H-EmbodVis/VEGA-3D-Spatial-Reasoning
Video-Text-to-Text • 10B • Updated • 21 • 1
H-EmbodVis
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
H-EmbodVis/HERMESV2
Image-to-3D • Updated • 1
H-EmbodVis/HyDRA
Text-to-Video • Updated • 12
H-EmbodVis/PUMA
Robotics • Updated • 17 • 1
H-EmbodVis/UniFuture
Other • Updated • 3
H-EmbodVis/GRANT
Other • Updated • 2 • 2
H-EmbodVis/Nautilus-llava-instruct-7b
7B • Updated • 4 • 2
H-EmbodVis/Nautilus-qwen-instruct-7b
9B • Updated • 48 • 2