arXiv subjects

Ali Adibi

Publications and source records attributed to Ali Adibi.

At least 19 recordsLinked to original sources

arXiv2026

GazeRIB: Systematic Evaluation of Multi-Reader Gaze-Guided Chest X-ray Learning

Radiologists' visual attention can supervise medical image learning, but how reader panel composition affects its value remains untested. We evaluated GazeRIB (Gaze-guided Radiologist-Informed Blackout), which masks unviewed regions during training and uses unmasked images at inference. Eight experts repeatedly read the same 80 chest X-rays (CXRs). We compared individual readers with three-, five- and eight-reader panels across seven architectures and 10 seeds, evaluating 910 models on a separate 2,897-CXR cohort for four-class severity prediction. Every panel improved macro F1 over the no-gaze baseline by 5.33-7.47 percentage points (pp; Bonferroni-adjusted p < 0.007); no individual reader reached significance on this endpoint. Three readers captured 73-80% of the eight-reader gain in macro F1, the area under the receiver-operating-characteristic curve (ROC-AUC) and the area under the precision-recall curve (AU-PRC). On external validation without retraining, all four panels improved ROC-AUC on SIIM-FISABIO-RSNA by +1.93 to +4.24 pp (p <= 0.004); on MIMIC-Eye no panel differed significantly from baseline, whereas the single-reader average declined (-1.40 pp, p = 0.008). Reader composition therefore influenced performance, although transfer depended on the cohort.

cs.CV↗

arXiv2026

CARDINAL Predicts Cardiovascular Risk From Non-contrast Cardiac CT

Cardiovascular risk prediction remains limited by incomplete clinical data and imaging biomarkers that reduce computed tomography (CT) to a small number of handcrafted features. We developed CARDINAL (Cardiovascular Assessment via Representation learning from Deep Imaging with Nested Anatomical Latent embeddings), a clinically grounded framework that learns compact representations from routine non-contrast cardiac CT for major adverse cardiovascular event (MACE) prediction. In 17,659 patients, CARDINAL was evaluated for 1-, 3-, 5-, and 10-year MACE prediction against American Heart Association (AHA) pooled cohort equations (PCE), AHA predicting risk of cardiovascular disease events (PREVENT), coronary artery calcium (CAC), segmentation-derived CT biomarkers, and 70-feature structural radiomics. Gains were largest at longer horizons. At 10 years, CARDINAL (joint) achieved an area under the receiver operating characteristic curve (AUROC) of 0.866 $\pm$ 0.020 and an area under the precision-recall curve (AUPRC) of 0.890 $\pm$ 0.015, compared with an AUROC of 0.826 $\pm$ 0.023 and an AUPRC of 0.826 $\pm$ 0.022 for structural radiomics, the strongest baseline. CARDINAL also achieved the highest survival concordance index (C-index), 0.753 $\pm$ 0.015, and high-versus-low risk-tertile hazard ratio, 10.78 $\pm$ 3.16, with favorable reclassification and exploratory calibration. These findings suggest that non-contrast cardiac CT contains prognostic information beyond conventional risk equations, CAC scoring, and engineered imaging biomarkers.

eess.IV↗

arXiv2026

Bayesian Optimization for Function-Valued Responses under Min-Max Criteria

Bayesian optimization is widely used for optimizing expensive black box functions, but most existing approaches focus on scalar responses. In many scientific and engineering settings the response is functional, varying smoothly over an index such as time or wavelength, which makes classical formulations inadequate. Existing methods often minimize integrated error, which captures average performance but neglects worst case deviations. To address this limitation we propose min-max Functional Bayesian Optimization (MM-FBO), a framework that directly minimizes the maximum error across the functional domain. Functional responses are represented using functional principal component analysis, and Gaussian process surrogates are constructed for the principal component scores. Building on this representation, MM-FBO introduces an integrated uncertainty acquisition function that balances exploitation of worst case expected error with exploration across the functional domain. We provide two theoretical guarantees: a discretization bound for the worst case objective, and a consistency result showing that as the surrogate becomes accurate and uncertainty vanishes, the acquisition converges to the true min-max objective. We validate the method through experiments on synthetic benchmarks and physics inspired case studies involving electromagnetic scattering by metaphotonic devices and vapor phase infiltration. Results show that MM-FBO consistently outperforms existing baselines and highlights the importance of explicitly modeling functional uncertainty in Bayesian optimization.

