mlsanityData to 7 Oct 2026

Accelerating Diffusion Transformer via Error-Optimized Cache

arXiv 2501.19243 ↗First posted 31 Jan 2025cs.CVcited by 14

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion Transformer (DiT) is a crucial method for content generation. However, it needs a lot of time to sample. Many studies have attempted to use caching to reduce the time consumption of sampling. Existing caching methods accelerate generation by reusing DiT features from the previous time step and skipping calculations in the next, but they tend to locate and cache low-error modules without focusing on reducing caching-induced errors, resulting in a sharp decline in generated content quality when increasing caching intensity. To solve this problem, we propose the Error-Optimized Cache (EOC). This method introduces three key improvements: (1) Prior knowledge extraction: Extract and process the caching differences; (2) A judgment method for cache optimization: Determine whether certain caching steps need to be optimized; (3) Cache optimization: reduce caching errors. Experiments show that this algorithm significantly reduces the error accumulation caused by caching, especially excessive caching. On the ImageNet dataset, without substantially increasing the computational load, this method improves the FID of the generated images when the rule-based model FORA has a caching level of 75%, 50%, and 25%, and the training-based model Learning-to-cache has a caching level of 22%. Specifically, the FID values change from 30.454 to 21.690 (28.8%), from 6.857 to 5.821 (15.1%), from 3.870 to 3.692 (4.6%), and from 3.539 to 3.451 (2.5%) respectively. Code is available at https://github.com/qiujx0520/EOCMM2025.git.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 7 of its 11 references that are in the map. First posted on arXiv 31 Jan 2025.

Builds on

7 of 11 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models16 Dec
  2. 2024Relational Diffusion Distillation for Efficient Image Generation10 Oct
  3. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun

Other references · 4

  1. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  2. 2024Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correctingcited by 26
  3. 2024Selective Vision-Language Subspace Projection for Few-shot CLIPcited by 18
  4. 2024Boosting Few-Shot Learning via Attentive Feature Regularizationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 6.

14 papers.

Sort:

By area:

  1. 2025From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeerscited by 124
  2. 2025SpeCa: Accelerating Diffusion Transformers with Speculative Feature Cachingcited by 27
  3. 2025FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximationcited by 23
  4. 2025FreqCa: Accelerating Diffusion Models via Frequency-Aware Cachingcited by 16
  5. 2025Accelerating Diffusion Transformer via Gradient-Optimized Cachecited by 15
  6. 2025Enhancing CLIP Robustness via Cross-Modality Alignmentcited by 14
  7. 2025Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Modelcited by 5
  8. 2025Hierarchical Semantic Alignment for Image Clusteringcited by 5
  9. 2026DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Cachingcited by 4
  10. 2026Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Modelcited by 2
  11. 2026DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsitycited by 2
  12. 2026Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Cachingcited by 1
2 more
  1. 2026BeCARE: Budgeted Cache Refresh for Diffusion Transformer Accelerationcited by 1
  2. 2026Accelerating Masked Image Generation by Learning Controlled Latent Dynamicscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Accelerating Diffusion Transformer via Increment-Calibrated Caching with Channel-Aware Singular Value Decomposition
  2. 2024FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
  3. 2026Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection
  4. 2024Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
  5. 2025FEB-Cache: Frequency-Guided Exposure Bias Reduction for Enhancing Diffusion Transformer Caching
  6. 2025Plug-and-Play Fidelity Optimization for Diffusion Transformer Acceleration via Cumulative Error Minimization
  7. 2024Token Caching for Diffusion Transformer Acceleration
  8. 2026Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers