zhaochen0110/OpenThinkIMG
Enables LVLMs to actively use adaptive vision tools
View on index · View in 3D Map
Related repos
- End-to-end autonomous driving with vision-language-action models
- Robot vision framework with world models for edge devices
- Unifies OpenCV and YOLOv8 into real-time perception pipeline
- Open vision-language models that compete with closed-source alternatives using fully open data
- Inference and fine-tuning of Vision Language Models on Mac
- vision-language model using reinforcement learning for visual understanding tasks
- Builds computer vision models fast
- Self-hosted AI computer vision NVR
- Big Vision: codebase for training large-scale vision models using Jax/Flax andTPUs
- Dataset and model for robot manipulation
