About Me
I'm Ke Xing, a third year undergraduate student majoring in CS from School of Computer Science & Technology, Beijing Jiaotong University. My research interest includes 3D&4D computer vision, AIGC and Embodied AI. With the development of large language models and multimodal large models, the ability of AI is becoming more and more capable. However, limited by the training data of large models, the current ability of AI is still limited to text, pictures and audio, and the understanding and logical reasoning of the real physical world is still limited. Therefore, I hope to devote myself to improving the three-dimensional world understanding ability of AI in future research. Align the spatial information with the existing modalities. If possible, I would like to find a primitive representation of knowledge or concepts that is not limited to modalities in order to increase the intelligence awareness of AI. I am very fortunate to be advised by Prof. Yunchao Wei of Wei Lab from School of Computer Science & Technology, Beijing Jiaotong University.