IDEA-Research/Rex-Omni
3B MLLM detects objects via point prediction
View on index · View in 3D Map
Related repos
- Unified vision model for open-world object detection
- Real-time object detection with DINOv3 features
- vision-language model using reinforcement learning for visual understanding tasks
- Detects any keypoints on images
- Vision foundation models for dense features
- Promptable 3D detection in unstructured environments
- Enables LVLMs to actively use adaptive vision tools
- Encoder for 3D point cloud tasks
- End-to-end autonomous driving with vision-language-action models
- Multimodal model for spatial action reasoning
