发表机构
Runway（Runway）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出Solaris界面世界模型，以逐帧生成交互式UI替代编码，结合自回归生成与少步蒸馏，用语言模型分离高层推理与视觉渲染，支持开放式交互，推动软件新范式。
AI 中文摘要
数字界面传统上通过代码等中间表示实现，要求其外观和行为需预先指定。我们提出Solaris，一种界面世界模型，它不再预先编码界面，而是逐帧直接生成交互式UI，响应用户操作。Solaris将鼠标交互视为条件信号，以自回归方式合成视觉状态，达到交互速度。为在延长的交互中保持视觉连贯性同时实现实时生成，我们结合自回归帧生成与少步蒸馏，并基于模型自身的输出进行训练。语言模型补充视觉世界模型，用于解释用户意图，指定交互如何影响生成环境，将高层推理与视觉渲染分离。通过动态生成界面的外观和行为，Solaris支持无需预先显式编程的开放式交互。我们认为界面世界模型是软件新范式的一步，在此范式中，界面围绕用户意图持续生成和适配，而非作为预定义状态的固定集合实现。
英文摘要
Digital interfaces are traditionally implemented through intermediate representations such as code, requiring their appearance and behavior to be specified in advance. We introduce Solaris, an interface world model that instead generates an interactive UI directly, frame by frame, in response to user actions. Solaris treats mouse interactions as conditioning signals and autoregressively synthesizes the resulting visual state at interactive speeds. To enable real-time generation while maintaining visual coherence over extended interactions, we combine autoregressive frame generation with few-step distillation and training on the model's own outputs. A language model complements the visual world model by interpreting user intent and specifying how interactions should affect the generated environment, separating high-level reasoning from visual rendering. By generating both the appearance and behavior of an interface dynamically, Solaris enables open-ended interactions that need not be explicitly programmed in advance. We view interface world models as a step toward a new paradigm for software, where interfaces are generated and adapted continuously around user intent rather than implemented as fixed collections of predefined states and
CommentsProject page: https://runway.com/news/research/introducing-solaris
