Wentao Yuan
Scholar

Wentao Yuan

Google Scholar ID: PZZZG6YAAAAJ
Google DeepMind
3D Computer VisionRobotics
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
2,358
 
H-index
13
 
i10-index
13
 
Publications
18
 
Co-authors
42
list available
Contact
CVOpen ↗TwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
4 items
GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training
2025
Cited
0
PointArena: Probing Multimodal Grounding Through Language-Guided Pointing
2025
Cited
0
Gemini Robotics: Bringing AI into the Physical World
2025
Cited
3
Vote-Tree-Planner: Optimizing Execution Order in LLM-based Task Planning Pipeline via Voting
2025
Cited
0
Resume (English only)
Academic Achievements
  • Selected Publications: RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics (2024); Manipulate-Anything: Automating Real-World Robots using Vision-Language Models (2024).
Research Experience
  • Currently a research scientist at Google DeepMind.
Education
  • Ph.D.: University of Washington, Computer Science, Advisor: Dieter Fox; M.S.: Carnegie Mellon University, Robotics Institute, Advisor: Martial Hebert; B.A.: Pomona College, Computer Science and Mathematics.
Background
  • Research Interests: Developing intelligent systems that enable embodied agents to perceive and interact with diverse 3D environments. Field: Computer Science.
Miscellany
  • Links: CV, GitHub, Google Scholar, LinkedIn, Twitter
Co-authors
42 total
Dieter Fox
Dieter Fox
University of Washington and AI2
martial hebert
martial hebert
CMU
David Held
David Held
Associate Professor in the Robotics Institute, Carnegie Mellon University
Ranjay Krishna
Ranjay Krishna
University of Washington, Allen Institute for AI
Jiafei Duan
Jiafei Duan
Computer Science PhD Student, University of Washington
Co-author 6
Co-author 6
Co-author 7
Co-author 7
Jan Kautz
Jan Kautz
Vice President of Research, NVIDIA Research