Qingyun Li(he/him)

I am a Computer Science student at the University of Washington. My current work studies how language models learn, represent, and expose structure through tokenization, decoding, and representation geometry. My earlier published work was in computational photography, which was my first route into computer vision & applied AI.

In my free time I like to talk about tokenizers, play the piano, and sometimes question my sanity—although I will admit these are not mutually exclusive activities.