Google DeepMind has added Agentic Vision to Gemini 3 Flash, enabling active image exploration through Python code execution ...

Abstract: Low-light image augmentation is crucial in many applications where visibility is regularly impeded by suboptimal lighting, such as autonomous driving, surveillance, and medical imaging.

Pixasonics is a library for interactive audiovisual image analysis and exploration, through image sonification. That is, it is using real-time audio and visualization to listen to image data: to map ...

Abstract: The recent development of autonomous vehicles has grown significantly, offering the possibility of safer and more effective modes of transportation. Enabling cars to travel and operate ...

See also the Bifrost tutorial notebooks, which can be run on Google Colab or any Jupyter environment where Bifrost is installed (and a GPU is available). Below is a longer snippet that demonstrates ...