Sit: Exploring flow and diffusion-based generative models with scalable interpolant transformers

N Ma, M Goldstein, MS Albergo, NM Boffi… - … on Computer Vision, 2024 - Springer
Abstract We present Scalable Interpolant Transformers (SiT), a family of generative models
built on the backbone of Diffusion Transformers (DiT). The interpolant framework, which …

Improved motif-scaffolding with SE (3) flow matching

J Yim, A Campbell, E Mathieu, AYK Foong… - Ar**v, 2024 - pmc.ncbi.nlm.nih.gov
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 …

Deep conditional generative learning: Model and error analysis

J Chang, Z Ding, Y Jiao, R Li, J Zhijian Yang - arxiv e-prints, 2024 - ui.adsabs.harvard.edu
Abstract We introduce an Ordinary Differential Equation (ODE) based deep generative
method for learning a conditional distribution, named the Conditional Follmer Flow. Starting …

Extended flow matching: a method of conditional generation with generalized continuity equation

N Isobe, M Koyama, J Zhang, K Hayashi… - arxiv preprint arxiv …, 2024 - arxiv.org
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 …

Conditional simulation via entropic optimal transport: Toward non-parametric estimation of conditional Brenier maps

R Baptista, AA Pooladian, M Brennan… - arxiv preprint arxiv …, 2024 - arxiv.org
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 …

Gaussian interpolation flows

Y Gao, J Huang, Y Jiao - arxiv preprint arxiv:2311.11475, 2023 - arxiv.org
Gaussian denoising has emerged as a powerful principle for constructing simulation-free
continuous normalizing flows for generative modeling. Despite their empirical successes …

Recurrent Interpolants for Probabilistic Time Series Prediction

Y Chen, M Biloš, S Mittal, W Deng, K Rasul… - arxiv preprint arxiv …, 2024 - arxiv.org
Sequential models like recurrent neural networks and transformers have become standard
for probabilistic multivariate time series forecasting across various domains. Despite their …

Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting

M Kollovieh, M Lienen, D Lüdke, L Schwinn… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent advancements in generative modeling, particularly diffusion models, have opened
new directions for time series modeling, achieving state-of-the-art performance in …

Boosting Latent Diffusion with Flow Matching

JS Fischer, M Gui, P Ma, N Stracke… - arxiv preprint arxiv …, 2023 - arxiv.org
Recently, there has been tremendous progress in visual synthesis and the underlying
generative models. Here, diffusion models (DMs) stand out particularly, but lately, flow …

A Generative Modeling Approach to Reconstructing 21-cm Tomographic Data

N Sabti, RPR Sudha, JB Muñoz… - Machine Learning …, 2025 - iopscience.iop.org
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 …