Research

Vision & Multimodal

Help AI understand images, video, and text together—for tasks such as reading documents or inspecting objects.

What we study

Help AI understand images, video, and text together—for tasks such as reading documents or inspecting objects.
Computer Vision ↗
Multimodal AI ↗
Generative AI ↗
Remote Sensing AI ↗

Let's move forward

YOGYAKARTA · CENTRAL JAVA · BALI

Have a high-value challenge?
Let's solve it together.

Start the conversation