H-EmbodVis/PUMA
Robotics • Updated • 9 • 1
H-EmbodVis
university
AI & ML interests
None defined yet.
Recent Activity
Papers
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
H-EmbodVis/HyDRA
Text-to-Video • Updated • 77
H-EmbodVis/UniFuture
Other • Updated • 37
H-EmbodVis/GRANT
Other • Updated • 26 • 2
H-EmbodVis/VEGA-3D-Spatial-Reasoning
10B • Updated • 17 • 1
H-EmbodVis/Nautilus-llava-instruct-7b
7B • Updated • 7 • 2
H-EmbodVis/Nautilus-qwen-instruct-7b
9B • Updated • 9 • 2