# Robot action generation

Nora is an open-source vision-language-action model trained on Qwen 2.5 VL - 3B, capable of generating robot actions based on language instructions and camera images.

OpenVLA-OFT is an optimized Vision-Language-Action model designed for robot tasks, which improves speed and success rate through fine-tuning technology.

OpenVLA-OFT is an optimized vision-language-action model that significantly improves the performance and speed of the basic OpenVLA model through fine-tuning technology.