CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing
Research paper by Fuchen Long and collaborators. Published 2026-08-18. Topics: compositional instruction-guided video editing, CoinVE-200K, CoinVE-Bench, CoinVE-Edit, region-aware attention.
Resource information
- Authors
- Fuchen Long, Cong Wang, Zitao Gao, Wenhao Zhong, Yu Cheng, Xiaolu Hou, Yan Li, Xiao Cao, Xinlong Sun, Xi Chen, Yu Liu
- Research topics
- compositional instruction-guided video editing, CoinVE-200K, CoinVE-Bench, CoinVE-Edit, region-aware attention, Wan2.1-T2V-14B, Qwen3-VL-8B-Instruct, temporal consistency
- Publication date
- 2026-08-18
- Publication
- arXiv
- Last record update
- Nov 3, 2026