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 …

We present rectified flow, a surprisingly simple approach to learning (neural) ordinary
differential equation (ODE) models to transport between two empirically observed …

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 …

We propose Image-to-Image Schr\" odinger Bridge (I $^ 2$ SB), a new class of conditional
diffusion models that directly learn the nonlinear diffusion processes between two given …

The past few years have witnessed the great success of Diffusion models~(DMs) in
generating high-fidelity samples in generative modeling tasks. A major limitation of the DM is …

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

Progressively applying Gaussian noise transforms complex data distributions to
approximately Gaussian. Reversing this dynamic defines a generative model. When the …

Common image-to-image translation methods rely on joint training over data from both
source and target domains. The training process requires concurrent access to both …

Score-based generative models (SGMs) are a powerful class of generative models that
exhibit remarkable empirical performance. Score-based generative modelling (SGM) …

AI-based molecule generation provides a promising approach to a large area of biomedical
sciences and engineering, such as antibody design, hydrolase engineering, or vaccine …