@HaiyuWu1: Learning causality from internet videos in latent space first, and then using RL to teach the foundation model how to a…
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.
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
Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning
Introduces Latent Dynamics Reasoning (LDR), a video world model that integrates kinematic dynamics in a structured latent space, enabling extrapolation of learned dynamics far beyond training distributions while using far fewer parameters and running much faster than video diffusion baselines.
@h100envy: Prime Intellect engineers explained how they train reasoning models over the open internet in 30 minutes - better than …
Prime Intellect engineers demonstrated a method to train reasoning models in 30 minutes using distributed RL over the open internet, utilizing Prime-RL, LLM judges, and multi-cloud GPUs, enabling open models to compete with closed labs without owning data centers.
@swyx: full writeup and links here
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
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.
@aimalysheva: latent actions are having a moment, especially in robotics: instead of predicting a robot's actual joint commands or ga…
Latent actions are gaining traction in robotics as a way to learn from unlabeled video without action labels. Recent papers from DeepMind and FAIR demonstrate progress from controlled game environments to in-the-wild internet video, promising scalable training for imitation learning.