paper-with-me

Papers

SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers

2024-01-16 · Nanye Ma, Mark Goldstein, Michael S. Albergo, Nicholas M. Boffi, Eric Vanden-Eijnden, Saining Xie

We present Scalable Interpolant Transformers (SiT), a family of generative models built on the backbone of Diffusion Transformers (DiT). The interpolant framework, which allows for connecting two distributions in a more flexible way than standard diffusion models, makes possible a modular study of various design choices impacting generative models built on dynamical transport: learning in discrete or continuous time, the objective function, the interpolant that connects the distributions, and deterministic or stochastic sampling. By carefully introducing the above ingredients, SiT surpasses DiT uniformly across model sizes on the conditional ImageNet 256x256 and 512x512 benchmark using the exact same model structure, number of parameters, and GFLOPs. By exploring various diffusion coefficients, which can be tuned separately from learning, SiT achieves an FID-50K score of 2.06 and 2.62, respectively.

📄 PDF Abstract BibTeX arXiv:2401.08740

Code (1)

willisma/sit 공식 구현 pytorch

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

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

Tilt Matching for Scalable Sampling and Fine-Tuning

2025-12-26 · Peter Potaptchik, Cheuk-Kit Lee, Michael S. Albergo arxiv

We propose a simple, scalable algorithm for using stochastic interpolants to sample from unnormalized densities and for fine-tuning generative models. The approach, Tilt Matching, arises from a dynamical equation relatin…

Stochastic Interpolants: A Unifying Framework for Flows and Diffusions

2023-03-15 · Michael S. Albergo, Nicholas M. Boffi, Eric Vanden-Eijnden

A class of generative models that unifies flow-based and diffusion-based methods is introduced. These models extend the framework proposed in Albergo & Vanden-Eijnden (2023), enabling the use of a broad class of continuo…

Denoising

Flow map matching with stochastic interpolants: A mathematical framework for consistency models

2024-06-11 · Nicholas M. Boffi, Michael S. Albergo, Eric Vanden-Eijnden

Generative models based on dynamical equations such as flows and diffusions offer exceptional sample quality, but require computationally expensive numerical integration during inference. The advent of consistency models…

Numerical Integration

Physics-aware generative models for turbulent fluid flows through energy-consistent stochastic interpolants

2025-04-08 · Nikolaj T. Mücke, Benjamin Sanderse

Generative models have demonstrated remarkable success in domains such as text, image, and video synthesis. In this work, we explore the application of generative models to fluid dynamics, specifically for turbulence sim…

Fast Sampling for Flows and Diffusions with Lazy and Point Mass Stochastic Interpolants

2026-02-03 · Gabriel Damsholt, Jes Frellsen, Susanne Ditlevsen arxiv

Stochastic interpolants unify flows and diffusions, popular generative modeling frameworks. A primary hyperparameter in these methods is the interpolation schedule that determines how to bridge a standard Gaussian base m…