Diffusion Transformer (DiT) has emerged as a powerful model architecture for generating high-quality images and videos. In the case of video DiT, 3D Spatio-Temporal Attention increases token length in proportion to the number of frames, sharply increasing computational cost. Token reduction methods mitigate this cost by exploiting spatial redundancy, but existing approaches rely on inaccurate similarity estimates and lightweight matching algorithms, resulting in poor matching quality and only marginal acceleration.
To overcome these limitations, we propose ORBIS, an SW-HW co-designed accelerator for video DiT. ORBIS leverages the output activation from the previous timestep to obtain more accurate inter-token similarity, substantially improving matching quality and enabling a higher token reduction ratio. We further introduce a Distribution-Aware Token Matching (DATM) algorithm that captures global token distribution and explicitly minimizes token-pair loss for additional gains. To fully hide DATM latency, we design specialized, deeply pipelined hardware and minimize its hardware cost through quantization, occupying only 2.4% of total area with negligible accuracy loss. Extensive experiments show that ORBIS achieves about 2x higher token reduction ratio than the state-of-the-art approach, AsymRnR, while delivering up to 4.5x speedup and 79.3% energy reduction compared to an NVIDIA A100 GPU.
Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；National Cheng-Kung University（国立成功大学）
针对 DiT 推理计算昂贵的问题，本文提出训练后即插即用的 SDTM，依据“先结构后细节”先验动态合并冗余视觉 token，实现 1.55 倍加速且几乎不损失图像质量。
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）
SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation
The University of Hong Kong（香港大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）；Peking University（北京大学）；xAI；Tsinghua University（清华大学）；Shanghai Jiao Tong University（上海交通大学）
Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
Shanghai Jiao Tong University（上海交通大学）；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）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Beihang University（北京航空航天大学）
Where and How to Prune: An Empirical Study of Visual Token Pruning for GUI Agent Navigation
Sichuan University（四川大学）；Sun Yat-sen University（中山大学）；Australian National University（澳大利亚国立大学）；Peking University（北京大学）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Jiao Tong University（上海交通大学）
XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（教育部多媒体可信感知与高效计算重点实验室，厦门大学）；Shandong Inspur Database Technology Co.,Ltd（山东浪潮数据库技术有限公司）
ApET: Approximation-Error Guided Token Compression for Efficient VLMs
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）；Peng Cheng Laboratory（鹏城实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Institute of Technology（哈尔滨工业大学）；Peking University（北京大学）
FastVGGT: Training-Free Acceleration of Visual Geometry Transformer
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）；AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院自动化实验室）
