1. Published a survey paper titled 'Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI'.
2. Released SeePhys, a full spectrum multimodal benchmark for evaluating physics reasoning across different knowledge levels.
3. Introduced AtomThink, a novel slow thinking framework for multimodal mathematical reasoning task.
4. Published a paper on improving robustness in COVID-19 detection at the AAAI Conference.
Research Experience
Working at the HCP-I2 Lab, focusing on how MLLMs can enhance perception and reasoning for real-world comprehension and enable modeling and interaction for physical engagement.
Education
PhD - Sun Yat-sen University, Advisor: Prof. Xiaodan Liang; Master - Sun Yat-sen University, Advisor: Prof. Shancheng Jiang; Bachelor - Sun Yat-sen University, Advisor: Prof. Shancheng Jiang.
Background
Currently a PhD student at the HCP-I2 Lab in Sun Yat-sen University, advised by Prof. Xiaodan Liang. Research interests lie in building generalizable multimodal reasoning systems from a data-centric perspective.
Miscellany
Feel free to reach out at xiangk123@gmail.com to discuss potential collaboration.