@article{fromperceptiontoreasoningdeepthinkingemp,
  title = {From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models},
  author = {Wenxin Zhu and Andong Chen and Yuchen Song and Kehai Chen and Conghui Zhu and Ziyan Chen and Tiejun Zhao},
  year = {2025},
  eprint = {2511.12861},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.12861},
}