Scholar
Boxi Yu
Google Scholar ID: Tat3jMQAAAAJ
The Chinese University of Hong Kong, Shenzhen
Citations & Impact
Citations
140
H-index
6
i10-index
5
Publications
11
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- - Paper “UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench” accepted by ACL’2025.
- - Extended abstract “DSPy Guardrails: Building Safe LLM Applications via Self-Refining Language Model Pipelines” accepted by Compound AI Systems Workshop (June 13th, 2024 in San Francisco at Data + AI Summit).
- - Paper “Testing Graph Database Systems via Equivalent Query Rewriting” accepted by ICSE’2024.
- - Introduced “Retromorphic Testing,” a new, general methodology to the test oracle problem.
- - Paper “Deep Learning or Classical Machine Learning? An Empirical Study on Log-Based Anomaly Detection” accepted by ICSE’2024.
- - Paper “Automated Testing and Improvement of Named Entity Recognition Systems” accepted by ESEC/FSE’23.
Research Experience
- No specific work experience or research projects described.
Education
- Degree: PhD
- University: The Chinese University of Hong Kong, Shenzhen
- Advisor: Prof. Pinjia He
Background
- Research interests: AI Robustness (e.g., developing automated tools for testing and improving the AI software, and developing new testing architectures), and AIOps/MLOps (developing and managing the distributed systems and AI systems). Currently a PhD candidate at The Chinese University of Hong Kong, Shenzhen, advised by Prof. Pinjia He.
Miscellany
- No other personal interests or hobbies described.
