Fangcheng Fu

4

Papers

41

Total Citations

Papers (4)

Training-free and Adaptive Sparse Attention for Efficient Long Video Generation

NetMoE: Accelerating MoE Training through Dynamic Sample Placement

HaCore: Efficient Coreset Construction with Locality Sensitive Hashing for Vertical Federated Learning

Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference