@ARTICLE{11086409,
  author={Wen, Zhiquan and Tan, Mingkui and Wang, Yaowei and Wu, Qingyao and Wu, Qi},
  journal={IEEE Transactions on Multimedia}, 
  title={Enhanced Reasoning via Multimodal LLMs and Collaborative Inference}, 
  year={2025},
  volume={27},
  number={},
  pages={7166-7178},
  keywords={Cognition;Training;Adaptation models;Large language models;Accuracy;Collaboration;Visualization;Reliability;Question answering (information retrieval);Predictive models;Collaborative inference;multimodal large language model;zero-shot visual question answering},
  doi={10.1109/TMM.2025.3590940}}