September 2025: Two papers accepted to NeurIPS 2025.
- TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop
- TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster
May 2025: One paper accepted to ACM SIGKDD 2025, 'Multi-modal Time Series Analysis: A Tutorial and Survey'
January 2025: One paper accepted to ICLR 2025, 'Learning System Dynamics without Forgetting'
Research Experience
Work closely with leading research institutions and industry partners, including NEC Labs America, Morgan Stanley, and Mayo Clinic. Started a summer research internship at Mayo Clinic - AI & I Department in June 2025.
Education
Ph.D. Student in Computer Science, School of Computing, University of Connecticut, advised by Dr. Dongjin Song.
Background
Research interests: Developing generalizable and interpretable deep learning methods for time series analysis, spanning multi-modal data, general-purpose models, and real-world learning constraints.