日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

週刊ニュースレター購読
レイアウト生成arXiv:2610.15290

Co-DSL:人間とLLMの協調によるレイアウト生成のための再利用可能な空間概念の設計

Co-DSL: Human-LLM Co-design of Reusable Spatial Concepts for Layout Generation

シェア:XThreadsFacebookLINEはてブBluesky

ユーザーとLLMが協調して再利用可能な空間概念を設計し、その概念を組み合わせてレイアウトを生成するフレームワークを提案。

著者: R. Kenny Jones, Jiajun Wu, Maneesh Agrawala

分類: cs.GR, cs.AI, cs.CV

原文アブストラクト

We present Co-DSL, a framework in which users and LLMs co-design reusable spatial concepts for layout generation. In the first stage, our system allows users to create a library of personalized operations. To add a concept, a user provides a description, which the LLM converts into an initial implementation. The user can then observe the concept's execution behavior over example scenarios and provide lightweight feedback to the LLM, which revises the concept's implementation logic. In the second stage, given a library, an LLM can author a layout program that meets a new layout request from a user. Executing a layout program instantiates a concept-graph, a declarative composition of library concepts. In this way, we require the LLM only to specify which concepts should hold, while we use a solver to search for a layout that satisfies them. Across five spatial layout domains, we find that Co-DSL libraries let LLMs capture layout patterns that are challenging for prior fixed-operation systems, and demonstrate that our concept-graph representation is needed for LLMs to reliably compose concepts together. We further find that Co-DSL lets LLMs author generative layout programs that expose high-level parametric controls users can manipulate to explore a distribution of related layouts without re-prompting.

関連論文

PR本紙発行元 EmplifAI