Diffusion models have achieved remarkable success in image and video generation tasks. However, the high computational demands of Diffusion Transformers (DiTs) pose a significant challenge to their practical deployment. While feature caching is a promising acceleration strategy, existing methods based on simple reusing or training-free forecasting struggle to adapt to the complex, stage-dependent dynamics of the diffusion process, often resulting in quality degradation and failing to maintain consistency with the standard denoising process. To address this, we propose a LEarnable Stage-Aware (LESA) predictor framework based on two-stage training. Our approach leverages a Kolmogorov-Arnold Network (KAN) to accurately learn temporal feature mappings from data. We further introduce a multi-stage, multi-expert architecture that assigns specialized predictors to different noise-level stages, enabling more precise and robust feature forecasting. Extensive experiments show our method achieves significant acceleration while maintaining high-fidelity generation. Experiments demonstrate 5.00x acceleration on FLUX.1-dev with minimal quality degradation (1.0% drop), 6.25x speedup on Qwen-Image with a 20.2% quality improvement over the previous SOTA (TaylorSeer), and 5.00x acceleration on HunyuanVideo with a 24.7% PSNR improvement over TaylorSeer. State-of-the-art performance on both text-to-image and text-to-video synthesis validates the effectiveness and generalization capability of our training-based framework across different models. Our code is available at https://github.com/caipeiliang2004/LESA.
Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
Shanghai Jiao Tong University(上海交通大学);University of Electronic Science and Technology of China(电子科技大学);Shandong University(山东大学);Xiamen University(厦门大学);Fudan University(复旦大学)
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)
MotionTrack: Learning Motion Predictor for Multiple Object Tracking
School of Computer Science, National University of Defense Technology(国防科技大学计算机学院);JD Explore Academy(京东探索研究院);Meituan Inc.(美团公司);Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology(国防科技大学前沿装备数字化软件实验室)
Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence
Institute of Robotics, Athena Research Center(机器人研究所,雅典研究中心);School of ECE, NTUA(电子工程学院,NTUA);HERON – Hellenic Robotics Center of Excellence(希腊机器人 excellence 中心);MPI for Intelligent Systems(智能系统研究所);ETH Zurich(苏黎世联邦理工学院);Google(谷歌)
Improved Prognostic Prediction of Pancreatic Cancer Using Multi-Phase CT by Integrating Neural Distance and Texture-Aware Transformer
DAMO Academy, Alibaba Group(阿里巴巴集团达摩院);Peking University(北京大学);Hupan Lab(湖畔实验室);Sun Yat-sen University Cancer Center(中山大学肿瘤防治中心);South China Hospital, Shenzhen University(深圳大学华南医院);Tianjin Medical University Cancer Institute and Hospital(天津医科大学肿瘤医院);Changsha Institute for Computing and Digital Economy(长沙计算与数字经济研究院);Guangdong Provincial People’s Hospital(广东省人民医院);Shengjing Hospital(盛京医院)