Chaoqi Chen

ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMs

Bures-Isotropy Alignment: Manifold Learning of Generalized Category Discovery

3D Shape Generation via Tri-Vectors: a Parsimonious Representation

Gestalt Generalized Category Discovery

MTMC: Generalized Category Discovery via Maximum Token Manifold Capacity

SlotSAM: Bootstrap Segmentation Foundation Model under Real-world Shifts via Object-Centric Learning