属性引导的扩散式文本到微结构生成
Property-Informed Diffusion-Based Text-to-Microstructure Generation
把文本中的语义与物理属性作为联合条件注入扩散模型，并用对比对齐加测试时奖励引导保证生成结果与提示一致，这套「属性条件 + 双重对齐」思路可直接迁移到视觉中的条件生成与可控合成任务。
原文依据 a dual alignment strategy is adopted, including contrastive text-structure alignment and test-time reward-guided alignment
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论设计满足预期功能的 3D 超材料微结构仍是一项重大挑战，因为这通常需要领域专业知识、迭代仿真以及大量人工调参。现有的逆设计工作基于期望的目标属性自动生成微结构，但往往设计多样性有限，且在保证生成结构的物理可行性方面面临困难。为解决这一问题，本文提出一种属性引导的扩散网络，可直接根据文本描述生成 3D 微结构。与传统属性条件方法不同，本方法利用文本输入中语义与物理属性两方面的丰富引导来支持多样化的结构合成。为强化生成结构与目标文本提示之间的一致性，采用双重对齐策略，包括对比式文本-结构对齐与测试时奖励引导对齐。实验结果表明，该模型能够在多种材料类别上生成语义有意义且物理上合理的结构。所提框架在交互式微结构设计方面具有良好潜力，并为将基于语言的接口与逆材料发现相结合开辟了新方向。代码见：https://github.com/hongsong-wang/PropDiff-TMG。
英文原文摘要 1427 字符
Designing 3D metamaterial microstructures that meet the intended functions remains a major challenge, as it typically requires domain expertise, iterative simulations, and extensive manual tuning. Existing work on inverse design that automatically generates microstructures based on desired target properties often suffers from limited design diversity and faces challenges in ensuring the physical feasibility of the generated structures. To address this issue, a property-informed diffusion-based network is proposed that enables the generation of 3D microstructures directly from textual descriptions. Unlike traditional property conditioning methods, our approach leverages rich guidance in terms of semantics and physical properties in the text input to support diverse structure synthesis. To enforce consistency between the generated structures and the target textual prompts, a dual alignment strategy is adopted, including contrastive text-structure alignment and test-time reward-guided alignment. Experimental results show that the model is capable of generating semantically meaningful and physically plausible structures across a wide range of material categories. The proposed framework has good potential for interactive microstructure design and opens up new directions for combining language-based interfaces with inverse material discovery. Code is available at: https://github.com/hongsong-wang/PropDiff-TMG.