xu

wxu2023

8 1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

upvoted a paper 3 months ago

HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation

upvoted a paper 4 months ago

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models

View all activity

Organizations

None yet

liked a dataset 8 months ago

H-EmbodVis/NautData

Viewer • Updated Dec 18, 2025 • 2.87M • 849 • 6