GRNEdit: Efficient General Video Editing from a New Binary-Evidence Perspective in Generative Refinement Networks

Feng Xie; Jiagao Hu; Fuhao Li; Zepeng Wang; Yuxuan Chen; Dahua Gao; Fei Wang; Daiguo Zhou

title

authors

Feng Xie, Jiagao Hu, Fuhao Li, Zepeng Wang, Yuxuan Chen, Dahua Gao, Fei Wang, Daiguo Zhou

date

2026-08-17

venue

arXiv (preprint, not peer reviewed)

arXiv:2608.16328

upvotes

13 (Hugging Face Daily Papers, 2026-11-01)

links

abs pdf hf code

abstract

Instruction-based general video editing seeks to unify diverse editing operations within a single, intuitive interface. Existing approaches often rely on resource-intensive conditioning, using either heavyweight branches or costly source concatenation. Is there any efficient way to model editing intent? Thus, we introduce GRNEdit, a lightweight two-stage framework. GRN inspires our approach by encoding visual semantics through combinations of bits. Through task-specific fine-tuning, we take this representation further and recast editing semantics as local retain-or-flip decisions over individual bits. Source information is consequently modeled as coordinate-wise evidence supporting the observed binary states, while the GRN backbone remains responsible for resolving their global composition into coherent generative semantics. In Stage I, a compact encoder translates discrete source codes into continuous evidence signals, which GRN assimilates throughout binary refinement. Inspired by null-prompt training for classifier-free guidance, we further assign the null condition an editing-specific meaning: an empty instruction denotes no edit and is supervised through source reconstruction. This identity pathway not only implicitly strengthens evidence utilization and content preservation in Stage I, but also produces a source-preserving state in the same representation space as the edited state. Stage II can therefore directly compare each edited state with its source-preserving counterpart and use their discrepancy to revise unresolved target-bit decisions. Trained on only 0.6M pairs with less than 3\% conditioning parameters, GRNEdit-2B and GRNEdit-8B achieve scores of 4.03 and 4.18 on OpenVE-Bench. The 2B model outperforms multiple 14B open-source editors, while the 8B model performs on par with leading open-source editors.

@misc{xie2026grnedit,
  title={GRNEdit: Efficient General Video Editing from a New Binary-Evidence Perspective in Generative Refinement Networks},
  author={Feng Xie and Jiagao Hu and Fuhao Li and Zepeng Wang and Yuxuan Chen and Dahua Gao and Fei Wang and Daiguo Zhou},
  year={2026},
  eprint={2608.16328},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2608.16328}
}