The MiMo Embodied Model (MiMo-Embodied) is a powerful cross-embodied vision-language model that has demonstrated excellent performance in both autonomous driving and embodied AI tasks. It is the first open-source vision-language model that combines these two key domains, significantly enhancing the understanding and reasoning abilities in dynamic physical environments.

MultimodalTransformers

Cosmos-Predict2.5 is a high-performance pre-trained world foundation model suite developed by NVIDIA specifically for physical AI. Based on diffusion model technology, it can generate high-quality images and videos with physical awareness based on text, image, or video input, providing world simulation capabilities for applications such as autonomous driving and robotics.

MultimodalDiffusers

Cosmos-Reason1 is a physical artificial intelligence model developed by NVIDIA. It has the ability to understand physical common sense and can generate embodied decisions through long-chain thinking reasoning. This model supports multimodal input (text + video/image) and outputs text, which is suitable for physical AI fields such as robotics and autonomous driving.

MultimodalTransformersEnglish

D-FINE is an advanced model for object detection. By redefining the bounding box regression task in the DETR model, it achieves excellent positioning accuracy. The model adopts two key components, Fine-grained Distribution Refinement (FDR) and Global Optimal Localization Self-distillation (GO-LSD), and performs excellently in various real-time object detection scenarios such as autonomous driving and monitoring systems.

Computer VisionTransformersEnglish

DriveLMM-o1 is a fine-tuned large multimodal model optimized for autonomous driving, based on the InternVL2.5-8B architecture and adapted using LoRA technology, achieving step-by-step reasoning through stitched multi-view images.

MultimodalTransformersEnglish

A license plate detection model fine-tuned based on the YOLOv8 framework, suitable for autonomous driving and traffic monitoring scenarios

A fine-tuned semantic segmentation model based on the Mask2Former framework, suitable for road scene understanding and autonomous driving applications

Computer VisionSafetensors