@article{adaptivedenserewardunderstandingthegap, title = {Adaptive Dense Reward: Understanding the Gap Between Action and Reward Space in Alignment}, author = {Yanshi Li and Shaopan Xiong and Gengru Chen and Xiaoyang Li and Yijia Luo and Xingyao Zhang and Yanhui Huang and Xingyuan Bu and Yingshui Tan and Chun Yuan and Jiamang Wang and Wenbo Su and Bo Zheng}, year = {2024}, eprint = {2411.00809}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.00809v2}, }