Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models

Xuran MA, Yexin LIU, Yaofu LIU, Xianfeng WU, Mingzhe ZHENG, Zihao WANG, Ser-Nam LIM*, Chao YANG*

*Corresponding author for this work

Research output: Contribution to conferenceConference Paperpeer-review

Original languageEnglish
Publication statusPublished - Oct 2025
EventInternational Conference on Computer Vision (ICCV 2025) -
Duration: 1 Oct 20251 Oct 2025

Conference

ConferenceInternational Conference on Computer Vision (ICCV 2025)
Period1/10/251/10/25

Cite this