@inproceedings{liu2026gdpo,
  title = {GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization},
  author = {Shih-Yang Liu and Xin Dong and Ximing Lu and Shizhe Diao and Peter Belcak and Mingjie Liu and Min-Hung Chen and Hongxu Yin and Yu-Chiang Frank Wang and Kwang-Ting Cheng and Yejin Choi and Jan Kautz and Pavlo Molchanov},
  year = {2026},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  eprint = {2601.05242},
  archiveprefix = {arxiv},
}