Diffusion-based image super-resolution (SR) methods are mainly limited by the low
inference speed due to the requirements of hundreds or even thousands of sampling steps …

Deep generative models have unlocked another profound realm of human creativity. By
capturing and generalizing patterns within data, we have entered the epoch of all …

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 …

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

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 …

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 …

Simulation-free methods for training continuous-time generative models construct probability
paths that go between noise distributions and individual data samples. Recent works, such …

Achieving machine autonomy and human control often represent divergent objectives in the
design of interactive AI systems. Visual generative foundation models such as Stable …

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 …