Wang , Dan Zhang , Joshua Luo , Yin Yang , Feng Luo

Recent work demonstrated that flow-based invertible neural networks are promising tools for solving ambiguous inverse problems. Following up on this, we investigate how ten invertible architectures and related models fare on two intuitive,…

Machine Learning · Computer Science 2021-06-23 Jakob Kruse , Lynton Ardizzone , Carsten Rother , Ullrich Köthe

Inverse reinforcement learning (IRL) and dynamic discrete choice (DDC) models explain sequential decision-making by recovering reward functions that rationalize observed behavior. Flexible IRL methods typically rely on machine learning but…

Machine Learning · Computer Science 2026-01-01 Lars van der Laan , Aurelien Bibaut , Nathan Kallus

Density varies spatiotemporally in low Mach number flows. Hence, incompressibility cannot be assumed, and the density must be accurately solved. Various methods have been proposed to analyze low Mach number flows, but their energy…

Fluid Dynamics · Physics 2025-02-13 Hideki Yanaoka , Yuji Sato

While much work on deep latent variable models of text uses continuous latent variables, discrete latent variables are interesting because they are more interpretable and typically more space efficient. We consider several approaches to…

Computation and Language · Computer Science 2020-06-12 Shuning Jin , Sam Wiseman , Karl Stratos , Karen Livescu