Abstract We present Scalable Interpolant Transformers (SiT), a family of generative models
built on the backbone of Diffusion Transformers (DiT). The interpolant framework, which …

We provide theoretical convergence guarantees for score-based generative models (SGMs)
such as denoising diffusion probabilistic models (DDPMs), which constitute the backbone of …

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 …

We provide the first polynomial-time convergence guarantees for the probabilistic flow ODE
implementation (together with a corrector step) of score-based generative modeling. Our …

We develop a framework for non-asymptotic analysis of deterministic samplers used for
diffusion generative modeling. Several recent works have analyzed stochastic samplers …

Diffusion models are a powerful method for generating approximate samples from high-
dimensional data distributions. Several recent results have provided polynomial bounds on …

Recent works have shown that diffusion models can learn essentially any distribution
provided one can perform score estimation. Yet it remains poorly understood under what …

In this paper, we contend that the objective of representation learning is to compress and
transform the distribution of the data, say sets of tokens, towards a mixture of low …

Diffusion models are a class of generative models that serve to establish a stochastic
transport map between an empirically observed, yet unknown, target distribution and a …

Diffusion models, which convert noise into new data instances by learning to reverse a
Markov diffusion process, have become a cornerstone in contemporary generative …