# FEB-Cache: Frequency-Guided Exposure Bias Reduction for Enhancing Diffusion Transformer Caching

arXiv: https://arxiv.org/abs/2503.07120 · HTML: https://mlsanity.com/paper/2503.07120/

## Key facts

- Cited by 2 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 63 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Placed in

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

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

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Fast Sampling of Diffusion Models with Exponential Integrator](https://mlsanity.com/paper/2204.13902/) (2022)
- [Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.06503/) (2022)
- [PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://mlsanity.com/paper/2403.04692/) (2024)
- [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021)
- [Mixture-of-Depths: Dynamically allocating compute in transformer-based language models](https://mlsanity.com/paper/2404.02258/) (2024)
- [Structural Pruning for Diffusion Models](https://mlsanity.com/paper/2305.10924/) (2023)
- [Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers](https://mlsanity.com/paper/2406.01125/) (2024)
- [Accelerating Diffusion Transformers with Token-wise Feature Caching](https://mlsanity.com/paper/2410.05317/) (2024)
- [Real-Time Video Generation with Pyramid Attention Broadcast](https://mlsanity.com/paper/2408.12588/) (2024)
- [Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching](https://mlsanity.com/paper/2406.01733/) (2024)
- [FORA: Fast-Forward Caching in Diffusion Transformer Acceleration](https://mlsanity.com/paper/2407.01425/) (2024)
- [DiTFastAttn: Attention Compression for Diffusion Transformer Models](https://mlsanity.com/paper/2406.08552/) (2024)
- [FiT: Flexible Vision Transformer for Diffusion Model](https://mlsanity.com/paper/2402.12376/) (2024)
- [Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps](https://mlsanity.com/paper/2305.15583/) (2023)
- [Progressive Distillation for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2202.00512/) (2022)
- [LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models](https://mlsanity.com/paper/2404.11098/) (2024)
- [Improved Noise Schedule for Diffusion Training](https://mlsanity.com/paper/2407.03297/) (2024)
- [Token Caching for Diffusion Transformer Acceleration](https://mlsanity.com/paper/2409.18523/) (2024)
- [Denoising Task Difficulty-based Curriculum for Training Diffusion Models](https://mlsanity.com/paper/2403.10348/) (2024)
- [DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing](https://mlsanity.com/paper/2409.07756/) (2024)
- [Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models](https://mlsanity.com/paper/2312.13307/) (2023)
- [Mitigating Exposure Bias in Discriminator Guided Diffusion Models](https://mlsanity.com/paper/2311.11164/) (2023)

## Built on by (most cited first, 2 of 2)

- [A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation](https://mlsanity.com/paper/2510.19755/) (2025)
- [SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models](https://mlsanity.com/paper/2602.18993/) (2026)

## Abstract (arXiv)

Diffusion Transformer (DiT) has exhibited impressive generation capabilities but faces great challenges due to its high computational complexity. To address this issue, various methods, notably feature caching, have been introduced. However, these approaches focus on aligning non-cache diffusion without analyzing why caching damage the generation processes. In this paper, we first confirm that the cache greatly amplifies the exposure bias, resulting in a decline in the generation quality. However, directly applying noise scaling is challenging for this issue due to the non-smoothness of exposure bias. We found that this phenomenon stems from the mismatch between its frequency response characteristics and the simple cache of Attention and MLP. Since these two components exhibit unique preferences for frequency signals, which provides us with a caching strategy to separate Attention and MLP to achieve an enhanced fit of exposure bias and reduce it. Based on this, we introduced FEB-Cache, a joint caching strategy that aligns with the non-exposed bias diffusion process (which gives us a higher performance cap) of caching Attention and MLP based on the frequency-guided cache table. Our approach combines a comprehensive understanding of the caching mechanism and offers a new perspective on leveraging caching to accelerate the diffusion process. Empirical results indicate that FEB-Cache optimizes model performance while concurrently facilitating acceleration. Code is available at https://github.com/aSleepyTree/EB-Cache.