Jiancheng Pan

Hi, I am Jiancheng Pan, a Ph.D. student at Tsinghua University. My research focuses on computer vision, multimodal learning, multimodal large language models and unified models for real-world applications in Earth science, medicine, and robotics, etc. I have published papers at CVPR, AAAI, ACM MM, and KDD, including a CVPR'26 Highlight and a KDD'26 Best Paper Award.