High-throughput single-cell profiling provides an unprecedented ability to uncover the
molecular states of millions of cells. These technologies are, however, destructive to cells …

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 …

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 …