TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM Paper • 2607.27205 • Published 9 days ago • 139
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation Paper • 2604.28196 • Published Apr 30 • 74
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation Paper • 2604.28196 • Published Apr 30 • 74
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published Apr 9 • 116
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published Apr 9 • 116
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published Apr 9 • 116
Seeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and Perception Paper • 2503.13587 • Published Mar 17, 2025