5 papers
Diffusion Classifiers Understand Compositionality, but Conditions Apply
Yujin Jeong, Arnas Uselis, Seong Joon Oh +1
Understanding visual scenes is fundamental to human intelligence. While discriminative models have significantly advanced computer vision, they often struggle with compositional un…
Optimal Empirical Risk Minimization under Temporal Distribution Shifts
Yujin Jeong, Ramesh Johari, Dominik Rothenhäusler +1
Temporal distribution shifts pose a key challenge for machine learning models trained and deployed in dynamically evolving environments. This paper introduces RIDER (RIsk minimizat…
Out-of-distribution generalization under random, dense distributional shifts
Yujin Jeong, Dominik Rothenhäusler
Many existing approaches for estimating parameters in settings with distributional shifts operate under an invariance assumption. For example, under covariate shift, it is assumed…
Read, Watch and Scream! Sound Generation from Text and Video
Yujin Jeong, Yunji Kim, Sanghyuk Chun +1
Despite the impressive progress of multimodal generative models, video-to-audio generation still suffers from limited performance and limits the flexibility to prioritize sound syn…
Identifying sparse treatment effects in high-dimensional outcome spaces
Yujin Jeong, Emily Fox, Ramesh Johari
Based on technological advances in sensing modalities, randomized trials with primary outcomes represented as high-dimensional vectors have become increasingly prevalent. For examp…