xiaomi-research/unidrivevla

Unifies 3D perception and semantic reasoning for autonomous driving

View on index · View in 3D Map

Related repos

• Fast, interpretable trajectory prediction for autonomous driving
• End-to-end autonomous driving with vision-language-action models
• Vision-Language-Action model with adaptive reasoning for autonomous driving
• Model for robot actions from videos
• Multimodal model for spatial action reasoning
• fast vision-language model for on-device AI
• Enhances LLMs for urban spatial intelligence
• Dataset and model for robot manipulation
• Enables LVLMs to actively use adaptive vision tools
• CUDA-accelerated visual SLAM for robotics