[1]
Ahn, D. et al. 2025. ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO. Proceedings of the AAAI Conference on Artificial Intelligence. 39, 2 (Apr. 2025), 1728–1736. DOI:https://doi.org/10.1609/aaai.v39i2.32166.