REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing

This repository contains the official implementation of "REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing"

REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing

Weihan Xu, Yimeng Ma, Jingyue Huang, Yang Li, Wenye Ma, Taylor Berg-Kirkpatrick, Julian McAuley, Paul Pu Liang, Hao-Wen Dong

NeurIPS 2025

[Paper] [Demo Page]

Get Started

Citation

@inproceedings{xu2025regen,
  title     = {REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing},
  author    = {Xu, Weihan and Ma, Yimeng and Huang, Jingyue and Li, Yang and Ma, Wenye and Berg-Kirkpatrick, Taylor and McAuley, Julian and Liang, Paul Pu and Dong, Hao-Wen},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2025}
}