Projects

Projects where I serve as the principal investigator or lead developer, responsible for the overall research direction, system design, and implementation.

Fundamental Research Funds for the Central Universities of China
Research on Prediction of User Travel Destination and Travel Time Based on Trajectory Representation Learning

Applies representation learning to trajectory data to transform original features into high-level information, improving the performance of downstream tasks such as travel time and destination prediction.

Personal Interest Project
Home Install
Development of OverleafCopilot - Empowering Academic Writing in Overleaf with Large Language Models

This project aims to develop a Browser extension to seamlessly integrate Large Language Models (such as ChatGPT) into the popular online academic writing platform, Overleaf.

Personal Interest Project
Website Code
Development of PromptGenius - All-purpose prompts for LLMs

This project focuses on developing a website that offers a wide range of prompt categories, enhancing the versatility of LLMs for various tasks and improving their output quality.

Projects where I participate as a key researcher, contributing to specific aspects such as model development, data analysis, or experimental design.

Villum Foundation
Research on Inverse Design of Materials Using Diffusion Probabilistic Models

This project focuses on developing diffusion probabilistic models to first understand the relationship between chemistry/structure and material properties, then enable the inverse design of new materials with specific properties. This project currently supports my postdoctoral research position.

National Natural Science Foundation of China
Research on Pre-training Representation Learning Methods of Spatial-temporal Trajectory Data for Traffic Prediction

This project aims to propose pre-training representation learning methods for spatial-temporal trajectory data, modeling multiple features to improve traffic prediction tasks. It demonstrates how trajectory representation learning can enhance traffic data mining.

National Natural Science Foundation of China
Research on Spatial-temporal Trajectory Generation and Representation Learning Methods for Sparsity Problems

This project explores how to generate high-quality spatial-temporal trajectory data and corresponding representations to address sparsity-related issues, thereby supporting a variety of downstream tasks.