Hi! I am a third-year undergrad in the school of EECS, Peking University.
I am advised by Prof. Yizhou Wang and Wentao Zhu. I spent a wonderful summer at Johns Hopkins University, where I was fortunate to be mentored by Prof. Tianmin Shu.
I am a member of the experimental Zhi Class.
I aspire to do interesting, insightful, and fundamental research. My current research interests lie in developing socially intelligent agents and exploring science of LMs.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Experience
-
Peking UniversityB.S. in Computer ScienceSep. 2022 - Present -
Johns Hopkins UniversityVisiting StudentJune. 2024 - Sep. 2024
Honors & Awards
-
Zhi-Class Scholarship2024
-
Peking University Scholarship2023
-
Award for Scientific Research, Peking University2023
News
‘Language Models Represent Belief of Self and Others’ is presented at ICML 2024
Publications - Not able to set up "Selected Pubs" yet :-) (view all )
AutoToM: Automated Bayesian Inverse Planning and Model Discovery for Open-ended Theory of Mind
Zhining Zhang*, Chuanyang Jin*, Mung Yao Jia*, Tianmin Shu (* equal contribution)
2025
We introduce AutoToM, an automated Bayesian Theory of Mind method for achieving open-ended machine ToM. Leveraging an LLM as the backend, AutoToM combines the robustness of Bayesian models and the open-endedness of Language models, offering a scalable and interpretable approach to machine ToM.
AutoToM: Automated Bayesian Inverse Planning and Model Discovery for Open-ended Theory of Mind
Zhining Zhang*, Chuanyang Jin*, Mung Yao Jia*, Tianmin Shu (* equal contribution)
2025
We introduce AutoToM, an automated Bayesian Theory of Mind method for achieving open-ended machine ToM. Leveraging an LLM as the backend, AutoToM combines the robustness of Bayesian models and the open-endedness of Language models, offering a scalable and interpretable approach to machine ToM.
Language models represent beliefs of self and others
Wentao Zhu, Zhining Zhang, Yizhou Wang
International Conference on Machine Learning (ICML) , 2024
We investigate belief representations in LMs: we discover that the belief status of characters in a story is linearly decodable from LM activations. We further propose a way to manipulate LMs through the activations to enhance their Theory of Mind performance.
Language models represent beliefs of self and others
Wentao Zhu, Zhining Zhang, Yizhou Wang
International Conference on Machine Learning (ICML) , 2024
We investigate belief representations in LMs: we discover that the belief status of characters in a story is linearly decodable from LM activations. We further propose a way to manipulate LMs through the activations to enhance their Theory of Mind performance.