I am a PhD Candidate at South China University of Technology (SCUT) and a Research Assistant at HKUST-GZ. My research focuses on Automated Machine Learning (AutoML) and LLM Agents. Currently, I am exploring autonomous workflows for scalable and reliable models, building resilient agentic systems to optimize real-world engineering pipelines under resource limits.

Email / GitHub / Google Scholar / CV

News

• [2026.05] Our Paper “EaSFE: Scalable and Efficient Feature Engineering for Boosting Machine Learning Performance” accepted by ACM TKDD!
• [2026.01] Our Paper “Towards Dynamic Interleaving Optimizers” accepted by ICLR 2026!
• [2025.11] Our Paper “A Better Start: Sensitivity-Aware Warm-Up for Robust and Efficient Fine-Tuning” accepted by AAAI 2026!
• [2025.06] Our Paper “Towards Recommendation on Good Quality Data Science Solutions” accepted by ACM TKDD!

Selected Publications

• Yile Chen, Zeyi Wen, Jian Chen, Jin Huang. Towards Dynamic Interleaving Optimizers. The 14th International Conference on Learning Representations (ICLR), 2026. PDF
• Yile Chen, Zeyi Wen, Jian Chen, Jin Huang. A Better Start: Sensitivity-Aware Warm-Up for Robust and Efficient Fine-Tuning. The 40th AAAI Conference on Artificial Intelligence (AAAI), 2026. PDF
• Yile Chen, Zeyi Wen, Jian Chen, Jin Huang. Enhancing the Performance of Bandit-based Hyperparameter Optimization. The 40th IEEE International Conference on Data Engineering (ICDE), 2024. PDF

View Full Publication List →