One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing

  • 类型:arxiv
  • 标识:2609.04190
  • 链接:https://arxiv.org/abs/2609.04190
  • 主分类:multimodal
  • 形态:method
  • TLDR:Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editing within a single unified framework remains challenging. We introduce EditVid, a training-free framework combining sparse causal memory for local coherence, correspondence-based post-attention token injection for long-range identity preservation, and soft latent blending for edit locality. The same framework supports instruction-guided and reference-guided edits, including style transfer, attribute modification, object insertion, part-level editing, and subject replacement. On
  • 副分类:engineering
  • 待LLM分类:否
  • 来源文件
  • /inbox/tom/_candidates/2026-09-08-rag-retrieval-reranking-candidates.json
  • /inbox/tom/_candidates/2026-09-08-agent-rag-longcontext-candidates.json