research
∙
06/26/2023
Restart Sampling for Improving Generative Processes
Generative processes that involve solving differential equations, such a...
share
research
∙
04/05/2023
GenPhys: From Physical Processes to Generative Models
Since diffusion models (DM) and the more recent Poisson flow generative ...
research
∙
02/08/2023
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
We introduce a new family of physics-inspired generative models termed P...
research
∙
02/01/2023
Stable Target Field for Reduced Variance Score Estimation in Diffusion Models
Diffusion models generate samples by reversing a fixed forward diffusion...
research
∙
09/22/2022
Poisson Flow Generative Models
We propose a new "Poisson flow" generative model (PFGM) that maps a unif...
research
∙
01/27/2022
Controlling Directions Orthogonal to a Classifier
We propose to identify directions invariant to a given classifier so tha...
research
∙
11/14/2021
Color Mapping Functions For HDR Panorama Imaging: Weighted Histogram Averaging
It is challenging to stitch multiple images with different exposures due...
research
∙
11/14/2021
Deep Joint Demosaicing and High Dynamic Range Imaging within a Single Shot
Spatially varying exposure (SVE) is a promising choice for high-dynamic-...
research
∙
10/19/2021
Learning Representations that Support Robust Transfer of Predictors
Ensuring generalization to unseen environments remains a challenge. Doma...
research
∙
06/05/2021
Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?
Can models with particular structure avoid being biased towards spurious...
research
∙
07/14/2020
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
Fusing data from multiple modalities provides more information to train ...
research
∙
02/25/2020
A Theory of Usable Information Under Computational Constraints
We propose a new framework for reasoning about information in complex sy...
research
∙
09/08/2019
L_DMI: An Information-theoretic Noise-robust Loss Function
Accurately annotating large scale dataset is notoriously expensive both ...
research
∙
05/31/2019