跳到正文
arXiv cs.AI· Raluca Stevenson, David Bignell, Jennifer C. White, Tabish Rashid, Emanuele Aiello, Mariya Hendriksen, Junha Hyung, Sadegh Aliakbarian, Abdelhak Lemkhenter, Marko Tot, Katja Hofmann, Sarah Parisot·· 4 小时前AI 评分41

面向数据高效与实时推理的世界模型研究

Towards Data-Efficient, Real-Time World Models

AI 导读

研究团队用两阶段离散扩散方法替代下一 token 预测范式,并引入轻量级精炼 Transformer 做迭代掩码预测,在保持一定质量损失的前提下实现 79 倍模型加速。该模型仅用约一天(28 小时)的游戏数据即可训练出高质量、连贯的游戏画面生成能力,指向实时推理与数据高效的世界模型应用。

正文 · 原文

Authors:Raluca Stevenson, David Bignell, Jennifer C. White, Tabish Rashid, Emanuele Aiello, Mariya Hendriksen, Junha Hyung, Sadegh Aliakbarian, Abdelhak Lemkhenter, Marko Tot, Katja Hofmann, Sarah Parisot

View PDF HTML (experimental)

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.
Comments: 18 pages, 12 figures, 1 table. Includes supplementary material
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.22497 [cs.AI]
  (or arXiv:2611.22497v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.22497

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Katja Hofmann [view email]
[v1] Tue, 17 Nov 2026 09:52:15 UTC (8,402 KB)

来源:arXiv cs.AI · arxiv.org