Junping Zhang

Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition

Revisiting Block-wise Interactions of MMDiT for Training-free Improved Synthesis

InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention

GMV: A Unified and Efficient Graph Multi-View Learning Framework

PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering