About Me

I am an undergraduate student at Peking University, majoring in Information and Computing Science. My research focuses on computer vision, image synthesis, and multimodal learning. I am passionate about bridging theoretical advances with practical applications, exploring how AI can interpret, generate, and reason over complex visual and multimodal data.
I actively engage in research projects involving image synthesis, multimodal understanding and generation, and post-training for visual generative models. Through these projects, I aim to deepen my understanding of both the theoretical foundations and practical challenges of modern AI, while strengthening skills in model design, experimentation, and problem-solving. I am always eager to collaborate on innovative research and contribute to projects that push the boundaries of visual intelligence and multimodal learning.