Solaris: Towards Interfaces That Are Generated, Not Coded

2026-09-01

AI Summary

该研究通过引入Solaris界面世界模型，利用自回归合成和少量步骤蒸馏等方法实时生成交互式UI，解决了传统数字界面需预先编码指定的问题。

Abstract

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

Problem

• digital interfaces
• autoregressive generation
• user interactions
• world model
• dynamic generation

Innovation

• autoregressive frame generation
• few-step distillation
• language model for user intent