In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as" consistent model reproducibility'': given the same starting noise input and …
Inversion by Direct Iteration (InDI) is a new formulation for supervised image restoration that avoids the so-called" regression to the mean" effect and produces more realistic and …
Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have thus far been held back by limitations in their simulation-based maximum …
GM Rotskoff - Current Opinion in Solid State and Materials Science, 2024 - Elsevier
If the promise of generative modeling techniques is realized, it may fundamentally change how we carry out molecular simulation. The suite of techniques and models collectively …
Understanding and predicting molecular responses in single cells upon chemical, genetic or mechanical perturbations is a core question in biology. Obtaining single-cell measurements …
Learning the continuous dynamics of a system from snapshots of its temporal marginals is a problem which appears throughout natural sciences and machine learning, including in …
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 …
Uncertainty quantification is crucial for the deployment of image restoration models in safety- critical domains, like autonomous driving and biological imaging. To date, methods for …
Diffusion models are powerful generative models that map noise to data using stochastic processes. However, for many applications such as image editing, the model input comes …