Diffusion models: A comprehensive survey of methods and applications
Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …
record-breaking performance in many applications, including image synthesis, video …
A survey on generative diffusion models
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 …
capturing and generalizing patterns within data, we have entered the epoch of all …
Diffusion Schrödinger bridge matching
Solving transport problems, ie finding a map transporting one given distribution to another,
has numerous applications in machine learning. Novel mass transport methods motivated …
has numerous applications in machine learning. Novel mass transport methods motivated …
Convergence of denoising diffusion models under the manifold hypothesis
V De Bortoli - arXiv preprint arXiv:2208.05314, 2022 - arxiv.org
Denoising diffusion models are a recent class of generative models exhibiting state-of-the-
art performance in image and audio synthesis. Such models approximate the time-reversal …
art performance in image and audio synthesis. Such models approximate the time-reversal …
Aligned diffusion Schrödinger bridges
Diffusion Schrödinger bridges (DSBs) have recently emerged as a powerful framework for
recovering stochastic dynamics via their marginal observations at different time points …
recovering stochastic dynamics via their marginal observations at different time points …
Score-based diffusion meets annealed importance sampling
More than twenty years after its introduction, Annealed Importance Sampling (AIS) remains
one of the most effective methods for marginal likelihood estimation. It relies on a sequence …
one of the most effective methods for marginal likelihood estimation. It relies on a sequence …
Denoising diffusion bridge models
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 …
processes. However, for many applications such as image editing, the model input comes …
The schrödinger bridge between gaussian measures has a closed form
The static optimal transport $(\mathrm {OT}) $ problem between Gaussians seeks to recover
an optimal map, or more generally a coupling, to morph a Gaussian into another. It has been …
an optimal map, or more generally a coupling, to morph a Gaussian into another. It has been …
Diffusion Models in De Novo Drug Design
Diffusion models have emerged as powerful tools for molecular generation, particularly in
the context of 3D molecular structures. Inspired by nonequilibrium statistical physics, these …
the context of 3D molecular structures. Inspired by nonequilibrium statistical physics, these …
Generative modeling with phase stochastic bridges
Diffusion models (DMs) represent state-of-the-art generative models for continuous inputs.
DMs work by constructing a Stochastic Differential Equation (SDE) in the input space (ie …
DMs work by constructing a Stochastic Differential Equation (SDE) in the input space (ie …