research
∙
06/13/2023
Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training
The surge in multimodal AI's success has sparked concerns over data priv...
share
research
∙
02/13/2023
Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data
Language-supervised vision models have recently attracted great attentio...
research
∙
10/06/2021
The Power of Contrast for Feature Learning: A Theoretical Analysis
Contrastive learning has achieved state-of-the-art performance in variou...
research
∙
02/28/2021
Asymptotic Risk of Overparameterized Likelihood Models: Double Descent Theory for Deep Neural Networks
We investigate the asymptotic risk of a general class of overparameteriz...
research
∙
07/04/2019