I am currently a Ph.D. candidate at the School of Computer Science, Peking University, under the supervision of Prof. Jun Gao. I am also an intern with the VLM Base Model Team at ByteDance Seed, where I work on multimodal coding agents. Prior to now, I obtained my B.Eng. degree from the College of Electronic and Information Engineering, Tongji University, under the supervision of Prof. Dawei Cheng.