LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention 事件

LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention arXiv:2605.04569v2 Announce Type: replace Abstract: 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 e