H-EmbodVis/VEGA-3D-Spatial-Reasoning
10B • Updated • 15 • 1
Xianjin-Wu
HyperbolicCurve
AI & ML interests
3D computer vision
Recent Activity
upvoted a paper about 1 hour ago
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models upvoted a paper 11 days ago
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models liked a model 15 days ago
H-EmbodVis/VEGA-3D-Spatial-ReasoningOrganizations