@article{
shi2026oraclerlaif,
title={Oracle-{RLAIF}: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinforcement Learning from Ranked Feedback},
author={Derek Shi and Ruben Glatt and Christine Klymko and Hongjun Choi and Shashank Kushwaha and Wesam A. Sakla and Felipe Leno da Silva},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=RIRgnRicTa},
note={}
}