Xintao Wang

Xintao Wang

Ph.D Candidate

Fudan University

Biography

Xintao Wang (王鑫涛) is a third 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. Hence, his research interests primarily focus on human-like generative agents and their personas, including (but not limited to):

  1. Role-Playing Language Agents: Targeting at creating AI agents that faithfully represent specific personas, including: (1) Agents for fictional characters from books and ACG, whose applications include virtual companions, games, and content creation; and (2) Agents for real-world individuals, which deeply understand user personas to serve as their digital proxies or personal assistants.

  2. Cognitive Modeling in Language Models: Focusing on integrating anthropomorphic cognition into LLMs, such as ego-awareness, social intelligence, personalities, etc. The goal is to promote LLMs’ understanding of the inner world of themselves and others, hence enabling them to generate more cognitively-aligned and human-like responses.

Interests
  • Large Language Models
  • Autonomous Agents
  • Role-Playing Language Agents
  • ACG, J Pop, Cosplay
Education
  • Ph.D in NLP, 2021 - 2026 (estimated)

    Fudan University

  • B.S in CS, 2017 - 2021

    Fudan University

News

Experience

 
 
 
 
 
Stepfun
Research Intern
Stepfun
July 2024 – Present Shanghai, China
Responsibilities: (1) Developing foundation models for role-playing language agents, and (2) Constructing high-quality datasets for established character role-playing.
 
 
 
 
 
Chat-Haruhi-Suzumiya Project
Research Leader
Chat-Haruhi-Suzumiya Project
August 2023 – March 2024 Shanghai, China
Lead the research project on the personality analysis of role-playing language agents.
 
 
 
 
 
Knowledge Works Lab, at Fudan University
Student Research Leader
Knowledge Works Lab, at Fudan University
September 2020 – Present Shanghai, China
Responsibilities: Lead the research groups on (1) role-playing language agents and (2) knowledge-enhanced LLM applications. Memtored near 10 graduate and undergraduate students. Together, we co-authored and published multiple research papers.
 
 
 
 
 
FudanNLP Group, at Fudan University
Student Researcher
FudanNLP Group, at Fudan University
July 2019 – September 2020 Shanghai, China
Responsibilities: Worked on fine-tuning language models for NLP tasks.

Awards

Second Prize of the InternLM Competitions
Chinese National Scholarship
Excellent Graduates of Shanghai
Chinese National Scholarship
Huawei Scholarship
Hhctea Freshman Scholarship

Recent Publications

Quickly discover relevant content by filtering publications.
(2024). From Persona to Personalization: A Survey on Role-Playing Language Agents. TMLR.

PDF Cite Project Slides

(2024). InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews. ACL 2024.

PDF Cite Code

(2024). Character is Destiny: Can Large Language Models Simulate Persona-Driven Decisions in Role-Playing?. In Arxiv.

PDF Cite Project

(2024). Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works. EMNLP 2024.

PDF Cite Project

(2024). SurveyAgent: A Conversational System for Personalized and Efficient Research Survey. In Arxiv.

PDF Cite Code Project Slides

Visitors