CV

Education

• Xi’an Jiaotong University, B.S. in Computer Science (Sep 2023 - Jun 2027 Expected)
  • GPA: 4.0/4.3 (Top 5%), Average Score: 91.32
  • TOEFL IBT: 106/120
• UC Berkeley, Berkeley Global Access (Jan 2025 - May 2025)
  • GPA: 4.0/4.0
  • Courses: Introduction to Artificial Intelligence, SICP, Computer Architecture

Research Experience

• Princeton AI2 Lab, Princeton University (Sep 2025 - Present)
  • Research Intern
  • Focus: LLM-based autonomous agents, GUI visual grounding
  • Conducted survey on LLM-based autonomous agents; leading research on self-evolving agents with cross-domain skill transfer
• Peking University & Beijing Innovation Center of Humanoid Robotics (Dec 2024 - Present)
  • Research Collaborator
  • Focus: World models for embodied agents
  • Collaborated on WoW world model framework; contributing to experiment implementation and cross-team coordination

Publications

Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test

Chun-Kai Fan*, Xiaowei Chi*, ... Zhiyuan Jiang, ... et al. (2026). "Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test." arXiv preprint arXiv:2601.04137.

Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding

Zhiyuan Jiang, Shenghao Xie, Wenyi Li, Wenqiang Zu, Peihang Li, Jiahao Qiu, Siqi Pei, Lei Ma, Tiejun Huang, Mengdi Wang, Shilong Liu. (2025). "Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding." arXiv preprint arXiv:2512.05941.

WoW: Towards a World omniscient World model Through Embodied Interaction

Xiaowei Chi*, Peidong Jia*, Chun-Kai Fan*, ... Zhiyuan Jiang, ... et al. (2025). "WoW: Towards a World omniscient World model Through Embodied Interaction." arXiv preprint arXiv:2509.22642.

Technical Skills

• Languages: Python, C/C++, Java, SQL, HTML/CSS
• ML/AI: PyTorch, Transformers, NumPy, Pandas
• Tools: Git, Docker, VS Code, Claude Code, Cursor

Ongoing Projects

• Autonomous Skill Learning for LLM Agents (Feb 2026 - Present)
  • Building self-evolving agent framework with transferable skills across terminal, web, and structured data environments
• Compositional Generalization of World Models (May 2025 - Present)
  • Designing prototype-tree-based framework for extracting & reusing atomic features from training data