Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers

20 May 2025

Papers citing "Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers"

6 / 6 papers shown

Title
DiCache: Let Diffusion Model Determine Its Own Cache Jiazi Bu Pengyang Ling Yujie Zhou Yibin Wang Yuhang Zang Tong Wu Dahua Lin Yuan Liu DiffM 28 1 0 24 Aug 2025
ReVision: High-Quality, Low-Cost Video Generation with Explicit 3D Physics Modeling for Complex Motion and Interaction Qihao Liu Ju He Qihang Yu Liang-Chieh Chen Alan Yuille DiffM VGen 270 1 0 30 Apr 2025
Deeply Supervised Flow-Based Generative Models Inkyu Shin Chenglin Yang Liang-Chieh Chen 140 3 0 18 Mar 2025
FlowTok: Flowing Seamlessly Across Text and Image Tokens Ju He Qihang Yu Qihao Liu Liang-Chieh Chen 256 5 0 13 Mar 2025
Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation Sucheng Ren Qihang Yu Ju He Xiaohui Shen Alan Yuille Liang-Chieh Chen VGen 328 19 0 27 Feb 2025
Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens Dongwon Kim Ju He Qihang Yu Chenglin Yang Xiaohui Shen Suha Kwak Liang-Chieh Chen VLM 218 16 0 13 Jan 2025