Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising process incurs substantial computational cost during inference. Existing caching methods accelerate DiTs by reusing intermediate computations across timesteps, but they share a common limitation: treating the denoising process as uniform across time,depth, and feature dimensions. In this work, we identify three orthogonal axes of non-uniformity in DiT denoising: (1) temporal -- sensitivity to caching errors varies dramatically across the denoising trajectory; (2) depth -- consecutive caching decisions lead to cascading approximation errors; and (3) feature -- different components of the hidden state exhibit heterogeneous temporal dynamics. Based on these observations, we propose SpectralCache, a unified caching framework comprising Timestep-Aware Dynamic Scheduling (TADS), Cumulative Error Budgets (CEB), and Frequency-Decomposed Caching (FDC). On FLUX.1-schnell at 512x512 resolution, SpectralCache achieves 2.46x speedup with LPIPS 0.217 and SSIM 0.727, outperforming TeaCache (2.12x, LPIPS 0.215, SSIM 0.734) by 16% in speed while maintaining comparable quality (LPIPS difference < 1%). Our approach is training-free, plug-and-play, and compatible with existing DiT architectures.
LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching
Shanghai Jiao Tong University（上海交通大学）；Shandong University（山东大学）；Terminal Intelligent Computing Division, Alibaba Cloud（阿里云终端智能计算事业部）；South China University of Technology（华南理工大学）；Jilin University（吉林大学）
LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching
Beijing Institute of Technology（北京理工大学）；Central South University（中南大学）；China University of Mining and Technology（中国矿业大学）；University of Electronic Science and Technology of China（电子科技大学）；Tsinghua University（清华大学）；Shanghai Jiaotong University（上海交通大学）
针对 MAR 双向自注意力无法使用传统 KV 缓存的问题，本文提出训练免费、即插即用的 LazyMAR，通过令牌与条件两类特征缓存实现 2.83 倍加速且几乎不损失生成质量。
Accelerating Diffusion Transformers with Token-wise Feature Caching
Shanghai Jiao Tong University（上海交通大学）；University of Electronic Science & Technology of China（电子科技大学）；Sichuan University（四川大学）；National University of Defense Technology（国防科技大学）；Zhejiang University（浙江大学）
针对 Diffusion Transformer 计算成本高的问题，提出逐 token 自适应特征缓存，并按层类型与深度设置缓存比例，在 PixArt-α、OpenSora 和 DiT 上免训练实现近无损加速。
Shanghai Jiao Tong University（上海交通大学）；South China University of Technology（南方科技大学）；Beihang University（北航）；Huawei Technologies Ltd（华为技术有限公司）；Shanghai AI Lab（上海人工智能实验室）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
Shanghai Jiao Tong University（上海交通大学）；South China University of Technology（华南理工大学）；Fudan University（复旦大学）；Tsinghua University（清华大学）；Hong Kong University of Science and Technology（香港科技大学）
BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China（人工智能学院，北京师范大学，北京）；Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai 519087, China（人工智能与未来网络研究院，北京师范大学，珠海）
MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference
Data Science & Artificial Intelligence Research Institute, China Unicom（中国unicom数据科学与人工智能研究 institute）；Unicom Data Intelligence, China Unicom（中国unicom数据智能）；National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）
From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
Shanghai Jiao Tong University（上海交通大学）；Shandong University（山东大学）；University of Electronic Science and Technology of China（电子科技大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
Shanghai Jiao Tong University（上海交通大学）；Shandong University（山东大学）；University of Electronic Science and Technology of China（电子科学与技术大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Tsinghua University（清华大学）；National University of Singapore（新加坡国立大学）
Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization
Department of Computer Science, North Carolina State University（北卡罗来纳州立大学计算机科学系）；National Center for Computational Science, Oak Ridge National Lab（橡树岭国家实验室计算科学中心）；Department of Mechanical Engineering, Keio University（庆应大学机械工程系）
Forecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated Taylor
School of Computer Science, Wuhan University（武汉大学计算机学院）；PaddlePaddle Team, Baidu Inc（百度公司PaddlePaddle团队）；International Joint Innovation Center, The Electromagnetics Academy at Zhejiang University（浙江大学电磁学学院国际联合创新中心）；Yunnan Key Laboratory of Media Convergence（云南媒体融合重点实验室）
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（中国教育部多媒体可信感知与高效计算重点实验室，厦门大学）；ByteDance（字节跳动）
HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration
iComAI Lab, Hong Kong University of Science and Technology（香港科技大学iComAI实验室）；SenseTime Research（商汤科技研究院）；SCSE, Beihang University（北京航空航天大学SCSE）；IAI, Beihang University（北京航空航天大学IAI）；SKLCCSE, Beihang University（北京航空航天大学SKLCCSE）；ZIP Lab, Monash University（墨尔本大学ZIP实验室）
Token Caching for Diffusion Transformer Acceleration
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所）；School of Information and Electronic Engineering, Shandong Technology and Business University（山东科技职业大学信息与电子工程学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；PeopleAl, Inc.（PeopleAl公司）；School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）；Terminal Technology Department, Alipay, Ant Group（蚂蚁集团支付宝终端技术部）
