👩💻 I am a Research Scientist at Apple. My work focuses on supervised fine-tuning (SFT), reinforcement learning (RL) post-training, and scalable LLM agent system design. I am passionate about translating cutting-edge research in large-scale modeling into production-ready AI systems.
🎓 I received my Ph.D. in Computer Science from the University of Minnesota, Twin Cities, where I was advised by Prof. Arindam Banerjee and worked closely with Prof. Steven Wu. My doctoral research focused on machine learning foundations, developing training algorithms that improve neural network generalization while preserving data privacy. I received my B.Sc. in Electronic Information and Communications from Huazhong University of Science and Technology.
🔥 News
- 2026.02: Co-organizing the Embodied AI Workshop (WDFM-EAI) at CVPR 2026.
- 2025.11: Paper on LLM Agents for E-Commerce Ad Generation accepted to EMNLP 2025.
- 2024.05: Paper on LLM-powered Recommendation Agents (RecMind) accepted to NAACL 2024 Findings.
- 2024.01: Paper on Theory of Generalization and Optimization accepted to AISTATS 2024.
- 2023.12: Paper on Conversational Query Rewrite with Feedback Learning accepted to EMNLP 2023.
- 2023.07: Paper on Unified Contextual Query Rewriting accepted to ACL 2023.
📚 Selected Publications
Improving Contextual Query Rewrite for Conversational AI Agents through User-preference Feedback Learning
EMNLP 2023 Industry
📋 Services
- Reviewer
- NLP Conferences: ACL, EMNLP, NAACL, EACL
- Machine Learning Conferences: ICML, NeurIPS, ICLR, AISTATS
- Workshop Organizer: Embodied AI Workshop - WDFM-EAI @ CVPR 2026