inverse-design

该论文提出 Simulator-Refined Diffusion (SRD)，将低精度可微代理模型与高精度不可微全波电磁模拟器结合到扩散采样过程中，用于 PCB 布局的射频逆向设计，实验显示其匹配目标 S 参数的效果比现有最先进方法提升最多达 21.2%。

This paper presents a graph-generation framework for designing 3D mechanical lattices, inspired by biological growth, which uses a GCNN for inverse design to achieve target mechanical properties.

Introduces SHRAV, an architecture-independent computational framework for physical modeling and inverse design using State, Hypothesis, Reason, Action, and Verify components.

VortexChat is an LLM-based agentic framework that automates the inverse design of integrated photonic devices from natural language specifications, demonstrated by autonomously fabricating a terahertz multiplexer with high performance.

The article highlights LLMs' lack of innate physical world understanding and introduces a Fourier Neural Operator-based framework that accelerates quantum dynamics prediction by 10^7 times, enabling efficient inverse design of quantum control protocols with improved success rates.

This paper presents a conditional catalyst generative model based on GPT architecture, pretrained on 133 million catalyst structures, achieving 98% structural validity and enabling controllable inverse design for targeted properties such as binding energy.

This paper presents a range-aware Bayesian optimization framework that directly scores the posterior probability that a candidate satisfies a target property range, enabling discovery of diverse valid designs across multiple specifications.

Researchers from MIT present a methodology for inverse design of nuclear critical experiments using deep neural networks with a novel multigroup attention pooling architecture and gradient-based optimization to maximize neutronic similarity coefficients. The approach is applied to validate a HALEU fuel transportation cask, achieving high similarity scores for three configurations of interest.

PolyFusionAgent is a framework that combines a multimodal polymer foundation model (PolyFusion) with a tool-augmented, literature-grounded design agent (PolyAgent) for polymer property prediction and inverse design, enabling evidence-linked discovery.

Proposes CoMole, a controllable molecular generative foundation model using motif-aware graph diffusion and reinforcement learning, achieving superior controllability across materials and drug discovery benchmarks.

This paper introduces RL-Kirigami, a framework combining optimal-transport conditional flow matching and reinforcement learning to solve the inverse design problem for kirigami metamaterials, achieving high accuracy and enabling rapid laser-cut prototype fabrication.