paper-with-me

Papers

Flow Matching for Generative Modeling

2022-10-06 · Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu, Maximilian Nickel, Matt Le

We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for training CNFs based on regressing vector fields of fixed conditional probability paths. Flow Matching is compatible with a general family of Gaussian probability paths for transforming between noise and data samples -- which subsumes existing diffusion paths as specific instances. Interestingly, we find that employing FM with diffusion paths results in a more robust and stable alternative for training diffusion models. Furthermore, Flow Matching opens the door to training CNFs with other, non-diffusion probability paths. An instance of particular interest is using Optimal Transport (OT) displacement interpolation to define the conditional probability paths. These paths are more efficient than diffusion paths, provide faster training and sampling, and result in better generalization. Training CNFs using Flow Matching on ImageNet leads to consistently better performance than alternative diffusion-based methods in terms of both likelihood and sample quality, and allows fast and reliable sample generation using off-the-shelf numerical ODE solvers.

📄 PDF Abstract BibTeX arXiv:2210.02747

Code (5)

edapinenut/ppflow pytorch
g4vrel/CFM pytorch
jjunak-yun/FLowHigh_code pytorch
leffff/FlowModels pytorch
shivammehta25/Matcha-TTS pytorch

Tasks

Density EstimationImage Generation

Methods 이 논문이 사용한 방법론

TRON Customer Service Number +1-833-534-1729 설명 없음
Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

CaLMFlow: Volterra Flow Matching using Causal Language Models

2024-10-03 · Sizhuang He, Daniel Levine, Ivan Vrkic, Marco Francesco Bressana 외

We introduce CaLMFlow (Causal Language Models for Flow Matching), a novel framework that casts flow matching as a Volterra integral equation (VIE), leveraging the power of large language models (LLMs) for continuous data…

Language ModelingLanguage Modelling

Generative Modeling of Quantum Distribution with Functional Flow Matching

2026-07-01 · Jaehoon Hahm, Tak Hur, Joonseok Lee, Daniel K. Park arxiv

The emergence of powerful deep generative models based on diffusion and flow matching has enabled the learning and modeling of complex distributions. Learning quantum distributions, however, remains challenging due to th…

Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{ö}dinger bridge

2026-06-29 · Titouan Vayer arxiv

These notes recapitulate the high level mathematical principles behind different techniques for generative modeling. I show the connections between optimal transport and standard techniques such as Schr{ö}dinger bridge a…

Towards Variational Flow Matching on General Geometries

2025-02-18 · Olga Zaghen, Floor Eijkelboom, Alison Pouplin, Erik J. Bekkers

We introduce Riemannian Gaussian Variational Flow Matching (RG-VFM), an extension of Variational Flow Matching (VFM) that leverages Riemannian Gaussian distributions for generative modeling on structured manifolds. We de…

Generator Matching: Generative modeling with arbitrary Markov processes

2024-10-27 · Peter Holderrieth, Marton Havasi, Jason Yim, Neta Shaul 외

We introduce generator matching, a modality-agnostic framework for generative modeling using arbitrary Markov processes. Generators characterize the infinitesimal evolution of a Markov process, which we leverage for gene…

Image Generation