By now, we’re all generally familiar with large language models (LLMs) and the core use of text in predictive, generative, and agentic AI services. As automated intelligence services now diversify, our attention turns to large image/vision models, large audio models, and the emerging field of video generation models.
The next frontier in this space may be what the industry is calling spatial intelligence — AI systems that understand and reason over physical environments rather than just text or images. One emerging approach is the…
