# Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching

arXiv: https://arxiv.org/abs/2604.22901 · HTML: https://mlsanity.com/paper/2604.22901/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding](https://mlsanity.com/paper/2505.22618/) (2025)
- [Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2101.12072/) (2021)
- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [A Survey on Generative Diffusion Model](https://mlsanity.com/paper/2209.02646/) (2022)
- [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024)
- [Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching](https://mlsanity.com/paper/2406.01733/) (2024)
- [Wavelet Diffusion Models are fast and scalable Image Generators](https://mlsanity.com/paper/2211.16152/) (2022)
- [ECG Heartbeat Classification: A Deep Transferable Representation](https://mlsanity.com/paper/1805.00794/) (2018)
- [Diffusion Models for Time Series Applications: A Survey](https://mlsanity.com/paper/2305.00624/) (2023)
- [A Fourier Space Perspective on Diffusion Models](https://mlsanity.com/paper/2505.11278/) (2025)
- [Time Series Diffusion in the Frequency Domain](https://mlsanity.com/paper/2402.05933/) (2024)
- [FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation](https://mlsanity.com/paper/2505.20353/) (2025)
- [FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching](https://mlsanity.com/paper/2510.08669/) (2025)
- [Accelerating Diffusion Transformer via Error-Optimized Cache](https://mlsanity.com/paper/2501.19243/) (2025)
- [TinyServe: Query-Aware Cache Selection for Efficient LLM Serving](https://mlsanity.com/paper/2509.12211/) (2025)
- [CXL-SpecKV: A Disaggregated FPGA Speculative KV-Cache for Datacenter LLM Serving](https://mlsanity.com/paper/2512.11920/) (2025)
- [MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning](https://mlsanity.com/paper/2603.20586/) (2026)
- [HSGM: Hierarchical Segment-Graph Memory for Scalable Long-Text Semantics](https://mlsanity.com/paper/2509.18168/) (2025)
- [WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation](https://mlsanity.com/paper/2510.11839/) (2025)
- [AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers](https://mlsanity.com/paper/2602.13357/) (2026)

## Built on by (most cited first, 1 of 1)

- [HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers](https://mlsanity.com/paper/2608.07616/) (2026)

## Abstract (arXiv)

Diffusion models achieve remarkable success in time series generation. However, slow inference limits their practical deployment. We propose E2-CRF (Error-Feedback Event-Driven Cumulative Residual Feature caching) to accelerate frequency domain diffusion models. Our method exploits two structural properties: (1) spectral localization, where signal energy concentrates in low frequencies, and (2) mirror symmetry, which halves the effective frequency dimension. E2-CRF uses a closed-loop error-feedback system that adaptively caches transformer KV features across diffusion steps. We trigger recomputation using event-driven residual dynamics instead of fixed schedules. Our method selectively recomputes high-energy or rapidly-changing tokens while reusing cached features for stable high-frequency components. E2-CRF achieves ~2.2 speedup while maintaining sample quality. We demonstrate effectiveness on 5 datasets. Our caching strategy naturally aligns with the diffusion process's structure-to-detail progression. We include sufficient-condition error and complexity bounds under standard regularity assumptions (Appendix), alongside empirical validation. Our code is available at https://github.com/NoakLiu/FastFourierDiffusion and is also integrated in https://github.com/NoakLiu/FastCache-xDiT.