Yuxuan Liang

Causal Time Series Generation via Diffusion Models

Enabling arbitrary inference in spatio-temporal dynamic systems: A physics-inspired perspective

Multi-Order Wavelet Derivative Transform for Deep Time Series Forecasting

Gaussian Motion Field for High-Performance Video Compression

Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecasting

Multi-view Latent Diffusion Reconstruction for Vision-enhanced Time Series Forecasting

STKAN: Kolmogorov-Arnold Networks for Spatio-Temporal Forecasting

Hierarchical Gradient-Informed Reinforcement Learning for Scalable and Partially Observable Dynamic Resource Allocation

Improving Bilinear RNN with Closed-loop Control

UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces

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

ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models

FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation

Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting

Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems

Open-CK: A Large Multi-Physics Fields Coupling benchmarks in Combustion Kinetics

Towards Neural Scaling Laws for Time Series Foundation Models

Test-Time Learning of Causal Structure from Interventional Data

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

Learned Data Transformation: A Data-centric Plugin for Enhancing Time Series Forecasting

CaPulse: Detecting Anomalies by Tuning in to the Causal Rhythms of Time Series

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting

Toward Physics-guided Time Series Embedding

Test-Time Graph Rebirth: Serving GNN Generalization Under Distribution Shifts

NuwaTS: a Foundation Model Mending Every Incomplete Time Series

TSI-Bench: Benchmarking Time Series Imputation

MIND SCRAMBLE: UNVEILING LARGE LANGUAGE MODEL PSYCHOLOGY VIA TYPOGLYCEMIA