Scholar
Wanyue Zhang
Google Scholar ID: U1ngwqMAAAAJ
Max Planck Institute for Informatics
Video Generation
Animation
Human Scene Interaction
Robotics
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
297
H-index
6
i10-index
5
Publications
8
Co-authors
14
list available
Publications
6 items
World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning
2026
Cited
0
MM-UAVBench: How Well Do Multimodal Large Language Models See, Think, and Plan in Low-Altitude UAV Scenarios?
2025
Cited
0
VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification
2025
Cited
0
Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning
2025
Cited
0
Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture
2025
Cited
0
BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects
arXiv.org · 2024
Cited
0
Co-authors
11 total
Thomas Funkhouser
Princeton University and Google
Alireza Fathi
Google DeepMind
David A. Ross
Google DeepMind
Abhijit Kundu
Google DeepMind
Xun Xu
Senior Scientist at I2R, A-STAR
Hehe Fan
Zhejiang University
Rishabh Dabral
Max-Planck Institute for Informatics
Christian Theobalt
Professor, Max Planck Institute for Informatics, Saarland Informatics Campus, Saarland University
