@article{perceptualdecouplingforscalablemulti,
  title = {Perceptual Decoupling for Scalable Multi-modal Reasoning via Reward-Optimized Captioning},
  author = {Yunhao Gou and Kai Chen and Zhili Liu and Lanqing Hong and Xin Jin and Zhenguo Li and James T. Kwok and Yu Zhang},
  year = {2025},
  eprint = {2506.04559},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.04559v1},
}