Inverse Design

Follow this topic Ask about this topic

Inverse design starts with a target—such as a material property, optical spectrum, or molecular structure—and searches for a system that can produce it. Common approaches optimize a learned forward model or differentiable simulator using gradients, Bayesian or evolutionary search, while diffusion, flow-matching, and transformer models generate candidate designs directly. Reinforcement learning and agent-based workflows increasingly use simulator feedback to refine candidates, often with constraints for physical validity and manufacturability. Because many designs can meet the same target, a central challenge is balancing diversity and search efficiency with reliable predictions, physical validation, and clear measures of success.

Latest papers

112 papers17 papers in the last four weeks, up 42% on the four weeks before. 0.1% of all new papers.

Multi-Solution Inverse Design of Pixelated Patch Antennas Using an Autoregressive Transformer
Oct 29, 2026Young-Mok Yun, Seung-Won Shin, Jaeyong Chung +1Inverse Design Inverse Problems
Department of System Semiconductor Engineering, Yonsei University, Seoul 03722, South Korea.
Probing the limits of forward screening and inverse design of crystal materials
Oct 23, 2026Zhilong Song, Zijun Pang, Lixue ChengMaterials Discovery Inverse Design
Department of Chemistry, Hong Kong University of Science and Technology, Kowloon, Hong Kong 999077, China · IAS Center for AI for Scientific Discoveries, Hong Kong University of Science and Technology, Kowloon, Hong Kong 999077, China · Department of Chemical and Biological Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong 999077, China
PCFBench: How Far Can Large Vision-Language Models Go in Physics-aware Photonic Inverse Design?
Oct 23, 2026Shengchao Chen, Ting Shu, Sufen RenInverse Design VLM Evaluation
Australian AI Institute, University of Technology Sydney · School of Artificial Intelligence, Shenzhen University · School of Information and Communication Engineering, Hainan University
Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion
Oct 22, 2026Ricardo Luna Gutierrez, Vineet Gundecha, Rahman Ejaz +5Inertial Confinement Fusion Inverse Design
Hewlett Packard Enterprise · University of Rochester
AcoustiPrint: Physics-Guided Neural Design of Manufacturable Acoustic Structures
Oct 21, 2026Shanmuka Sadhu, Harshvardhan C. Takawale, Yehia Zakaria +2Inverse Design Physics-Informed ML
Department of Computer Science, University of Maryland, College Park · Department of Mechanical and Materials Engineering, University of Cincinnati
The Forward/Inverse Duality of Controlled Emergence:A Computational Design Program from Explanation to Engineering
Oct 19, 2026Hao Li, Minghui Ren, Shaowen LuInverse Design Emergent Behavior in Multi-Agent Systems
Aufkenn Technologies Co., Ltd., Ningbo, China · Northeastern University, Shenyang, China
CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning
Oct 16, 2026Tianmeng Hu, Biao Luo, Ke LiInverse Design Molecular Generation
Living Systems Institute, University of Exeter, United Kingdom · Department of Computer Science, University of Exeter, United Kingdom · School of Automation, Central South University, China
GOLD: Geometric Optimized Latent Diffusion for Structure-Aware RNA Inverse Folding
Oct 16, 2026Qi Si, Xuyang Liu, Penglei Wang +6Molecular Generation Inverse Design
Shanghai Academy of Artificial Intelligence for Science · School of Biomedical Engineering, Shanghai Jiao Tong University · Community Science Department, Kuaishou +2
TANGO: RNA Topology and Geometry Co-Design
Oct 14, 2026Tianmeng Hu, Biao Luo, Ke LiInverse Design
University of Exeter · Earlham Institute · Central South University
Inverse Garment Design with Visual Agents
Oct 11, 2026Nanxiang Jiang, Yunuo Chen, Zeng Tao +53D Garment Reconstruction Inverse Design
University of California, Los Angeles · Envora · Stanford University +2
DiffGA: Steering Frozen Diffusion Models for Materials Design via Evolutionary Search
Oct 10, 2026Shivang Agarwal, Rodrigo Wang, Kevin Ryczko +1Inverse Design Crystal Structure Generation
SandboxAQ, Palo Alto, CA 94301, USA.
MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design
Oct 9, 2026Jixin Tang, Ji Guo, Jun ZhaoInverse Design Reward Design for RL
Fudan University
A Physics-Informed Hybrid Forward-Inverse Machine Learning Framework for High-Dimensional Sparse Recipe Reconstruction
Oct 8, 2026Md. Muqtadir Fuad, Md. Istiak Adnan, Ridwan Al AzizInverse Design Sparse Recovery
Department of Industrial and Production Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka 1000, Bangladesh
La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching
Oct 8, 2026Runze Ma, Will Hua, Shuangjia ZhengInverse Design Flow-Based Generative Modeling
Shanghai Jiao Tong University · Independent Researcher
Learning qBIC Resonances across Metasurface Families in Dielectric Fourier Space
Oct 8, 2026Shuangteng Lei, Li Yu, Tianxin Li +1Frequency-Domain Feature Learning Inverse Design
State Key Laboratory of Infrared Physics, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China · University of Chinese Academy of Sciences, Beijing 100049, China · School of Physical Science and Technology, ShanghaiTech University, Shanghai 201210, China
Stream-Based Active Learning with Cooperative Neural Networks for Data-Efficient Partial Inverse Design: An Automotive Glass Run Channel Case Study
Oct 7, 2026Agung Nugraha, Hyerin Kwon, Heungjun Im +2Inverse Design Data-Efficient Learning
Department of Industrial and Data Engineering, Major in Industrial Data Science and Engineering, Pukyong National University, Busan, 48513, Republic of Korea · DRB Co., Ltd., Busan, 46329, Republic of Korea
Which alloy composition,what process parameters? Inferring the recipe from optimized metallic microstructure and texture
Oct 6, 2026Mahish K. Guru, Jan Bohlen, Louam Lemjid +3Inverse Design Materials Science
Institute of Material and Process Design, Helmholtz-Zentrum Hereon, Germany · Institute of Production Technology and Systems, Leuphana University Lüneburg, Germany · Institute of Material Systems Modeling, Helmholtz-Zentrum Hereon, Germany +2
Physics-Augmented Graph Transformers for Patch-Antenna Forward and Inverse Design
Oct 4, 2026Avi Epstein, Snir Nehemia, Haim Suchowski +1Physics-Informed GNNs Graph Transformer
Tel Aviv University
AbsorbEvo: An Agentic Framework for Autonomous Inverse Design of Microwave Absorbers
Oct 1, 2026Zhicheng Feng, Yubo Zhao, Xuefeng YaoLarge Language Model-Guided Optimization Natural Language to Optimization Modeling
Department of Engineering Mechanics, Applied Mechanics Lab, Tsinghua University, Beijing 100084, P. R. China
Simulator-Refined Diffusion for Radio-Frequency Inverse Design
Sep 29, 2026Jinhao Liang, Jacob K. Christopher, Michael Frei +2Diffusion Model Guidance Surrogate-Assisted Optimization
University of Virginia · Arena Physica
Co-PiLOT: Constrained Physics-Informed Latent Optimization for Target-Driven Inverse Design
Sep 29, 2026Mahish K. Guru, Mayank Nagar, Ayush vyas +3Physics-Informed Generative Modeling Bayesian Optimization
Institute of Material and Process Design, Helmholtz-Zentrum Hereon, Germany · Institute of Production Technology and Systems, Leuphana University Lüneburg, Germany · AI for Physical Systems, German Research Center for Artificial Intelligence (DFKI), Germany +1
RNA Design via Conditioned Flow Matching and Finite-Policy Reinforcement Learning
Sep 29, 2026Zefeng Lin, Xianyong Fang, Tianfan Fu +1Inverse Design Molecular Generation
School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China · School of Computer Science and Technology, Anhui University, Hefei, Anhui, China · State Key Laboratory for Novel Software Technology at Nanjing University, School of Computer Science, Nanjing University, Nanjing, Jiangsu, China
Graph Forward Distribution Matching for Molecular Inverse Design
Sep 25, 2026Yihan Zhu, Yuhan Liu, Brett Savoie +2Molecular Graph Generation Inverse Design
University of Notre Dame
Growth-Inspired Graph Generation and Inverse Design of Mechanical Lattices via Dot Matrices Database Augmentation and GCNN
Sep 24, 2026Weiyun Xu, Jiamu LiuGraph Generation Structural Mechanics
Department of Civil and Environmental Engineering, University of Illinois Urbana-Champaign, Urbana, Illinois 61801, USA · State Key Laboratory of Clean and Efficient Turbomachinery Power Equipment, Department of Mechanical Engineering, Tsinghua University, Beijing, 100084, China
SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design
Sep 23, 2026Ziheng Guo, Yang BuPhysics-Informed ML Inverse Design
ZhangJiang Laboratory
K-TRAIL: Simulator-Guided Generative Design of EM/RF Circuits
Sep 19, 2026Piyush Saha, Evan Newell, Hanna O'Leary +2Inverse Design Electronic Design Automation
School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, OR 97331 USA · Department of Electrical and Computer Engineering, Yale University, New Haven, CT 06511 USA
Symmetry- and Property-Aware Crystal Generation with Reinforcement Learning for Inverse Materials Design
Sep 11, 2026Ting-Wei Hsu, Arun Bansil, Qimin YanCrystal Structure Generation Inverse Design
Department of Physics, Northeastern University, Boston, 02155, Massachusetts, USA. · Quantum Materials and Sensing Institute, Northeastern University, Burlington, 01803, Massachusetts, USA.
Molecular representation shapes the balance between target fidelity and exploration in flow based polymer generation
Sep 10, 2026Tianren ZhangMolecular Generation Inverse Design
Department of Materials Science and Engineering, University of Delaware, Newark, Delaware 19716, United States
AI and TCAD for Inverse Design and Defect Discovery: From Simple Machine Learning to LLM
Sep 7, 2026Hiu Yung WongInverse Design Electronic Design Automation
Electrical Engineering, San Jose State University
Recovering molecules from coarse-grained beads: free-energy-conditioned generative backmapping across chemical space
Sep 3, 2026Luis Itza Vazquez-Salazar, Tristan BereauMolecular Generation Molecular Graph Generation
Institute for Theoretical Physics, Heidelberg University, Heidelberg, Germany. · Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, Heidelberg, Germany.

