CV
PDF format of my CV is available: Curriculum Vitae, 个人简历.
Education
- Dalian University of Technology, School of Future Technology
- Undergraduate student in Artificial Intelligence, 2023-present
Academic performance
- Weighted average: 89.76/100
- GPA: 3.98/5
- First 5 semesters academic rank: 13/63
Language test: CET-6 (591), CET-4 (618)
Selected coursework: Probability and Statistics (96), Deep Learning (96), Programming for Artificial Intelligence (92)
Research experience
Language-guided expertise evolution for protein optimization (Apr. 2025 - Present)
- Built a multi-agent system for protein optimization that evolves executable code blocks as an external expertise pool instead of tuning model parameters directly.
- Used gating and evolutionary search to specialize different expertise blocks to different sub-distributions in the protein sequence space.
- Introduced dense natural-language feedback from large language models as the fitness signal for code evolution.
- The early version won the Best Exploration Award at the Bohrium + SciMaster AI4S Competition, reached the interview round of MiraclePlus (top 10%), and led to a co-first-author workshop paper at ICLR 2026 RSI.
Protein hydration and crystallization condition prediction (Dec. 2023 - Present)
- Extract structured crystallization conditions from free-text Protein Data Bank records with large language models.
- Curated a high-quality protein sub-database with roughly 7,000 entries that contain both complete crystallization conditions and structural information.
- Built graph neural network models to predict major crystallization variables, including PEG concentration and polymerization degree.
- Studied hydration-aware protein representations that go beyond sequence, structure, and coarse electrostatic descriptors.
- Currently exploring surface hydration-guided protein design through representation learning and preference optimization.
Motif-driven molecular graph representation learning (Oct. 2024 - Dec. 2024)
- Studied a motif-based molecular graph representation framework that decouples functional encoding from structural encoding.
- Focused on core experimental work for the resulting publications on motif-aware GNNs and substructure-aware tokenization for molecular LLMs.
Publications
From Graphs to Tokens: Substructure-Aware Molecular Representation for Large Language Models
Runze Wang, Zijie Xing, Xingyue Liu, Mingqi Yang, Che He, Yanming Shen*, “From Graphs to Tokens: Substructure-Aware Molecular Representation for Large Language Models,” Information Processing and Management, vol. 63, no. 6, p. 104771, Sep. 2026
Language-guided expertise evolution for protein optimization
Xingyue Liu†, Zijie Xing†, Runze Wang, Luoming Hu, and Yanming Shen*, “Language-guided expertise evolution for protein optimization,” ICLR 2026 Workshop on AI with Recursive Self-Improvement, 2026
Motif-driven molecular graph representation learning
Runze Wang, Yuting Ma, Xingyue Liu, Zijie Xing, and Yanming Shen*, “Motif-driven molecular graph representation learning,” Expert Systems with Applications, vol. 269, p. 126484, 2025
Competitions and awards
- 2025 National First Prize, Mechanical Engineering Innovation & Creativity Competition – AI-based Non-Destructive Testing Image Evaluation Track (team leader)
- 2025 Third Prize, Northeast regional round, China Collegiate Computing Contest AIGC Innovation Competition
- 2025 First Prize, Dalian University of Technology Information Security Competition (team leader)
Scholarships
- National Scholarship, 2024-2025
- Academic Excellence Scholarship, 2023-2024
- Academic Excellence Scholarship, 2024-2025