Summary
Hantao Lou is an undergraduate AI researcher at Peking University (class of ’26) focused on AI alignment, interpretability, and scalable alignment methods. He has three years of hands-on research experience across academic and industry labs, including visiting research at PKU’s Alignment and Interaction Lab, internships at Shanghai AI Lab and Beneficial AI Foundation, and a focused fellowship on mechanistic interpretability. Supervised by leaders like Yaodong Yang and Evan Hubinger, Hantao works at the intersection of algorithmic alignment and multimodal/LM interpretability, exploring training dynamics and characteristic evaluation of language models. Based in Beijing, he combines rigorous academic training with practical research deployments and a track record of cross-institution collaborations that push toward responsible, value-aligned AI systems.
3 years of coding experience
Bachelor of Engineering - BE, Artificial Intelligence, Bachelor of Engineering - BE, Artificial Intelligence at 北京大学