Hi, I am Tianyi Zhang

I am Tianyi Zhang (张添翼), a Ph.D. student at the College of Computer Science and Technology, Zhejiang University. My research focuses on embodied intelligence and multimodal large language models, with an emphasis on Vision-Language-Action (VLA) policy learning for robotic manipulation.

Previously, I was a research intern at the Shanghai Innovation Institute (Large Model Center), where I worked on generalist robot manipulation models including Dita (ICCV 2025), OC-VLA (AAAI 2026), and Vlaser (ICLR 2026), as well as the InternVL series. I received my M.S. from Tsinghua University, working on CUDA optimization and large-scale neural network training acceleration, and my B.S. from Xiamen University, ranking 1st in my major.