The journey of developing spatial intelligence will lead to unforeseen possibilities, expanding the boundaries of technology and its applications.

Spatial intelligence is about a machine's ability to perceive, reason, and act in 3D space and time, understanding how objects and events are positioned and how interactions affect those positions.

The future of spatial intelligence includes generating immersive 3D worlds for various applications, such as gaming and education, rather than just static images or videos.

The ultimate goal of spatial intelligence is to have widespread deployment and impact, allowing businesses and individuals to leverage its capabilities effectively.

By integrating a 3D representation into models, we can better align the model's capabilities with the tasks we want it to perform, enhancing user affordances. Spatial intelligence is crucial for creating technology that understands and interacts with the 3D world, enabling a wide range of applications.

Visual spatial intelligence is as fundamental as language, and we have the right ingredients now, including advancements in compute and algorithms, to unlock its potential.

The integration of spatial intelligence with augmented reality will enhance user experiences, allowing for real-time interaction with the physical world.

Spatial intelligence will enable robots to interact effectively with the physical world, bridging the gap between digital and real-world environments.

To build intelligence that collaborates with humans, it must be trained on diverse data, including video, as human learning occurs across multiple modalities.