activity
20242026
collaborators

6 papers

cs.RO2026

Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models

Xiangkai Ma, Yue Ma, Junjie Wang +6

World Action Models (WAMs) aim to construct a unified architecture capable of understanding world state evolution and guiding to generative motion planning. However, existing visua…

cs.RO2026

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…

cs.CV2025

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…

cs.AI2025

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…

cs.LG2025

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…

cs.LG2024

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…