2 papers
cs.CV2026
Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V
Junhao Wu, Dezhong Yao, Hai Jin
W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges: sparse large-magnitude activation outliers, and st…
cs.LG2025
FedMHO: Heterogeneous One-Shot Federated Learning Towards Resource-Constrained Edge Devices
Dezhong Yao, Yuexin Shi, Tongtong Liu +1
Federated Learning (FL) is increasingly adopted in edge computing scenarios, where a large number of heterogeneous clients operate under constrained or sufficient resources. The it…