NeuralOS: Towards Simulating Operating Systems via Neural Generative Models

TL;DR

NeuralOS is a neural framework that simulates operating system GUIs by predicting screen images from user inputs, enabling realistic GUI sequence generation and application simulation.

Contribution

It introduces NeuralOS, combining RNNs and diffusion models to simulate GUIs and demonstrates learning from synthetic data to simulate unseen applications.

Findings

Successfully generates realistic GUI sequences

Accurately predicts mouse interactions and state transitions

Can simulate applications not present in training data

Abstract

We introduce NeuralOS, a neural framework that simulates graphical user interfaces (GUIs) of operating systems by directly predicting screen frames in response to user inputs such as mouse movements, clicks, and keyboard events. NeuralOS combines a recurrent neural network (RNN), which tracks computer state, with a diffusion-based neural renderer that generates screen images. The model is trained on a dataset of Ubuntu XFCE recordings, which include both randomly generated interactions and realistic interactions produced by AI agents. Experiments show that NeuralOS successfully renders realistic GUI sequences, accurately captures mouse interactions, and reliably predicts state transitions like application launches. Beyond reproducing existing systems, NeuralOS shows that synthesized training data can teach the model to simulate applications that were never installed, as illustrated by a Doom application, and suggests a path toward learning user interfaces purely from synthetic demonstrations.