Blog · 001
3 min read

Welcome to Apsidion. Why physical AI needs a world model grounded in physics.

What physical AI is missing, why physics is the way to supply it, and how we are building the model.

Language models had their moment when one model learned enough about text to be useful to everyone. Physical AI has not had that moment. We started Apsidion to build the model that brings it: a world model grounded in physics.

What physical AI is missing

Robots, autonomous machines and self-optimizing factories act on the physical world, but they know very little about it. They do not know how a sheet deforms under a press, where the heat goes in a weld, or what happens when a gripper closes on a soft part.

A world model holds that knowledge. Given the state of a process and an action, it predicts what happens next, and how sure it is. We are grounding ours in physics, because physics is the part of the world that is the same for every customer.

Why physics

Engineering computation today forces a choice between trust and speed:

SpeedTrustOutside its training data
Classical solversHours per runHigh: built on the conservation lawsHolds
Learned surrogatesMillisecondsNo physical guaranteesBreaks
A physics world modelReal timeConservation by constructionHolds

Conservation of mass, momentum and energy, contact and phase change are the same in a foundry, a robot cell and a human eye. A model that learns them once carries them into every domain. That is what lets it run fast without drifting away from reality, and reason about designs nobody has built yet.

Five gaps

Five gaps separate today's tools from a world model physical AI can use. Most tools close one or two of them. The second and third are not fully closed by any tool today.

GapWhere it comes fromWhat it blocks
Speed at scaleSerial, stability-limited time steps; attention that explodes across a million elementsReal-time control
One representationGrids and particles cannot hold discontinuities and smooth fields at onceCoupled phenomena
Gradients through discontinuitiesTearing, phase change and step changes break differentiationInverse design, closed-loop tuning
Live calibrationParameters are fixed offline, with no sensor streamAdapting to drift, wear and ageing
GeneralizationLearned operators map functions, not physicsDesigns that have never been made

How the model is built

Because the physics is shared, the core is built once. A new domain brings only its materials, the events that switch its behaviour, its sensors and the actions it can take (Fig. 2).

The core has seven layers, each standing on the one before:

LayerWhat it does
1 · Physical stateMoves between meshes, particles, grids and latent tokens, conserving what must be conserved
2 · Differentiable kernelKeeps gradients through contact and phase change
3 · Large physics modelCarries mechanisms from one regime to the next
4 · Learned closuresFill in what the equations leave open, and report their own uncertainty
5 · State estimationInfers the hidden state of a process from sparse sensors
6 · Action modelPredicts the consequence of an action before it is taken
7 · Inverse reasoningWorks back from a target to a process, and validates it

The physics is shared across every deployment. Each customer's recipes stay private.

Where it starts

We start in manufacturing. The physics there is dense, the sensors are already on the line, and a better model shows up directly as fewer trial runs.

How a process gets madeWhat comes out
TodayExperts, separate CAE tools and trial runs, with scrap as the feedbackA process that works after many runs; the knowledge retires with the engineer
With a physics world modelThe model, plant data and inverse search, calibrated on each lineA validated process in fewer runs, with error bars; the knowledge compounds

What this blog is for

We will write here about the work as it happens: how one representation holds a crack and a smooth field at once, what calibrating on a live line looks like, and where the model is wrong and by how much. Failures get written up alongside results.