"model sparsification" Papers
2 papers found
Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation
Youwei Zheng, Yuxi Ren, Xin Xia et al.
ICCV 2025posterarXiv:2510.09094
4
citations
Elastic ViTs from Pretrained Models without Retraining
Walter Simoncini, Michael Dorkenwald, Tijmen Blankevoort et al.
NeurIPS 2025posterarXiv:2510.17700