CV

Education

• Jinan University, Guangzhou, China
  • Bachelor of Information Management and Information Systems, Department of Mathematics
  • Expected graduation: June 2027
  • GPA: 3.34 / 5.00; average: 83.4 / 100

Research experience

• May 2025 — present: Research Assistant, Jinan University
  • With Associate Professor Mingliang Hou
  • Research on efficient LLM data selection, information-theoretic evaluation, causal model auditing, and robotic manipulation evaluation.
• November 2024 — September 2025: Research Assistant, Macau University of Science and Technology
  • With Professor Hao Chen
  • Research on knowledge graphs, graph representation learning, recommendation systems, and knowledge-enhanced retrieval.

Research interests

• AI evaluation and model auditing
• Mechanistic interpretability
• Trustworthy and causal machine learning
• Data-centric AI and efficient LLM systems
• Information-theoretic machine learning
• Generative models and computer vision

Technical skills

• Programming: Python, MATLAB, SQL, Java, C
• Scientific computing: Pandas, NumPy, Matplotlib, Seaborn
• Machine learning: PyTorch, Scikit-Learn, Transformers, Hugging Face, Qwen, DeepSeek
• Tools: Linux, Git, Jupyter, LaTeX

Honors and awards

• Jinan University Third-Class Outstanding Student Scholarship
• Mathematical Contest in Modeling (MCM/ICM), Successful Participant (2024)
• Mathematical Contest in Modeling (MCM/ICM), Honorable Mention (2025)

Language

• IELTS: Overall 7.0 (Listening 7.5, Reading 7.5, Speaking 6.0, Writing 6.0)

Publications

An Information-Theoretic Evaluation Framework for Benchmark and Model Diagnosis in Knowledge Tracing

Jiang, H.*, Wang, Z.*, Cheng, T., Li, X., Hou, M., Zheng, J., Luo, R., Guo, T., & Liu, Z. (2026). "An Information-Theoretic Evaluation Framework for Benchmark and Model Diagnosis in Knowledge Tracing." NeurIPS 2026. Accepted as poster.

arXiv

CDIS: Training-Free Data Selection for Instruction Tuning with Compression Ratio and Token Entropy

Jiang, H.*, Wang, Z., Hou, M., Li, X., Guo, T., Zheng, J., & Luo, R. (2026). "CDIS: Training-Free Data Selection for Instruction Tuning with Compression Ratio and Token Entropy." ACL ARR 2026 October. Conference submission. * Equal contribution.

Residualizing DKT with Symbolic Sequence Priors for Knowledge Tracing

Wang, Z.*, Jiang, H.*, Cheng, T., Li, X., Hou, M., & Liu, Z. (2027). "Residualizing DKT with Symbolic Sequence Priors for Knowledge Tracing." AISTATS 2027. Conference submission. * Equal contribution.

When Target Accuracy Hides Semantic Interface Drift in Vision–Language Adaptation

Jiang, H., Wang, Z., Hou, M., Li, X., Guo, T., Liang, Q., & Liu, Z. (2027). "When Target Accuracy Hides Semantic Interface Drift in Vision–Language Adaptation." ICLR 2027. Conference submission.

Download a PDF CV