Ahn, Daechul, et al. “ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 2, Apr. 2025, pp. 1728-36, doi:10.1609/aaai.v39i2.32166.