Deep neural networks excel in supervised learning tasks but are constrained by the need for
extensive labeled data. Self-supervised learning emerges as a promising alternative …

Unsupervised representation learning approaches aim to learn discriminative feature
representations from unlabeled data, without the requirement of annotating every sample …

In this paper, we contend that the objective of representation learning is to compress and
transform the distribution of the data, say sets of tokens, towards a mixture of low …

Abstract Masked Image Modeling (MIM) achieves outstanding success in self-supervised
representation learning. Unfortunately, MIM models typically have huge computational …

In a wide range of multimodal tasks, contrastive learning has become a particularly
appealing approach since it can successfully learn representations from abundant …

Unsupervised multiplex graph representation learning (UMGRL) has received increasing
interest, but few works simultaneously focused on the common and private information …

Temporal modeling is crucial for various video learning tasks. Most recent approaches
employ either factorized (2D+ 1D) or joint (3D) spatial-temporal operations to extract …

Recently, finetuning pretrained vision-language models (VLMs) has been a prevailing
paradigm for achieving state-of-the-art performance in VQA. However, as VLMs scale, it …

Recently, numerous studies have demonstrated the effectiveness of contrastive learning
(CL), which learns feature representations by pulling in positive samples while pushing …

The success of graph neural networks (GNNs) provokes the question about
explainability:“Which fraction of the input graph is the most determinant of the prediction?” …