Yuxuan Liang

9 papers The Hong Kong University of Science and Technology (Guangzhou)

• Aeolus: A Multi-structural Flight Delay Dataset
• FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation
• Improving Bilinear RNN with Closed-loop Control
• Learning to Factorize Spatio-Temporal Foundation Models
• Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting
• Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting
• Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
• ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models
• UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces