@article{aplotrobustrewardmodelingviaadaptivepref,
  title = {APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport},
  author = {Zhuo Li and Yuege Feng and Dandan Guo and Jinpeng Hu and Anningzhe Gao and Xiang Wan},
  year = {2025},
  eprint = {2510.10963},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.10963},
}