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 …

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

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 …

Solving transport problems, ie finding a map transporting one given distribution to another,
has numerous applications in machine learning. Novel mass transport methods motivated …

Abstract Despite Flow Matching and diffusion models having emerged as powerful
generative paradigms for continuous variables such as images and videos, their application …

Normalizing flows are a class of deep generative models that are especially interesting for
modeling probability distributions in physics, where the exact likelihood of flows allows …

The biological functions of proteins often depend on dynamic structural ensembles. In this
work, we develop a flow-based generative modeling approach for learning and sampling the …

The generation of 3D molecules requires simultaneously deciding the categorical features
(atom types) and continuous features (atom coordinates). Deep generative models …

Abstract We present Piecewise Rectified Flow (PeRFlow), a flow-based method for
accelerating diffusion models. PeRFlow divides the sampling process of generative flows …

We present FrameFlow, a method for fast protein backbone generation using SE (3) flow
matching. Specifically, we adapt FrameDiff, a state-of-the-art diffusion model, to the flow …