Weidong Cai

6

Papers

74

Total Citations

Papers (6)

V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models

VRM: Knowledge Distillation via Virtual Relation Matching

CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination

PaintHuman: Towards High-Fidelity Text-to-3D Human Texturing via Denoised Score Distillation

Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling

Device-Wise Federated Network Pruning