@article{reinforcementlearningwithdynamicmulti,
  title = {Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation},
  author = {Karin de Langis and Ryan Koo and Dongyeop Kang},
  year = {2024},
  eprint = {2402.14146},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.14146v3},
}