Recently, contrastive multi-view clustering (MvC) has emerged as a promising avenue for analyzing data from heterogeneous sources, typically leveraging the off-the-shelf instances as positives and randomly sampled ones as negatives. In practice, however, this paradigm would unavoidably suffer from the Dual Noisy Correspondence (DNC) problem, where noise compromises the constructions of both positive and negative pairs.

Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice.

We further propose a federated natural actor critic (NAC) method for multi-task RL with function approximation and stochastic policy evaluation, and establish its finite-time sample complexity taking the errors of function approximation into account.

The Rashomon effect is a mixed blessing in responsible machine learning.

MLaaS are limited by their reliance on training samples or white-box model analysis, highlighting the need for a black-box backdoor purification method.