Scholar
Tianze Hua
Google Scholar ID: Au_icjEAAAAJ
Master Student, Brown University
Citations & Impact
Citations
13
H-index
1
i10-index
1
Publications
2
Co-authors
0
Resume
Academic Achievements
- Publications: 'How Do Vision-Language Models Process Conflicting Information Across Modalities?' (NEMI'25); 'mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?' (Findings of NAACL 2024)
Research Experience
- Currently investigating the modularity of representations and circuits in transformer models. Officially joined the LUNAR lab as a PhD student starting Fall 2025.
Education
- 2025-Present PhD in Computer Science, Brown University; 2023-2025 Sc.M. in Computer Science, Brown University; 2019-2023 B.S. in Computer Science & Philosophy, Tufts University
Background
- PhD student in Computer Science at Brown University, with research interests in interpretability and human-model comparison. Believes that attributing cognitive properties to computational models requires two components: operationalized definitions of those cognitive properties and sufficient knowledge of the inner workings of the computational models of interest.
Miscellany
- Links to CV, Twitter, GitHub, Google Scholar, and Semantic Scholar are provided on the personal website