Welcome

Hello, traveler from afar, who has stumbled upon this humble corner of the internet. Whether your arrival is by chance or by intention, you’re warmly welcomed. May you find exactly what you’re seeking—or perhaps uncover something delightful and unexpected.

I’m Xiang Fu

My research interests are in model behavior, evaluation, and alignment of language models. I aim to understand the internal mechanisms by which these systems represent and transform information; design metrics that reveal both their strengths and blind spots; and devise alignment techniques that reliably steer their outputs toward human values and intent. More broadly, I probe the interface between machine and human cognition—examining how artificial models learn to generalize, reason, and communicate in ways that both parallel and depart from human understanding. To pursue this work further, I started Modularium Research, where we study how models behave and develop better ways to evaluate them.

Should you choose to explore further, you might start with some projects

There’s also my CV