Yunkai Dang

prof_pic.jpg

I am a first-year Ph.D. student at the School of Intelligence Science and Technology, Nanjing University, advised by Prof. Wenbin Li and co-supervised by Prof. Yuekun Yang.

My research focuses on multimodal foundation models, with particular interests in high-resolution vision–language modeling, remote sensing foundation models, and uncertainty quantification and calibration.

If you have any questions, please feel free to contact me at yunkaidang1@gmail.com.

news

May 1, 2026 Our paper UHR-BAT has been accepted to ICML 2026.
Dec 24, 2025 I have created my own personal academic homepage and hope for good luck in the future.

selected publications

  1. Confidence/Motivation.png
    Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models
    Yunkai Dang, Yifan Jiang, Yizhu Jiang, Anqi Chen, Wenbin Li, and Yang Gao
    arXiv preprint arXiv:2604.17274, 2026
    Project arXiv PDF
  2. UHR_BAT.png
    UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing
    Yunkai Dang, Minxin Dai, Yuekun Yang, Zhangnan Li, Wenbin Li, Feng Miao, and Yang Gao
    In International Conference on Machine Learning, 2026
    ICML 2026
    Project arXiv PDF Code
  3. CLASP.png
    CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models
    Yunkai Dang, Yizhu Jiang, Yifan Jiang, Qi Fan, Yinghuan Shi, Wenbin Li, and Yang Gao
    arXiv preprint arXiv:2604.12767, 2026
    Project arXiv PDF Code
  4. RSVLM.png
    FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing
    Yunkai Dang, Donghao Wang, Jiacheng Yang, Yifan Jiang, Meiyi Zhu, Yuekun Yang, Cong Wang, Qi Fan, Wenbin Li, and Yang Gao
    arXiv preprint arXiv:2512.24022, 2025
    Project arXiv PDF Code
  5. RSHR.png
    A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs
    Yunkai Dang, Meiyi Zhu, Donghao Wang, Yizhuo Zhang, Jiacheng Yang, Qi Fan, Yuekun Yang, Wenbin Li, Feng Miao, and Yang Gao
    arXiv preprint arXiv:2512.17319, 2025
    Project arXiv PDF Code
  6. uncertainy.png
    Exploring response uncertainty in mllms: An empirical evaluation under misleading scenarios
    Yunkai Dang, Mengxi Gao, Yibo Yan, Xin Zou, Yanggan Gu, Jungang Li, Jingyu Wang, Peijie Jiang, Aiwei Liu, Jia Liu, and Xuming Hu
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing(EMNLP Main), 2025
    Project
  7. survery_explain.png
    Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey
    Yunkai Dang, Kaichen Huang, Jiahao Huo, Yibo Yan, Sirui Huang, Dongrui Liu, Mengxi Gao, Jie Zhang, Chen Qian, Kun Wang, Yong Liu, Jing Shao, Hui Xiong, and Xuming Hu
    arXiv preprint arXiv:2412.02104, 2024
    Project
  8. RLAIF-V.png
    RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness
    Tianyu Yu, Haoye Zhang, Yuan Yao, Yunkai Dang, Da Chen, Xiaoman Lu, Ganqu Cui, Taiwen He, Zhiyuan Liu, Tat-Seng Chua, and Maosong Sun
    arXiv preprint arXiv:2405.17220, 2024
    Project arXiv PDF
  9. Multi-level.png
    Multi-level correlation network for few-shot image classification
    Yunkai Dang, Min Zhang, Zhengyu Chen, Xinliang Zhang, Zheng Wang, Meijun Sun, and Donglin Wang
    In IEEE International Conference on Multimedia and Expo (ICME), 2023
    Project
  10. few-shot.png
    FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?
    Zihao Jiang, Yunkai Dang, Dong Pang, Huishuai Zhang, and Weiran Huang
    arXiv preprint arXiv:2307.04114, 2023
    Project