@HaiyuWu1: Learning causality from internet videos in latent space first, and then using RL to teach the foundation model how to a…

X AI KOLs Following Models

Summary

Induction Labs introduces imagination models, a new foundation model architecture that learns from internet-scale video. Their first model, Photon-1, learns to use a computer by watching 18 years of screen recordings without action labels, achieving better results at 30× lower pretraining cost than Gemini 3.1 Flash.

Learning causality from internet videos in latent space first, and then using RL to teach the foundation model how to act. This approach is 30× cheaper than Gemini 3.1 Flash on pretraining and achieves a better result. JEPA is all you need! However, actions are still learned during post-training. Figuring out how to automatically learn actions without action labels is still very important!
Original Article
View Cached Full Text

Cached at: 07/25/26, 08:11 PM

Learning causality from internet videos in latent space first, and then using RL to teach the foundation model how to act.

This approach is 30× cheaper than Gemini 3.1 Flash on pretraining and achieves a better result. JEPA is all you need!

However, actions are still learned during post-training. Figuring out how to automatically learn actions without action labels is still very important!

Induction Labs (@induction_labs): We’re introducing imagination models: a new foundation model architecture that unlocks learning from internet-scale video.

Our first imagination model, Photon-1, learned to use a computer by watching 18 years of screen recording video without action labels.

Similar Articles

@swyx: full writeup and links here

X AI KOLs Timeline

A Latent Space podcast episode discusses the thesis that video models derive intelligence from LLMs, and that the next frontier is video agents. Guest Ethan He, who built Grok Imagine at xAI, shares insights on building frontier image and video systems.

Learning Visual Feature-Based World Models via Residual Latent Action

Hugging Face Daily Papers

This paper introduces RLA-WM, a visual feature-based world model that leverages residual latent actions and flow matching to efficiently predict future visual states. The method outperforms existing video-diffusion and feature-based approaches while enabling novel robot learning techniques from offline, actionless demonstration videos.