AI Paper Atlas

Research map / Large language models / AI and society

NeuralOS: Towards Simulating Operating Systems via Neural Generative Models

Luke Rivard, Sun Sun, Hongyu Guo, Wenhu Chen, Yuntian Deng

ICLR 2026 · Large language models › AI and society · approach: Social-science view of AI evaluation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Gaussian spatial cursor position map to the renderer context (ablation)NeuralOS · Cursor position (730 eval examples)x position error (pixels): 130.0 -> 1.6Improved
add joint training with the diffusion renderer after RNN pretraining (ablation)NeuralOS · qualitative generationframe sharpnessImproved
add scheduled sampling stage (ablation)NeuralOS · long interaction sequencespixel RMSE of generated framesImproved
add RNN pretraining with MSE loss before joint trainingNeuralOS · trainingRNN gradient useImproved
replace transformer encoder with hierarchical RNN (ablation)NeuralOS · inference memory, 1024 s videoGPU memory (GB): >40 (OOM) -> 11.96Improved
add random exploration data to agent-generated demonstrationsNeuralOS · training dataspurious correlationsImproved
use recurrent state instead of a fixed 64-frame context (vs adapted DIAMOND)NeuralOS · OS simulation, equal computepixel RMSE over generated stepsImproved
fine-tune DIAMOND with scheduled sampling (p=0.05)adapted DIAMOND · OS simulation, equal computeapplication-launch transitionsMixed
extend test delay beyond the training delay (64, 128, 256 frames vs 8 in training)NeuralOS · Folder presence after reopeningfraction predicted has folder: 0.52 -> 0.60 -> 0.62Mixed
crop bottom 40 pixels of videos in human evaluation (ablation)NeuralOS · Human identification of real OShuman success rate (%): 58.3 -> 51.7 (10s)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy