Hello, I am An Wang (王安). I received my Ph.D. in Computer Science from Institute of Science Tokyo (formerly Tokyo Institute of Technology) in June 2025, advised by Prof. Naoaki Okazaki. I am currently working at Tencent, on the LLM Pretraining Team (Qingyun Project) of Hunyuan. I am a core contributor to Hy3, mainly responsible for the model architecture design and base model production. Previously, my research focused on model architecture, training strategies, and scaling laws for large language models. Nowadays, I am passionate about AI agents and automating all workflows.