AMI Labs: Real World. Real Intelligence.
AMI - Advanced Machine Intelligence - builds world-model-based AI that understands the real world. We develop safe, controllable intelligent systems for industry, robotics, healthcare, and beyond.
Our main goal is to build intelligent systems that understand the real world. Real-world data is continuous, high-dimensional, and noisy, whether it is obtained through cameras or any other sensor modality. Generative architectures trained by self-supervised learning to predict the future have been astonishingly successful for language understanding and generation. But much of real-world sensor data is unpredictable, and generative approaches do not work well. AMI is developing world models that learn abstract representations of real-world sensor data, ignoring unpredictable details,…
saved by
related reading
- Thinking Machines Labthinkingmachines.ai
- World Models: Computing the Uncomputablenotboring.co
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixelsle-wm.github.io
- RTFM: A Real-Time Frame Model | World Labsworldlabs.ai
- World Models | Rohit Bandarurohitbandaru.github.io
- A Functional Taxonomy of World Models - Dr. Fei-Fei Lidrfeifei.substack.com
- pdfopenreview.net
- Runway | Building Real-World Intelligencerunwayml.com
- The Model That Dreams the Worldmoe-capital.com
- Explore | alphaXivalphaxiv.org
- Language Models, World Models, and Human Model-Buildinglingo.csail.mit.edu
- Genie 3: A new frontier for world modelsdeepmind.google