Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation
Paper
•
2507.04047
•
Published
Yixuan Li
Yixuan-Li
·
AI & ML interests
Robotics Learning, Scene Understanding, Human Motion, Multimodality Learning
Recent Activity
authored
a paper
about 2 months ago
Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration
for Efficient and Versatile Embodied Navigation
Organizations
None yet
authored
a
paper
about 2 months ago