Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration
Published in In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference, 2025
Recommended citation: Haipeng Fang, Sheng Tang, Juan Cao, Enshuo Zhang, Fan Tang, Tong-Yee Lee; "Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference, 2025.
Download Bibtex