提出稀疏注意力机制，让视频编辑模型提速60%且画质几乎不变。
LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
- 通过筛选低重要性上下文和动态分组查询，实现高效稀疏计算。
- 在三大评测集上超越现有方法，注意力模块延迟降低约60%。
- 适合追求高速视频编辑且不牺牲画质的研究者与开发者。
视频编辑正朝上下文学习（ICL）范式发展，但随之而来的二次复杂度注意力开销构成关键计算瓶颈。本文提出针对ICL视频编辑的首个近无损稀疏框架——上下文稀疏注意力（ISA）。设计基于两大洞察：其一，上下文令牌显著低于源令牌的重要程度；其二，理论证明并实证验证了查询锐度与近似误差相关。据此，ISA采用预筛选策略剔除冗余上下文，并引入动态查询分组机制，将高误差查询导向全注意力，低误差查询则交由计算高效的零阶泰勒稀疏注意力处理。此外，我们构建了基于ISA的新型闪电视频编辑模型 extbf{ exttt{LIVEditor-14B}}，并开发了一个精心筛选的170万条高质量视频编辑数据集。大量实验表明，LIVEditor-14B在注意力模块延迟上实现约60%的降低，同时在EditVerseBench、IVE-Bench和VIE-Bench三大评测集上超越现有方法，实现近乎无损加速且不损失视觉质量。
原文摘要 · Abstract (English)
Video editing has evolved toward In-Context Learning (ICL) paradigms, yet the resulting quadratic attention costs create a critical computational bottleneck. In this work, we propose In-context Sparse Attention (ISA), the first near-lossless empirical sparse framework tailored for ICL video editing. Our design is grounded in two key insights: first, context tokens exhibit significantly lower saliency than source tokens; second, we theoretically prove and empirically validate that Query sharpness correlates with approximation error. Motivated by these findings, ISA implements an efficient pre-selection strategy to prune redundant context, followed by a dynamic query grouping mechanism that routes high-error queries to full attention and low-error ones to a computationally efficient 0-th order Taylor sparse attention. Furthermore, we build \textbf{\texttt{LIVEditor-14B}} , a novel lightning video editing model via ISA and a proposed video-editing data pipeline that curated a 1.7M high-quality dataset. Extensive experiments demonstrate that LIVEditor-14B achieves a $\sim$60% reduction in attention-module latency while surpassing state-of-the-art methods across EditVerseBench, IVE-Bench, and VIE-Bench, delivering near-lossless acceleration without compromising visual fidelity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。