KalmanCache+: Uncertainty-Aware Closed-Loop Diffusion Caching via Predict–Trust–Correct Residual Estimation

Diffusion transformers (DiTs) achieve high-fidelity visual generation but incur substantial inference costs from repeated block evaluations across denoising steps. Training-free caching mitigates these costs through feature or residual reuse, yet fixed schedules, local proxies, and model-specific calibration provide limited control over cache reliability and accumulated skip errors. We introduce KalmanCache+, an uncertainty-aware closed-loop framework that formulates diffusion caching as sequential residual estimation. A lightweight channel-wise Kalman filter predicts residual evolution and uses predictive uncertainty to choose between FULL computation and SKIP. Prediction errors observed at FULL steps refine subsequent decisions and residual reconstructions during SKIP steps. This Predict–Trust–Correct cycle adapts online to each sampling run without modifying pretrained weights or requiring calibration tables. Across image and video DiTs, KalmanCache+ achieves latency speedups of $1.91\times$ on DiT-XL/2 (FID 2.241 vs. 2.282 for full computation), $3.10\times$ on FLUX.1-dev (LPIPS 0.199 vs. 0.368 for step reduction at $2.88\times$), and $2.13\times$ on Wan2.1-1.3B (PSNR 29.55 vs. 23.16 dB for TeaCache at $2.05\times$).