Research · Ongoing
EO-VLM
A benchmarking framework for evaluating vision-language models on Earth observation tasks using satellite and UAV imagery.
Independent Research Lab
We conduct research in AI, Vision, and Robotics, and collaborate with organizations to turn research ideas into working systems.

We bring research and engineering together to investigate how intelligent systems perceive, understand, and interact with the world.
Place recognition, localization, and 3D scene representations.
Connecting images, video, language, and 3D for grounded reasoning.
Robot learning, planning, and control in the physical world.
Learning from satellite and aerial observations.
Research · Ongoing
A benchmarking framework for evaluating vision-language models on Earth observation tasks using satellite and UAV imagery.
Research · Ongoing
A collection of models and algorithms for image retrieval, image matching, and image-to-3D localization in XR and robotics.
We welcome collaboration with startups, research institutions, and innovation teams on challenges aligned with our expertise.
Define the question and success criteria.
Compare approaches and evaluate uncertainty.
Build, validate, and support handover.
Meet the researcher behind Layer42 and explore opportunities to collaborate.
Connect with us about a research direction or technical challenge.