---
title: "Induction Labs' Photon-1 learns world simulation without action labels"
url: https://www.parallelquant.com/posts/induction-labs-photon-1-learns-world-simulation-without-action-labels-3f0df2
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/07/26/induction-labs-photon-1-simulates-desktops-plays-checkers-and-models-billiard-physics-from-one-pretraining-run/
published: 2026-07-26T09:14:22.000Z
topics: ["research", "products"]
publisher: "Parallel Quant"
---

# Induction Labs' Photon-1 learns world simulation without action labels

*2026-07-26 · Source: [MarkTechPost](https://www.marktechpost.com/2026/07/26/induction-labs-photon-1-simulates-desktops-plays-checkers-and-models-billiard-physics-from-one-pretraining-run/)*

Induction Labs released "imagination models," a foundation model architecture pretrained on raw video with no action labels attached. Their model, Photon-1, is a sparse 106-billion-parameter mixture-of-experts (MoE) system that can simulate desktop interfaces, play checkers, and model billiard-ball physics from a single pretraining run.

**Why it matters:** Removing the need for action-labeled data matters because labeled interaction data is the scarce, expensive ingredient in training world models and embodied agents -- most video on the internet has no action labels. If this generalizes, it could unlock a far larger pool of training data for agents that need to reason about cause and effect in digital or physical environments.

**Topics:** research, products

---
Read the original: https://www.marktechpost.com/2026/07/26/induction-labs-photon-1-simulates-desktops-plays-checkers-and-models-billiard-physics-from-one-pretraining-run/
Canonical: https://www.parallelquant.com/posts/induction-labs-photon-1-learns-world-simulation-without-action-labels-3f0df2
Published by Parallel Quant — https://www.parallelquant.com