cs.LG↗

arXiv2026

GiBS: Generative Input-side Basis-driven Structures

Designing large-scale metasurfaces with nonlocal optical effects remains challenging due to the immense dimensionality and fabrication constraints of conventional optimization methods. We introduce GiBS (Generative Input-side Basis-driven Structures), an inverse-design framework that represents the entire device using a compact set of coefficients from smooth parametric bases such as Fourier or Chebyshev functions. This formulation compresses the design space by more than an order of magnitude, enabling efficient optimization of complex, broadband, and aperiodic geometries. GiBS integrates this low-dimensional representation with an autoencoder-based manifold-learning workflow to map the relationship between geometry and optical response, facilitating rapid exploration, discovery of high-performance designs, and systematic analysis of fabrication sensitivity. The inherent smoothness of the basis functions ensures manufacturability while capturing the asymmetry required for nonlocal optical interactions. We experimentally validated the framework through the realization of a PEDOT:PSS broadband scattering metasurface, whose measured response closely matched full-wave simulations across 500-1100 nm. These results establish GiBS as a scalable, data-efficient, and fabrication-aware platform for the inverse design of multifunctional metasurfaces, bridging AI-guided representation learning with experimentally realizable photonic architectures.

physics.optics↗

arXiv2026

Systematic Design and Demonstration of Multipole, Coupled-Cavity Integrated Photonic Bandpass Filters with High FSR, High-Q Single-Mode Microresonators in Low-Loss Silicon Nitride Platform

Tunable, low-loss, narrowband, and frequency-stabilized filters play a critical role in the realization of transceivers for efficient signal processing in telecommunications and sensing applications in the presence of strong interference and noise. We systematically design, fabricate, and demonstrate multi-cavity, multipole integrated photonic bandpass filters with gigahertz to sub-gigahertz bandwidths. The filters feature ultra-wideband tunable center frequencies exceeding 400 GHz, ultra-low insertion loss, steep roll-off, and compact footprints, making them suitable for radio-frequency, microwave, and millimeter-wave front-end applications. Using a set of design principles for multi-cavity high-order filters together with supporting nanofabrication techniques in a silicon nitride platform, the demonstrated filters achieve record-high figures of merit and advance the state of the art in integrated photonic filtering for radio-frequency, microwave, and millimeter-wave systems. The resonator structures, which are the key building blocks enabling the reported performance, combine a large free spectral range of approximately 70 GHz with a high quality factor of 2.1 times ten to the power of seven. This performance is enabled by combining wide multimode waveguide segments with narrow single-mode regions connected through adiabatic tapers. To the best of our knowledge, the experimentally demonstrated bandwidth of 520 MHz, tuning range of one free spectral range, filter insertion loss of 2 dB, and out-of-band rejection ratios of up to 55 dB represent record performance metrics for integrated photonic filtering of radio-frequency, millimeter-wave, and terahertz signals.

physics.optics↗

arXiv2026

Planar Scale Invariant Waveguides and Resonators with Uniform Air Confined Modes

We demonstrate a planar metamaterial based resonator and waveguide with strong light confinement in air based on a silicon-on-insulator (SOI) platform that exhibits scale invariance in the lateral direction. By embedding a sub wavelength grating (SWG) region between two silicon ridges, the waveguide maintains a nearly constant effective index across varying widths while sustaining a uniform field distribution. Simulations and experimental measurements using Mach Zehnder interferometers confirm scale invariance, and racetrack resonators fabricated from the same structure exhibit an intrinsic quality factor of 40000. The ability of the resonance based structures for confining light in air, providing large interaction regions with high quality factors along with compatibility with CMOS fabrication processes and robustness against fabrication imperfections make them excellent candidates for enhanced light matter interaction applications with improved power handling, offering a promising platform for integrated photonics.

physics.optics↗

arXiv2025

Inverse Design in Nanophotonics via Representation Learning

Inverse design in nanophotonics, the computational discovery of structures achieving targeted electromagnetic (EM) responses, has become a key tool for recent optical advances. Traditional intuition-driven or iterative optimization methods struggle with the inherently high-dimensional, non-convex design spaces and the substantial computational demands of EM simulations. Recently, machine learning (ML) has emerged to address these bottlenecks effectively. This review frames ML-enhanced inverse design methodologies through the lens of representation learning, classifying them into two categories: output-side and input-side approaches. Output-side methods use ML to learn a representation in the solution space to create a differentiable solver that accelerates optimization. Conversely, input-side techniques employ ML to learn compact, latent-space representations of feasible device geometries, enabling efficient global exploration through generative models. Each strategy presents unique trade-offs in data requirements, generalization capacity, and novel design discovery potentials. Hybrid frameworks that combine physics-based optimization with data-driven representations help escape poor local optima, improve scalability, and facilitate knowledge transfer. We conclude by highlighting open challenges and opportunities, emphasizing complexity management, geometry-independent representations, integration of fabrication constraints, and advancements in multiphysics co-designs.

physics.app-ph↗

arXiv2025

HiLAB: A Hybrid Inverse-Design Framework

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.

physics.optics↗

arXiv2025

Deep Active Learning for Lung Disease Severity Classification from Chest X-rays: Learning with Less Data in the Presence of Class Imbalance

To reduce the amount of required labeled data for lung disease severity classification from chest X-rays (CXRs) under class imbalance, this study applied deep active learning with a Bayesian Neural Network (BNN) approximation and weighted loss function. This retrospective study collected 2,319 CXRs from 963 patients (mean age, 59.2 $\pm$ 16.6 years; 481 female) at Emory Healthcare affiliated hospitals between January and November 2020. All patients had clinically confirmed COVID-19. Each CXR was independently labeled by 3 to 6 board-certified radiologists as normal, moderate, or severe. A deep neural network with Monte Carlo Dropout was trained using active learning to classify disease severity. Various acquisition functions were used to iteratively select the most informative samples from an unlabeled pool. Performance was evaluated using accuracy, area under the receiver operating characteristic curve (AU ROC), and area under the precision-recall curve (AU PRC). Training time and acquisition time were recorded. Statistical analysis included descriptive metrics and performance comparisons across acquisition strategies. Entropy Sampling achieved 93.7% accuracy (AU ROC, 0.91) in binary classification (normal vs. diseased) using 15.4% of the training data. In the multi-class setting, Mean STD sampling achieved 70.3% accuracy (AU ROC, 0.86) using 23.1% of the labeled data. These methods outperformed more complex and computationally expensive acquisition functions and significantly reduced labeling needs. Deep active learning with BNN approximation and weighted loss effectively reduces labeled data requirements while addressing class imbalance, maintaining or exceeding diagnostic performance.

eess.IV↗

arXiv2025

PolitiSky24: U.S. Political Bluesky Dataset with User Stance Labels

Stance detection identifies the viewpoint expressed in text toward a specific target, such as a political figure. While previous datasets have focused primarily on tweet-level stances from established platforms, user-level stance resources, especially on emerging platforms like Bluesky remain scarce. User-level stance detection provides a more holistic view by considering a user's complete posting history rather than isolated posts. We present the first stance detection dataset for the 2024 U.S. presidential election, collected from Bluesky and centered on Kamala Harris and Donald Trump. The dataset comprises 16,044 user-target stance pairs enriched with engagement metadata, interaction graphs, and user posting histories. PolitiSky24 was created using a carefully evaluated pipeline combining advanced information retrieval and large language models, which generates stance labels with supporting rationales and text spans for transparency. The labeling approach achieves 81\% accuracy with scalable LLMs. This resource addresses gaps in political stance analysis through its timeliness, open-data nature, and user-level perspective. The dataset is available at https://doi.org/10.5281/zenodo.15616911

cs.CL↗

arXiv2025

Photonic Crystal Microring Resonators on a Hybrid Silicon Nitride-on-Lithium Niobate Platform

Photonic-crystal resonators (PhCRs) have been widely used in nonlinear integrated photonics for frequency engineering applications. A microwave-assisted frequency converter based on PhCRs highlights its precise control of frequency (enabled by creation of a pair of supermodes by a corrugated PhCR) and bidirectional frequency conversion. In this paper, we demonstrate a high-quality PhCR on a hybrid silicon nitride-on-lithium niobate-on-insulator (SiN-on-LNOI) platform for the first time for voltage-driven flexible frequency conversion using the electro-optic effect (0.85 pm/V). The fabricated PhCR has a large supermode splitting bandwidth = 14.6 GHz and an intrinsic quality factor (Q) = 147,000. Using different periodic corrugation amplitudes in the fabricated PhCRs enables the precise control of mode splitting with a ratio of 93.5 MHz/nm between the mode splitting bandwidth and the corrugation amplitude.

