Sit: Exploring flow and diffusion-based generative models with scalable interpolant transformers
Abstract We present Scalable Interpolant Transformers (SiT), a family of generative models
built on the backbone of Diffusion Transformers (DiT). The interpolant framework, which …
built on the backbone of Diffusion Transformers (DiT). The interpolant framework, which …
Improved motif-scaffolding with SE (3) flow matching
Protein design often begins with the knowledge of a desired function from a motif which motif-
scaffolding aims to construct a functional protein around. Recently, generative models have …
scaffolding aims to construct a functional protein around. Recently, generative models have …
Deep conditional generative learning: Model and error analysis
Abstract We introduce an Ordinary Differential Equation (ODE) based deep generative
method for learning a conditional distribution, named the Conditional Follmer Flow. Starting …
method for learning a conditional distribution, named the Conditional Follmer Flow. Starting …
Extended flow matching: a method of conditional generation with generalized continuity equation
The task of conditional generation is one of the most important applications of generative
models, and numerous methods have been developed to date based on the celebrated flow …
models, and numerous methods have been developed to date based on the celebrated flow …
Conditional simulation via entropic optimal transport: Toward non-parametric estimation of conditional Brenier maps
Conditional simulation is a fundamental task in statistical modeling: Generate samples from
the conditionals given finitely many data points from a joint distribution. One promising …
the conditionals given finitely many data points from a joint distribution. One promising …
Gaussian interpolation flows
Gaussian denoising has emerged as a powerful principle for constructing simulation-free
continuous normalizing flows for generative modeling. Despite their empirical successes …
continuous normalizing flows for generative modeling. Despite their empirical successes …
Recurrent Interpolants for Probabilistic Time Series Prediction
Sequential models like recurrent neural networks and transformers have become standard
for probabilistic multivariate time series forecasting across various domains. Despite their …
for probabilistic multivariate time series forecasting across various domains. Despite their …
Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting
Recent advancements in generative modeling, particularly diffusion models, have opened
new directions for time series modeling, achieving state-of-the-art performance in …
new directions for time series modeling, achieving state-of-the-art performance in …
Boosting Latent Diffusion with Flow Matching
Recently, there has been tremendous progress in visual synthesis and the underlying
generative models. Here, diffusion models (DMs) stand out particularly, but lately, flow …
generative models. Here, diffusion models (DMs) stand out particularly, but lately, flow …
A Generative Modeling Approach to Reconstructing 21-cm Tomographic Data
Analyses of the cosmic 21-cm signal are hampered by astrophysical foregrounds that are far
stronger than the signal itself. These foregrounds, typically confined to a wedge-shaped …
stronger than the signal itself. These foregrounds, typically confined to a wedge-shaped …