Resume
Academic Achievements
- Next-LocLLM: Location Semantics Modeling and Coordinate-Based Next Location Prediction with LLMs.
- Enhancing Large Language Models for Mobility Analytics with Semantic Location Tokenization.
- FSTLLM: Spatio-Temporal LLM for Few Shot Time Series Forecasting.
- Self-supervised Learning for Geospatial AI: A Survey.
- Disentangling Dynamics: Advanced, Scalable and Explainable Imputation for Multivariate Time Series.
- UrbanLLM: Autonomous Urban Activity Planning and Management with Large Language Models.
- SAGDFN: A Scalable Adaptive Graph Diffusion Forecasting Network for Multivariate Time Series Forecasting.
- Multivariate time-series imputation with disentangled temporal representations.
- Electron Beam Melted Heterogeneously Porous Microlattices for Metallic Bone Applications: Design and Investigations of Boundary and Edge Effects.
Background
- Research interests include spatio-temporal data mining, artificial intelligence, and machine learning. Committed to developing advanced machine learning models to tackle practical challenges such as spatio-temporal data analysis, spatio-temporal LLMs and foundation models, AI-driven decision-making, and the application of machine learning techniques in various domains.
Miscellany
- Skills: Python (PyTorch, Hugging Face, LLM inference & QLoRA/LoRA fine-tuning, data processing), Spatio-Temporal ML (time-series forecasting, STGNNs, retrieval-augmented TS, Urban/transport data); Tools: Git/GitHub, JAX/NumPy/Pandas, Docker, Linux; Languages: Mandarin, English; Service: Reviewer: TKDE 2024–2025, KDD 2025, EMNLP 2024; External Reviewer: NeurIPS 2025, SIGSPATIAL 2025, VLDB 2023, CIKM 2023/2025.