LabProc @ ICML 2026 · read the work ↓

The perception layer for Physical AI

TacitTangible

The most valuable knowledge on Earth was never written down. We build world models that perceive it.

We know more than we can tell. Now a machine perceives it, too.
after Polanyi
Tacit Perception 0.00 Tangible
ineffable · latent · felt perceived · structured · actionable

↑ drag to resolve

01 · Thesis

Language is lossy compression.
The physical world is what it drops.

Every lab protocol, every assembly manual, every standard operating procedure is a compression of something richer: the trained hands and calibrated eyes of a person who knows how. The pressure of a pipette draw. The angle that avoids aerosolizing a sample. The half-second hesitation that means a step went wrong. None of it survives translation into text. And text is all we have been feeding our machines.

This is why robots that ace language benchmarks still fumble physical procedures. The knowledge they need was never in the training data, because it was never in words at all. Philosopher Michael Polanyi named this six decades ago: tacit knowledge: the kind we demonstrably possess but cannot articulate.

Our bet: the path to Physical AI does not run through better descriptions. It runs through world models: systems that learn the structure of physical procedures by watching them, predicting them, and representing what language cannot encode. Not tacit to explicit. Tacit to tangible.

Polanyi · 1966
"We can know more than we can tell." Tacit knowledge is real, valuable, and structurally resistant to language.
Moravec · 1988
What is effortless for humans (perception, dexterity) is hardest for machines. The hard part is the valuable part.
LeCun · JEPA
Autoregressive text prediction cannot ground physical understanding. World models that predict in representation space can.
Fei-Fei Li
Spatial intelligence is its own intelligence. Seeing and acting in the world is not a downstream application of language.
Tacit World · now
The perception layer that makes tacit procedure tangible to machines, starting where it matters most: the laboratory.

02 · Research

LabProc: measuring the gap
between what is written and what is seen.

Laboratories are the sharpest test bed for tacit knowledge: procedures are precisely specified in writing, yet outcomes depend on what the writing never captures. Consider a reflux that must reach steady state: actively boiling versus settled. Same equipment, same label; only the motion of the fluid distinguishes them, and a frontier VLM reading sampled frames cannot tell them apart. LabProc is our six-task benchmark structured along exactly this axis, from language-amenable state recognition to motion-only discrimination. Tacit, our 305M-parameter domain-adapted V-JEPA-2.1 encoder, is the vision-only baseline we release alongside it.

ICML 2026 · AI for Science Workshop

LabProc and Tacit: Quantifying the Visual–Textual Prior Gap in Autonomous Laboratory Perception

Jagrati Gogia · Monish Kaul (Mstack AI)

Across a structural axis from language-amenable to motion-only tasks, a frontier VLM leads by 41 points where its pretraining carries the signal. The gradient reverses on the hardest motion-only subset, where Tacit leads by 9.1 points despite a ~1000× parameter asymmetry. Where pretraining provides the signal, pretraining wins; where motion-state is the only distinguishing feature, dense-temporal video representations win.

+9.1
points over a frontier VLM on the hardest motion-only test, where clips share equipment and nominal state and only motion distinguishes them, despite ~1000× fewer parameters.
$1.30
total compute cost of Tacit's adaptation: 28 minutes on a single H100, improving over base V-JEPA-2.1 on every task with a mean uplift of +8.2 points.
360×
cheaper per perception call than polling a frontier VLM: the economics that make hybrid perception the right architecture for autonomous labs.

03 · The Model

Tacit: a world model for procedure.

Tacit, a 305M-parameter domain-adapted V-JEPA-2.1 video encoder, watches physical procedures and learns their structure by representing them, not by generating captions. That distinction is the whole company. A captioning model tells you what is happening. Dense-temporal video representations capture what distinguishes this execution from the one that fails: the part that never made it into the protocol.

Input
Video of procedure
Real lab footage: hands, instruments, materials in motion.
Perception
Representation space
Tacit encodes the dynamics language discards: technique, timing, deviation.
Output
Tangible structure
Verification, qualification, and evaluation signals for autonomous labs.

04 · Vision

Start where tacit knowledge
is most expensive.

Drug discovery runs on physical procedure, and on the scarce experts who execute it well. As labs automate, a new question becomes existential: how do you verify that an autonomous system actually performed the procedure correctly? That verification layer is where we begin.

Near term

Perception for pharma R&D

Verification and qualification for automated laboratories: giving CROs and CDMOs an independent perception layer that watches procedures and certifies execution, accelerating the design-make-test-analyze cycle.

Long arc

The perception layer for Physical AI

Every domain where expertise lives in hands rather than documents (manufacturing, materials, medicine) needs machines that perceive procedure. We are building the models, benchmarks, and methodology to be that layer.

05 · Why we exist

Built by an operator
who kept meeting the same gap.

Tacit World was founded by Jagrati Gogia after eleven years building ML and data systems inside high-scale operations, where the distance between what the documentation said and what skilled people actually did was, again and again, where the value hid.

"Everyone is racing to make machines that talk about the world. We are building machines that can tell when the world is being handled correctly."

Tacit World · Delaware C-Corp · Bengaluru → US

06 · Contact

Working on autonomous labs?
We should talk.

Partnerships, pilots, research collaboration, or the ICML poster session. Reach out.

jagrati@tacitworld.ai