Omilab Unveils Two Major Open-Source Breakthroughs: VLM-FO1 and OpenTrackVLA

2025-12-12 / Read about 0 minute

Author：小编

On December 12, during the 2025 Global Developers Pioneer Conference, Omilab proudly presented two significant open-source innovations: VLM-FO1 and OpenTrackVLA. Additionally, it marked the inaugural offline launch of the OmAgent developer community.
VLM-FO1 stands as a plug-and-play framework designed to enhance visual-language models (VLMs). It boasts versatility in supporting a wide array of tasks, encompassing intricate visual reasoning, open-vocabulary object detection, and video object tracking.
On the flip side, OpenTrackVLA emerges as a fully open-source visual-language-action (VLA) system. It seamlessly blends natural language directives, real-time visual perception, and robotic action planning into a cohesive whole.

Previous page：For Product Development: TCL CSOT Unveils Vertical...

Next page：ChatGPT Entangled in a Lawsuit Tied to a Murder Ca...

Return to List

Hot Reading

2 day ago

All the important news from the ongoing India AI Impact Summit

2 day ago

Fractal Analytics’ muted IPO debut signals persistent AI fears in India

2 day ago

After all the hype, some AI experts don’t think OpenClaw is all that exciting

2 day ago

Flapping Airplanes on the future of AI: ‘We want to try really radically different things’