physics.optics↗

arXiv2024

Ion-Assisted Nanoscale Material Engineering in Atomic Layers

Achieving deterministic control over the properties of low-dimensional materials with nanoscale precision is a long-sought goal. Mastering this capability has a transformative impact on the design of multifunctional electrical and optical devices. Here, we present an ion-assisted synthetic technique that enables precise control over the material composition and energy landscape of two-dimensional (2D) atomic crystals. Our method transforms binary transition metal dichalcogenides (TMDs), like MoSe$_2$, into ternary MoS$_{2α}$Se$_{2(1-α})$ alloys with systematically adjustable compositions, $α$. By piecewise assembly of the lateral, compositionally modulated MoS$_{2α}$Se$_{2(1-α)}$ segments within 2D atomic layers, we present a synthetic pathway towards the realization of multi-compositional designer materials. Our technique enables the fabrication of complex structures with arbitrary boundaries, dimensions as small as 30 nm, and fully customizable energy landscapes. Our optical characterizations further showcase the potential for implementing tailored optoelectronics in these engineered 2D crystals.

cond-mat.mtrl-sci↗

arXiv2022

Reconfigurable Multifunctional Metasurfaces Employing Hybrid Phase-Change Plasmonic Architecture

We present a hybrid device platform for creating an electrically reconfigurable metasurface formed by the integration of plasmonic nanostructures with phase-change material germanium antimony telluride (GST). By changing the phase of GST from amorphous to crystalline through Joule heating, a large range of responses from the metasurface can be achieved. Furthermore, by using the intermediate phases of GST, the metasurface can interact with the incident light in both over-coupling and under-coupling regimes, leading to an inherently broadband response. Through a detailed investigation of the nature of the fundamental modes, we demonstrate that changing the crystalline phase of the GST at the pixel-level enables an effective control over the key properties (i.e., amplitude, phase, and polarization) of incident light. This leads to the realization of a broadband electrically tunable multi-functional metadevice enabling beam switching, focusing, steering, and polarization conversion. Such a hybrid structure offers a high-speed, broadband, and non-volatile reconfigurable paradigm for electrically programmable optical devices such as switches, holograms, and polarimeters.

physics.optics↗

arXiv2022

Enhanced Polling and Infiltration for Highly-Efficient Electro-Optic Polymer-Based Mach-Zehnder Modulators

An ultra-narrow slot waveguide is fabricated for use in highly-efficient, electro-optic-polymer-based, integrated-optic modulators. Measurement results indicate that $V_πL$'s below 1.2 V.mm are possible for balanced Mach-Zehnder modulators using this ultra-narrow slot waveguide on a silicon-organic hybrid platform. Simulated $V_πL$'s of 0.35 V.mm have also been obtained. In addition to adapting standard recipes, we developed two novel fabrication processes for achieving miniaturized devices with high modulation sensitivity. To boost compactness and decrease the overall footprint, we use a fabrication approach based on air bridge interconnects on thick, thermally-reflowed, MaN 2410 E-beam resist protected by an alumina layer. To overcome the challenges of high currents and imperfect infiltration of polymers into ultra-narrow slots, we use a carefully designed, atomically-thin layer of TiO$_2$ as a carrier-barrier to enhance the polling efficiency of our electro-optic polymers. Additionally, finite-difference time-domain simulations are employed to optimize the effect of the thin layer of TiO$_2$. As compared to other, non-optimized, cases, our peak measured current is reduced by a factor of 3; scanning electron microscopy images also demonstrate that we achieve almost perfect infiltration. The anticipated increase in total capacitance due to the TiO$_2$ layer is shown to be negligible. In fact, applying our TiO$_2$ surface treatment to our ultra-narrow slot, allows us to obtain an improved phase shift efficiency ($\partial n / \partial V$) of $\sim$94% for a 10 nm TiO$_2$ layer.

