titleOne Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing
authorsAdheesh Sunil Juvekar, Onkar Kishor Susladkar, Kiet A. Nguyen, Muntasir Wahed, Nabeel Bashir, Xiaona Zhou, Tianjiao Yu, Vedant Shah, Ismini Lourentzou
date2026-09-03
venuearXiv (preprint, not peer reviewed)
idarXiv:2609.04190
affiliationPLAN Lab @University of Illinois Urbana-Champaign
upvotes6 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
abstractVideo 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 FiVE, EditVid achieves 78.16 FiVE-Acc, compared with 58.95 for the strongest evaluated training-free baseline, while obtaining competitive results on IVEBench. A user study further shows a 51.8\% overall preference for EditVid over 7 competing methods.

cite

@misc{juvekar2026one,
  title={One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing},
  author={Adheesh Sunil Juvekar and Onkar Kishor Susladkar and Kiet A. Nguyen and Muntasir Wahed and Nabeel Bashir and Xiaona Zhou and Tianjiao Yu and Vedant Shah and Ismini Lourentzou},
  year={2026},
  eprint={2609.04190},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2609.04190}
}