Accelerating Text-to-Video Generation with Calibrated Sparse Attention
This paper introduces CalibAtt, a training-free sparse attention method that identifies stable sparsity patterns via offline calibration, skips unimportant connections at inference, achieving up to 1.58× end-to-end speedup without sacrificing video quality.
content type paperpublished July 2026
Accelerating Text-to-Video Generation with Calibrated Sparse Attention
AuthorsShai Yehezkel†**, Shahar Yadin, Noam Elata, Yaron Ostrovsky-Berman, Bahjat Kawar
View publication
Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In this paper, we identify that a significant fraction of token-to-token connections consistently yield negligible scores across various inputs, and their patterns often repeat across queries. Thus, the attention computation in these cases can be skipped with little to no effect on the result. This observation continues to hold for connections among local token blocks. Motivated by this, we introduce CalibAtt, a training-free method that accelerates video generation via calibrated sparse attention. CalibAtt performs an offline calibration pass that identifies block-level sparsity and repetition patterns that are stable across inputs, and compiles these patterns into optimized attention operations for each layer, head, and diffusion timestep. At inference time, we compute the selected input-dependent connections densely, and skip the unselected ones in a hardware-efficient manner. Extensive experiments on Wan 2.1 14B, Mochi 1, and few-step distilled models at various resolutions show that CalibAtt achieves up to 1.58× end-to-end speedup, outperforming existing training-free methods while maintaining video generation quality and text-video alignment.
† Tel Aviv University
** Work done while at Apple
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
July 2, 2026research area Computer Visionconference ICML
Visual tokenizers map high-dimensional raw pixels into a compressed representation for downstream modeling. Beyond compression, tokenizers dictate what information is preserved and how it is organized. A de facto standard approach to video tokenization is to represent a video as a spatiotemporal 3D grid of tokens, each capturing the corresponding local information in the original signal. This requires the downstream model that consumes the…
Read more
STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows
April 30, 2026research area Computer Vision, research area Methods and Algorithmsconference CVPR
Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where spatiotemporal complexity and computational cost are substantially higher, state-of-the-art systems almost exclusively rely on diffusion-based models. In this work, we revisit this design space by presenting STARFlow-V, a…
Read more