- “Don’t Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space Transformation” accepted by ACL 2025 and presented orally.
- “JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models” accepted by IEEE TVCG 2025.
- “DataLab: A Unified Platform for LLM-Powered Business Intelligence” accepted by ICDE 2025.
- “InsightLens: Augmenting LLM-Powered Data Analysis with Interactive Insight Management and Navigation” accepted by IEEE TVCG 2025.
- “AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systems” accepted by IEEE TVCG 2024.
- “PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation” accepted by IEEE VIS 2023.
- “XNLI: Explaining and Diagnosing NLI-based Visual Data Analysis” accepted by IEEE TVCG 2023.
Research Experience
Conducted research in the VAI group and participated in multiple projects, including GSTansform, JailbreakLens, DataLab, InsightLens, AgentLens, PromptMagician, etc.
Education
Ph.D. in Computer Engineering at Zhejiang University, supervised by Prof. Wei Chen; B.S. degree from Zhejiang University of Technology.
Background
Research interests include visual analytics and natural language interaction. Specifically, designing and developing visual and interactive systems to facilitate the understanding and utility of NLP models for downstream tasks, including creative tasks (e.g., text-to-image, painting-to-poetry) and analytical tasks (e.g., NLI-based data analysis).