Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers

Pengtao Chen, Xianfang Zeng, Maosen Zhao, Mingzhu Shen, Wei Cheng, Gang Yu 0002, Tao Chen 0003. Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers. In Sven Koenig, Chad Jenkins, Matthew E. Taylor, editors, Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2026, Singapore, January 20-27, 2026. pages 2957-2965, AAAI Press, 2026. [doi]

Abstract

Abstract is missing.