Scholar
Kuangzhi Ge
Google Scholar ID: _kPOfsoAAAAJ
Peking University
Multimodal Learning
Embodied AI
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
3
H-index
1
i10-index
0
Publications
4
Co-authors
6
list available
Publications
10 items
Token-World: World Modeling in Vision-Language Model Token Space for Robot Manipulation
2026
Cited
0
TrAct: Bridging Robot Control and Visual Prediction with Visual Tracks
2026
Cited
0
Data Pyramid for Embodied Manipulation
2026
Cited
0
LABSHIELD: A Multimodal Benchmark for Safety-Critical Reasoning and Planning in Scientific Laboratories
2026
Cited
0
TC-IDM: Grounding Video Generation for Executable Zero-shot Robot Motion
2026
Cited
0
PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models
2026
Cited
0
Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test
arXiv.org · 2026
Cited
1
Can World Models Benefit VLMs for World Dynamics?
2025
Cited
0
Load more
Co-authors
6 total
Shanghang Zhang
Peking University
Xiaowei Chi
The Hong Kong University of Science and Technology
Yike Guo
Dept of CSE, The Hong Kong University of Science and Technology
Lingjun Chen
Peking University
Kevin Zhang
Peking University
Yulin Luo
Peking University
