替代文本

Welcome to my homepage!

I am Hongao Zhu (IPA: /xʊŋ35 ɑʊ35/ /ʈʂu55/, Mandarin: 朱虹翱, pinyin: ZHŪ HÓNG ÁO). Here’s a copy of my CV.

I am a second-year PhD student in computational linguistics at UC San Diego, advised by Alex Warstadt in the Learning, Meaning, and Natural Language Lab (LeM🍋N Lab). I use language models to study how people learn and process language: whether models can show the critical-period effects seen in human second-language learners, when language model surprisal predicts reading times in Chinese, and how to test what models know about grammar, as with the Chinese minimal-pair benchmark ZhoBLiMP. I also co-organized the first ChineseBabyLM Challenge.

Before UCSD, I received a B.A. in Linguistics from Shanghai Jiao Tong University, where I worked with Hai Hu on how language models acquire the Chinese Ba construction. Since 2024, I have also worked with William Schuler at Ohio State on language model surprisal as a predictor of human reading times.

Curious what I have been thinking about lately? Here are my recent research puzzles, from benchmarking language models beyond text, including sign language, to what makes a construction learnable.

I am always open to summer research internships. If you work on language model evaluation, learnability, or language beyond text, I would be glad to hear from you; see the Contact page.

To know more about me and my research, please visit the About page.

Posts

subscribe via RSS