Home
Research Area
News
Featured Projects
Members
Publications
Contact
NVIDIA Research
Light
Dark
Automatic
Wentao Yuan
UW
Interests
Learning-based robotic manipulation
task and motion planning
Latest
AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation
Avoid Everything: Model-Free Collision Avoidance with Expert-Guided Fine-Tuning
Manipulate-Anything: Automating Real-World Robots using Vision-Language Models
RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics
M2T2: Multi-task Masked Transformer for Object-centric Pick-and-Place
SORNet: Spatial Object-Centric Representations for Sequential Manipulation
Cite
×
