Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization

@inproceedings{nguyen2025aligning,
  title = {Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization},
  author = {T. T. Nguyen and Campbell Wilson and Janis Dalins},
  year = {2025},
  booktitle = {International Conference on Advances in Computing and Artificial Intelligence},
  eprint = {2509.06759},
  archivePrefix = {arXiv},
  doi = {10.1109/ACAI68217.2025.11406573},
  url = {https://arxiv.org/abs/2509.06759},
}