6 papers
Temporal-Visual Semantic Alignment: A Unified Architecture for Transferring Spatial Priors from Vision Models to Zero-Shot Temporal Tasks
Xiangkai Ma, Han Zhang, Wenzhong Li +1
Large Multimodal Models (LMMs) have achieved remarkable progress in aligning and generating content across text and image modalities. However, the potential of using non-visual, co…
Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generation
Xiangkai Ma, Lekai Xing, Han Zhang +2
Vision-Language-Action (VLA) models built upon Chain-of-Thought (CoT) have achieved remarkable success in advancing general-purpose robotic agents, owing to its significant percept…
Energy-Aware Pattern Disentanglement: A Generalizable Pattern Assisted Architecture for Multi-task Time Series Analysis
Xiangkai Ma, Xiaobin Hong, Wenzhong Li +1
Time series analysis has found widespread applications in areas such as weather forecasting, anomaly detection, and healthcare. While deep learning approaches have achieved signifi…
Unify and Anchor: A Context-Aware Transformer for Cross-Domain Time Series Forecasting
Xiaobin Hong, Jiawen Zhang, Wenzhong Li +2
The rise of foundation models has revolutionized natural language processing and computer vision, yet their best practices to time series forecasting remains underexplored. Existin…
Domain Fusion Controllable Generalization for Cross-Domain Time Series Forecasting from Multi-Domain Integrated Distribution
Xiangkai Ma, Xiaobin Hong, Mingkai Lin +3
Conventional deep models have achieved unprecedented success in time series forecasting. However, facing the challenge of cross-domain generalization, existing studies utilize stat…
A Wave is Worth 100 Words: Investigating Cross-Domain Transferability in Time Series
Xiangkai Ma, Xiaobin Hong, Wenzhong Li +1
Time series analysis is a fundamental data mining task that supervised training methods based on empirical risk minimization have proven their effectiveness on specific tasks and d…