arXiv AI
The Golden Path Hypothesis: Reusable Schedules in Diffusion Caching
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 22
SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
arXiv:2602.24208v2 Announce Type: replace-cross Abstract: Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequenti...
Hugging Face Trending Papers
Jul 26
OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models
High-resolution image and video diffusion models, including SD3, FLUX, and recent video diffusion transformers, have substantially improved generative quality but remain expensive at inference time because they repeatedly evaluate attention-heavy denoisers over many sampling steps. We address this inefficiency by exploiting redundancy in intermediate diffusion features rather than changing model weights or retraining.
arXiv AI
Aug 14
From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
arXiv:2608. 13043v1 Announce Type: new Abstract: Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead.
arXiv Machine Learning
Aug 3
OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference
arXiv:2607. 29398v1 Announce Type: new Abstract: Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising.
arXiv AI
Sep 1
EpaCache: Error-Propagation-Aware Caching for Accelerating Diffusion-Based Visual Generation
arXiv:2608.29264v1 Announce Type: new Abstract: Diffusion-based visual generative models deliver strong image and video synthesis quality but incur high inference costs because sequential samplers re...
arXiv AI
Jul 1
OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models
arXiv:2606. 31026v1 Announce Type: cross Abstract: We propose OTCache, a training-free framework for accelerating diffusion sampling via caching schedule prediction.