@inproceedings{towardsbetteralignmenttrainingdiffusion,
  title = {Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards},
  author = {Zijing Hu and Fengda Zhang and Long Chen and Kun Kuang and Jiahui Li and Kaifeng Gao and Jun Xiao and Xin Wang and Wenwu Zhu},
  year = {2025},
  booktitle = {CVPR 2025 1},
  eprint = {2503.11240},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.11240v2},
}