# CalibAtt：无需训练的稀疏注意力方法，将文生视频速度提升至 1.58 倍

- 来源：Apple Machine Learning Research（RSS）
- 发布时间：2026-07-21 08:00
- AIHOT 分数：55
- AIHOT 链接：https://aihot.virxact.com/items/cmruw1v74005vbiymxxxmhf22
- 原文链接：https://machinelearning.apple.com/research/calibrated-sparse-attention

## AI 摘要

Apple 与特拉维夫大学联合提出 CalibAtt，一种无需训练的校准稀疏注意力方法，通过离线识别 token 间可跳过的低分连接并编译为优化操作，在推理时跳过无关计算。在 Wan 2.1 14B、Mochi 1 及少步蒸馏模型上，CalibAtt 实现最高 1.58 倍端到端加速，在保持视频质量和文本-视频对齐的同时优于现有免训练方法。

## 正文

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

Related readings and updates.

VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization

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…

STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows

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…

Discover opportunities in Machine Learning.