FIRST INTUITION · RESEARCHPapers · Reports · Notes · Talks

Research,
in public.

We work on foundational world models — physics-based, 3D-driven, end-to-end. This is where we publish what we put out. More reports, notes, and talks will follow.

Position PaperThe work we think the field should be doing

A world model owes its world.

Generative video looks right for five seconds and then forgets. We argue the next generation of world models has to be physics-based, 3D-driven, and channel-committed — models that don't just predict pixels but maintain a world a robot, a creator, and an audience can all rely on.

AuthorsFirst Intuition Research Team
PublishedMay 2026
Reading time8 min
StatusLiving document · v0.4
Position Paper · MMXXVINo. 01