# HiLAB: A Hybrid Inverse-Design Framework

arXiv: https://arxiv.org/abs/2505.17491 · HTML: https://mlsanity.com/paper/2505.17491/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 62 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 13 of 13)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [Visual Transformers: Token-based Image Representation and Processing for Computer Vision](https://mlsanity.com/paper/2006.03677/) (2020)
- [Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification](https://mlsanity.com/paper/1802.00850/) (2018)
- [Global optimization of dielectric metasurfaces using a physics-driven neural network](https://mlsanity.com/paper/1906.04157/) (2019)
- [A Generative Model for Inverse Design of Metamaterials](https://mlsanity.com/paper/1805.10181/) (2018)
- [Physics-enhanced deep surrogates for partial differential equations](https://mlsanity.com/paper/2111.05841/) (2021)
- [Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials](https://mlsanity.com/paper/1902.06836/) (2019)
- [Deep learning approach based on dimensionality reduction for designing electromagnetic nanostructures](https://mlsanity.com/paper/1902.03865/) (2019)
- [End-to-end metasurface inverse design for single-shot multi-channel imaging](https://mlsanity.com/paper/2111.01071/) (2021)

## Built on by (most cited first, 6 of 6)

- [Inverse Design in Nanophotonics via Representation Learning](https://mlsanity.com/paper/2507.00546/) (2025)
- [Harnessing AI for Inverse Partial Differential Equation Problems: Past, Present, and Prospects](https://mlsanity.com/paper/2605.16966/) (2026)
- [Physics Enhanced Deep Surrogates for the Phonon Boltzmann Transport Equation](https://mlsanity.com/paper/2512.05976/) (2025)
- [Bayesian Optimization for Function-Valued Responses under Min-Max Criteria](https://mlsanity.com/paper/2512.07868/) (2025)
- [Field-Space Autoencoder for Scalable Climate Emulators](https://mlsanity.com/paper/2601.15102/) (2026)
- [Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization](https://mlsanity.com/paper/2607.07682/) (2026)

## Abstract (arXiv)

HiLAB (Hybrid inverse-design with Latent-space learning, Adjoint-based partial optimizations, and Bayesian optimization) is a new paradigm for inverse design of nanophotonic structures. Combining early-terminated topological optimization (TO) with a Vision Transformer-based variational autoencoder (VAE) and a Bayesian search, HiLAB addresses multi-functional device design by generating diverse freeform configurations at reduced simulation costs. Shortened adjoint-driven TO runs, coupled with randomized physical parameters, produce robust initial structures. These structures are compressed into a compact latent space by the VAE, enabling Bayesian optimization to co-optimize geometry and physical hyperparameters. Crucially, the trained VAE can be reused for alternative objectives or constraints by adjusting only the acquisition function. Compared to conventional TO pipelines prone to local optima, HiLAB systematically explores near-global optima with considerably fewer electromagnetic simulations. Even after accounting for training overhead, the total number of full simulations decreases by over an order of magnitude, accelerating the discovery of fabrication-friendly devices. Demonstrating its efficacy, HiLAB is used to design an achromatic beam deflector for red, green, and blue wavelengths, achieving balanced diffraction efficiencies of ~25% while mitigating chromatic aberrations-a performance surpassing existing demonstrations. Overall, HiLAB provides a flexible platform for robust, multi-parameter photonic designs and rapid adaptation to next-generation nanophotonic challenges.