Xiaofei Wen
Scholar

Xiaofei Wen

Google Scholar ID: gC6_i38AAAAJ
CS PhD@UCDavis
Natural Language Processing
Citations & Impact
All-time
Citations
26
 
H-index
3
 
i10-index
0
 
Publications
9
 
Co-authors
5
list available
Resume (English only)
Academic Achievements
  • - Publications:
  • - Towards Policy-Compliant Agents: Learning Efficient Guardrails For Policy Violation Detection (Preprint, 2025)
  • - REDCODER: Automated Multi-Turn Red Teaming for Code LLMs (Preprint, 2025)
  • - Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models (Preprint, 2025)
  • - ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails (ACL-Findings, 2025)
  • - MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design (NAACL-HLT, 2025)
  • - Red Teaming Language Models for Processing Contradictory Dialogues (EMNLP, 2024)
  • - Personalized Topic Selection Model for Topic-Grounded Dialogue (ACL-Findings, 2024)
  • - Sequential Topic Selection Model with Latent Variable for Topic-Grounded (EMNLP-Findings, 2022)
Research Experience
  • - Summer 2023: Research Intern, Fuxi@Netease, Hangzhou, China
  • - Fall 2022: Research Intern, Ant Group, Hangzhou, China
Education
  • - Degree: PhD in progress
  • - School: University of California, Davis
  • - Advisor: Muhao Chen
  • - Time: Second year
  • - Major: Computer Science
Background
  • - Research Interests: LLM Reasoning, AI safety, and Multimodal model task perception problems
  • - Field of Study: Natural Language Processing
  • - Introduction: Second-year PhD student in the Department of Computer Science at the University of California, Davis, working on developing intelligent systems capable of seamless interactions with humans.
Miscellany
  • - Personal Interests: Big fan of gangster films, especially The Godfather trilogy, drawn to the performances of Al Pacino and Robert De Niro.
  • - Other Hobbies: Loves Breaking Bad and Better Call Saul.
  • - Special Declaration: Proudly ShinRan/新蘭派.