Published multiple papers, including 'Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works' and 'Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data'; participated in important conferences like ACL 2024 and EMNLP 2024; won the second prize in the InternLM competition hosted by the Shanghai Artificial Intelligence Laboratory as part of the Takway.AI team.
Research Experience
Involved in several research projects related to role-playing, such as BookWorld, CoSER, etc.
Education
Ph.D. in NLP, 2021 - 2026 (estimated), Fudan University; B.S. in CS, 2017 - 2021, Fudan University.
Background
Xintao Wang is a fourth-year Ph.D. candidate at Fudan University in the School of Computer Science. He is deeply fascinated with ACG (Anime, Comics & Games) culture and is devoted to revolutionizing the ACG industry with AI techniques. His research interests primarily focus on human-like generative agents and their personas, including (but not limited to): role-playing language agents, cognitive modeling in language models.
Miscellany
Has a strong interest in ACG culture, J Pop music, and Cosplay.