Oct 29, 2026J/K move · Enter open · S save

Multi-Solution Inverse Design of Pixelated Patch Antennas Using an Autoregressive Transformer

Young-Mok Yun, Seung-Won Shin, Jaeyong Chung, Kyung-Sik Choi

Department of System Semiconductor Engineering, Yonsei University, Seoul 03722, South Korea.

Inverse Design Inverse Problems Autoregressive Transformer

Open paper AskPDF arXiv

Deep-learning-based inverse design has emerged as a promising framework for pixelated patch antenna synthesis by enabling broader exploration of discrete geometry spaces and reducing design time compared with conventional template-based methods. Existing methods, including surrogate-assisted metaheuristic optimization, tandem inverse networks, and diffusion models, have advanced the field but still face practical limitations. Metaheuristic methods such as binary particle swarm optimization (BPSO) are sensitive to initialization and search hyperparameters and are often time-consuming, tandem networks have difficulty capturing the one-to-many nature of inverse antenna design, and diffusion models may require excessive complexity and data for moderate-scale binary layout synthesis. In this paper, an autoregressive (AR) transformer is presented for the inverse design of 10 x 10 pixelated patch antennas. Its sequential discrete generation process enables the synthesis of multiple feasible structures for a given target response. The pretrained model is further fine-tuned for dual-band design using step-shaped target responses with sharp spectral transitions, allowing intuitive band specification without manually constructing detailed S11 curves. Compared with BPSO, our proposed method generates valid and diverse antenna candidates more efficiently. Fabricated and measured examples confirm that distinct pixelated layouts can realize the desired antenna responses, thereby demonstrating the multi-solution capability of the proposed framework.