@article{
lai2026unified,
title={Unified Text-Image-to-Video Generation: A Training-Free Approach to Flexible Visual Conditioning},
author={Bolin Lai and Sangmin Lee and Xu Cao and Xiang Li and James Matthew Rehg},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=eCJvmZMhNb},
note={}
}