Translations:Diffusion Models Are Real-Time Game Engines/10/zh: Difference between revisions

Latest revision as of 00:18, 9 September 2024

Information about message (contribute)

This message has no documentation. If you know where or how this message is used, you can help other translators by adding documentation to this message.

Message definition (Diffusion Models Are Real-Time Game Engines)

Several important works (Ha & Schmidhuber, [https://arxiv.org/html/2408.14837v1#bib.bib10 2018]; Kim et al., [https://arxiv.org/html/2408.14837v1#bib.bib16 2020]; Bruce et al., [https://arxiv.org/html/2408.14837v1#bib.bib7 2024]) (see Section [https://arxiv.org/html/2408.14837v1#S6 6]) simulate interactive video games with neural models. Nevertheless, most of these approaches are limited in respect to the complexity of the simulated games, simulation speed, stability over long time periods, or visual quality (see Figure [https://arxiv.org/html/2408.14837v1#S1.F2 2]). It is therefore natural to ask:

有几项重要研究（Ha & Schmidhuber，2018；Kim 等人，2020；Bruce 等人，2024）（见第6节）使用神经模型来模拟交互式视频游戏。然而，这些方法大多在模拟游戏的复杂性、仿真速度、长时间的稳定性或视觉质量等方面存在局限性（见图2）。因此，自然而然地会问：