Preprint
Aug 2026
LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching
LinCa decomposes cached features into sub-components with distinct continuity properties via a lightweight invertible network and applies differentiated prediction orders matched to each component, forming a unified Decompose-Predict-Reconstruct pipeline.
Jin-Shan Liu, Hao-Ran Qin, Xiao-Bing Tu et al.
· 0 citations