physics.app-ph↗

arXiv2021

Enhanced Meta-Displays Using Advanced Phase-Change Materials

Structural colors generated due to light scattering from static all-dielectric metasurfaces have successfully enabled high-resolution, high-saturation, and wide-gamut color printing applications. Despite recent advances, most demonstrations of these structure-dependent colors lack post-fabrication tunability. This hinders their applicability for front-end dynamic display technologies. Phase-change materials (PCMs), with significant contrast of their optical properties between their amorphous and crystalline states, have demonstrated promising potentials in reconfigurable nanophotonics. Herein, we leverage tunable all-dielectric reflective metasurfaces made of newly emerged classes of low-loss optical PCMs, i.e., antimony trisulphide (Sb$_2$S$_3$) and antimony triselenide (Sb$_2$Se$_3$), with superb characteristics to realize switchable, high-saturation, high-efficiency and high-resolution dynamic meta-pixels. Exploiting polarization-sensitive building blocks, the presented meta-pixel can generate two different colors when illuminated by either one of two orthogonally polarized incident beams. Such degrees of freedom (i.e., material phase and polarization state) enable a single reconfigurable metasurface with fixed geometrical parameters to generate four distinct wide-gamut colors. We experimentally demonstrate, for the first time, an electrically-driven micro-scale display through the integration of phase-change metasurfaces with an on-chip heater formed by transparent conductive oxide. Our experimental findings enable a versatile platform suitable for a wide range of applications, including tunable full-color printing, enhanced dynamic displays, information encryption, and anti-counterfeiting.

physics.optics↗

arXiv2021

Advanced Phase-Change Materials for Enhanced Meta-Displays

Structural colors generated due to light scattering from static all-dielectric metasurfaces have successfully enabled high-resolution, high-saturation and wide-gamut color printing applications. Despite recent advances, most demonstrations of these structure-dependent colors lack post-fabrication tunability that hinders their applicability for front-end dynamic display technologies. Phase-change materials (PCMs), with significant contrast of their optical properties between their amorphous and crystalline states, have demonstrated promising potentials in reconfigurable nanophotonics. Herein, we leverage a tunable all-dielectric reflective metasurface made of a newly emerged class of low-loss optical PCMs with superb characteristics, i.e., antimony trisulphide (Sb$_2$S$_3$), antimony triselenide (Sb$_2$Se$_3$), and binary germanium-doped selenide (GeSe$_3$), to realize switchable, high-saturation, high-efficiency and high-resolution structural colors. Having polarization sensitive building blocks, the presented metasurface can generate two different colors when illuminated by two orthogonally polarized incident beams. Such degrees of freedom (i.e., structural state and polarization) enable a single reconfigurable metasurface with fixed geometrical parameters to generate four distinct wide-gamut colors suitable for a wide range of applications, including tunable full-color printing and displays, information encryption, and anti-counterfeiting.

physics.optics↗

arXiv2021

Electrically driven programmable phase-change meta-switch reaching 80% efficiency

Despite recent advances in active metaoptics, wide dynamic range combined with high-speed reconfigurable solutions is still elusive. Phase-change materials (PCMs) offer a compelling platform for metasurface optical elements, owing to the large index contrast and fast yet stable phase transition properties. Here, we experimentally demonstrate an in situ electrically-driven reprogrammable metasurface by harnessing the unique properties of a phase-change chalcogenide alloy, Ge$_{2}$Sb$_{2}$Te$_{5}$ (GST), in order to realize fast, non-volatile, reversible, multilevel, and pronounced optical modulation in the near-infrared spectral range. Co-optimized through a multiphysics analysis, we integrate an efficient heterostructure resistive microheater that indirectly heats and transforms the embedded GST film without compromising the optical performance of the metasurface even after several reversible phase transitions. A hybrid plasmonic-PCM meta-switch with a record electrical modulation of the reflectance over eleven-fold (an absolute reflectance contrast reaching 80%), unprecedented quasi-continuous spectral tuning over 250 nm, and switching speed that can potentially reach a few kHz is presented. Our work represents a significant step towards the development of fully integrable dynamic metasurfaces and their potential for beamforming applications.

physics.optics↗

arXiv2021

Racetrack microresonator based electro-optic phase shifters on a 3C-silicon-carbide-on-insulator platform

We report the first demonstration of integrated electro-optic (EO) phase shifters based on racetrack microresonators on a 3C-silicon-carbide-on-insulator (SiCOI) platform working at near-infrared (NIR) wavelengths. By applying DC voltage in the crystalline axis perpendicular to the waveguide plane, we have observed optical phase shifts from the racetrack microresonators whose loaded quality (Q) factors are ~ 30,000. We show voltage length-product (V$π$${\cdot}$L$π$) of 118 V${\cdot}$cm, which corresponds to an EO coefficient r$_{41}$ of 2.6 pm/V. The SiCOI platform can be used to realize tunable SiC integrated photonic devices that are desirable for applications in nonlinear and quantum photonics over a wide bandwidth that covers visible and infrared wavelengths.

physics.optics↗