Scholar
Wenxuan Song
Google Scholar ID: jtFoCpwAAAAJ
The Hong Kong University of Science and Technology (Guangzhou)
Vision-language-action Model
Robotics
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
144
H-index
7
i10-index
6
Publications
12
Co-authors
9
list available
Publications
45 items
EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation
2026
Cited
0
UniWAM: Unified World-Action Model
2026
Cited
0
Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts
2026
Cited
0
TacDyn-WAM: Learning Implicit Tactile Dynamics in a Heterogeneous Visuo-Tactile World Action Model
2026
Cited
0
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
2026
Cited
0
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
2026
Cited
0
ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware
2026
Cited
0
4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields
2026
Cited
0
Load more
Co-authors
9 total
Pengxiang Ding
Zhejiang University
Han Zhao
Zhejiang University | Westlake University
Donglin Wang
Westlake University
Siteng Huang
Alibaba DAMO Academy | ZJU | Westlake University
Can Cui
Shanghai Jiao Tong University
Zongyuan (Tony) Ge
Associate Prof | Director of AIM for Health Lab | NVIDIA AI Fellowship
Haoang Li
Assistant Professor, Hong Kong University of Science and Technology (Guangzhou)
JIAYI CHEN
Tongji University
