Wenxuan Song
Scholar

Wenxuan Song

Google Scholar ID: jtFoCpwAAAAJ
The Hong Kong University of Science and Technology (Guangzhou)
Vision-language-action ModelRobotics
Google Scholar↗
Citations & Impact
All-time
Citations
144
 
H-index
7
 
i10-index
6
 
Publications
12
 
Co-authors
9
list available
Contact
No contact links provided.
Publications
37 items
Is Forward Prediction Enough? Physical State Grounding for JEPA World Models
2026
Cited
0
Robust-WAM: Bridging Generative Pretraining and Semantic Foresight in World-Action Models
2026
Cited
0
MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight
2026
Cited
0
DreamTrajectory: Trajectory-Guided Action Generation with World Model Alignment for Mobile Manipulation
2026
Cited
0
PIVOTSBench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models
2026
Cited
0
Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation
2026
Cited
0
IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams
2026
Cited
0
SEDualVLN: A Spatially-Enhanced Dual-System for Vision-Language Navigation
2026
Cited
0
Resume (English only)
Co-authors
9 total
Pengxiang Ding
Pengxiang Ding
Zhejiang University
Han Zhao
Han Zhao
Zhejiang University | Westlake University
Donglin Wang
Donglin Wang
Westlake University
Siteng Huang
Siteng Huang
Alibaba DAMO Academy | ZJU | Westlake University
Can Cui
Can Cui
Shanghai Jiao Tong University
Zongyuan (Tony) Ge
Zongyuan (Tony) Ge
Associate Prof | Director of AIM for Health Lab | NVIDIA AI Fellowship
Haoang Li
Haoang Li
Assistant Professor, Hong Kong University of Science and Technology (Guangzhou)
JIAYI CHEN
JIAYI CHEN
Tongji University