Chun-Guang Li

Learning Deep Modality-Shared Self-Expressiveness for Image Clustering with Textual Information

DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD

Multi-Modal Representation Learning via Semi-Supervised Rate Reduction for Generalized Category Discovery

Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few

Taming Transformer Without Using Learning Rate Warmup

Exploring a Principled Framework for Deep Subspace Clustering

Stable-Transformer: Towards a Stable Transformer Training