Biography

I am an Associate Professor in the School of Computing, University of Connecticut (UConn) since August 2025. Before that, I was an assistant professor at (UConn) since August 2020 and a research staff member at NEC Labs America in Princeton, NJ since July 2016. I received my Ph.D. degree in the Department of Electrical and Computer Engineering from University of California San Diego (UCSD) with the guidance of Prof. David A. Meyer in June 2016. I also work closely with Prof. Dacheng Tao from Nanyang Technological University (NTU).

My research focuses on developing foundational AI and machine learning models in the form of continual learning, graph machine learning, domain generalization, LLMs, foundation models, multimodal LLMs, and Agentic AI to perform time series analysis (e.g., representation, similarity search, prediction/forecasting, and anomaly detection), understand complex networks/graphs, and make trustworthy and interpretable decisions for continuously evolving real world applications (e.g., evolving graphs, dynamic systems, physical world, environmental science, healthcare and biomedical data). Four of my papers DARNN, HetGNN, MSCRED, and Empowering TS with LLMs have been ranked as the most influential papers in IJCAI 2017, KDD 2019, AAAI 2019, IJCAI 2024 by paperdigest.org, respectively.

I received the prestigious NSF Career Award (2024), Frontiers of Science Award (FSA) (2024), the UConn AAUP Excellence Award for Research and Creativity - Earlier Career (2025), the AI 2000 Most Influential Scholar Award Honorable Mention - Data Mining (2025), NEC Faculty Research Award (2025), and Best Paper Award (3rd Place CCC Award) at BlueSky Track of ICDM 2025. I also received UCONN Research Excellence Program (REP) Award in 2021. Recently, I have been elected as an AAAI Senior Member as one of 11 members in class 2026! [Link]

[New Survey]: Multi-modal Time Series Analysis: A Tutorial and Survey, KDD 2025 [Paper] [Github]

[New Survey]: Harnessing Vision Models for Time Series Analysis: A Survey, IJCAI 2025 [Paper] [Github]

[New Paper]: TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster, NeurIPS 2025 [Paper] [Github]

[New Paper]: TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop, NeurIPS 2025 [Paper]

[New Paper]: Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting, NeurIPS 2025 [Paper] [Github]

[Recruiting]: Looking for multiple Ph.D. students in 1) Machine Learning for (Multimodal) Time Series Analysis/Graph Representation Learning with LLMs & Foundation Models; 2) AI for Healthcare/Biomedical Data Analysis; 3) Reinforcement Learning, Reasoning, and Agentic AI. Please send me an email with your CV and transcripts.