activity
20242026
collaborators

6 papers

cs.CV2026

VLM-Aware Meta-Optic Front-End Design for Frozen Vision-Language Models

Chanik Kang, Raphaël Pestourie, Haejun Chung

Conventional machine-vision pipelines typically rely on high-quality optics that produce clean, human-interpretable images, and optical design has therefore been driven by image-le…

cs.LG2026

Neural Adjoint Method for Meta-optics: Accelerating Volumetric Inverse Design via Fourier Neural Operators

Chanik Kang, Hyewon Suk, Haejun Chung

Meta-optics promises compact, high-performance imaging and color routing. However, designing high-performance structures is a high-dimensional optimization problem: mapping a desir…

cs.LG2025

Generalizing Deep Surrogate Solvers for Broadband Electromagnetic Field Prediction at Unseen Wavelengths

Joonhyuk Seo, Chanik Kang, Dongjin Seo +1

Recently, electromagnetic surrogate solvers, trained on solutions of Maxwell's equations under specific simulation conditions, enabled fast inference of computationally expensive s…

physics.optics2025

Inverse-Designed Metasurfaces for Wavefront Restoration in Under-Display Camera Systems

Jaegang Jo, Myunghoo Lee, Seunghyun Lee +3

Under-display camera (UDC) systems enable full-screen displays in smartphones by embedding the camera beneath the display panel, eliminating the need for notches or punch holes. Ho…

physics.optics2025

Inverse design of ultrathin metamaterial absorber

Eunbi Jang, Junghee Cho, Chanik Kang +1

Electromagnetic absorbers combining ultrathin profiles with robust absorptivity across wide incidence angles are essential for applications such as stealth technology, wireless com…

physics.optics2024

Deep-learning-driven end-to-end metalens imaging

Joonhyuk Seo, Jaegang Jo, Joohoon Kim +7

Recent advances in metasurface lenses (metalenses) have shown great potential for opening a new era in compact imaging, photography, light detection and ranging (LiDAR), and virtua…