I am Yuewen Gao, a senior undergraduate at the School of Intelligence Science and Technology, Nanjing University (NJU). Supervised by Prof. Ke Xu and mentored by Dr. Wenchao Li, I have embarked on my research journey in the fields of HCI.
My research interest lies, broadly, in Human-AI Collaboration, I am driven by a vision to build intelligent systems that move beyond task automation toward a more fluid, agency-preserving synergy between human cognition and machine intelligence.
I ground this vision in three core research pillars:
- Human-Centric AI: Investigating adaptive agents that dynamically align with human cognitive architectures, fostering mutual understanding while safeguarding human agency in open-ended tasks.
- Visualization and Intelligent Exploration: Creating scalable and AI-augmented visualization systems to facilitate progressive knowledge discovery from multimodal data.
- Cognitive Foundations of Interaction: Grounding human-system interaction in empirical cognitive theories to derive foundational design principles for next-generation interfaces.
Seeking Fall 2027 Ph.D. and M.Phil. opportunities in NLP and HCI (US, Singapore, or Hong Kong). If my background aligns with your work, I would love to connect.
🔥 News
- 2026.07: 🎉🎉 I start my journey in NEU as a research assistant!
- 2026.03: 🎉🎉 My collaborative work NetworkCanvas is accepted by CHI 2026. Many thanks to my wonderful collaborators!
- 2025.03: 🎉🎉 I start my journey in NJU as a research intern!
📝 Publications
ProactiveFlow: Coordinating Proactive AI Support for Sketch-Based Ideation
Yuewen Gao, Wenchao Li, Yiqing Yang, Lejia Li, Yutong Wu, Ke Xu
ProactiveFlow is a sketch-based proactive AI assistant that uses interaction traces and canvas context to coordinate whether, when, and what support to provide—including when not to intervene. Informed by flow theory, it combines adaptive timing with context-aware divergent and convergent support to assist creative ideation while preserving user agency.
NetworkCanvas: Supporting Progressive Network Visualization Exploration via Adaptive Recommendations
Wenchao Li, Yuewen Gao, Yu He, Cong Zhu, Ke Xu
NetworkCanvas is an adaptive, AI-assisted exploration system for complex networks. It combines interactive visualization, recommendation guidance, and a traceable exploration history tree to support progressive, explainable network analysis.
Multimodal Analysis of News Videos: Event-based Visual Summarization over Serial Broadcasts
Yuewen Gao, Yu He, Xianglei Lv, Yingying Dong, Ke Xu
NewsTract is a multimodal news intelligence system that segments video news into atomic events, extracts key semantic signals, and models event relations. It provides an interactive visualization interface for exploring complex news narratives and uncovering hidden event connections.
🎖 Honors and Awards
- 2025.11 Nanjing University People’s Scholarship.
- 2025.01 Honorable Mention, Mathematical Contest in Modeling 2025.
- 2024.11 Nanjing University People’s Scholarship.
📖 Educations
- 2023.09 - Now, Nanjing University, School of Intelligence Science and Technology.
💻 Internships
- 2026.07 - Now, Research Assistant, NEU HAI Lab, advised by Prof. Arthur Yao.
- 2025.11 - 2026.01, Research Intern, Pi Lab, collaborating with Chang Liu, Tsinghua University.
- 2025.03 - Now, Research Intern, iMATE Lab, advised by Prof. Ke Xu, Nanjing University.