cs.AINov 17, 2026

Towards Data-Efficient, Real-Time World Models

Authors: Raluca Stevenson, David Bignell, Jennifer C. White, Tabish Rashid, Emanuele Aiello, Mariya Hendriksen, Junha Hyung, Sadegh Aliakbarian, 

Organizations: Microsoft, Cambridge, United Kingdom · Now at Google DeepMind. · Now at Prometheus. · Now at the University of Oxford. · 

Abstract

State-of-the-art world models have been used to produce sequences of gameplay that accord with provided user-input actions. However, high quality, consistent gameplay generation often comes at the cost of inference speed, making real-time interactive play and ideation challenging. The substantial quantities of data used to train state-of-the-art models have also made custom training of these models appear impractical, limiting many of their potential uses in creative fields. In this work we demonstrate a major step towards efficient world models: achieving both fast high-quality inference, and improved data efficiency. This is done by replacing the next-token prediction paradigm with a two-stage discrete diffusion-based approach, introducing a lightweight refinement transformer which carries out iterative masked predictions. Building on an autoregressive world model capable of generating highly consistent and complex sequences over minutes (Kanervisto et al., 2025), we achieve substantial model speed-up (79x) with a modest quality trade-off. Additionally, we demonstrate that this model can be trained to reproduce high-quality, consistent gameplay using a dataset containing approximately one day (28 hours) of gameplay data. Our results demonstrate progress towards removing barriers to the use of world models in settings where real-time inference and data efficiency are essential.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MoWorld: A Flash World Model

    Jul 7, 2026Team Moxin, Deyi Ji, Tianrun Chen +26Efficient InferenceInteractive World Models

  2. WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching

    Mar 6, 2026Weilun Feng, Guoxin Fan, Haotong Qin +10Diffusion Model Inference AccelerationDiffusion Model Caching