arXiv subjects

Sangwon Lee

Publications and source records attributed to Sangwon Lee.

At least 19 recordsLinked to original sources

arXiv2026

On Controlling the Effect of Error Growth in Unlimited Encrypted Iterative Learning Control

This paper proposes a Ring Learning With Errors (Ring-LWE) based encrypted iterative learning control (ILC) framework for repetitive tracking tasks over networked control systems. The architecture integrates an encrypted dynamic feedback controller with an encrypted ILC computation. During each trial, the feedback controller is evaluated in the ciphertext domain, and the encrypted output trajectory is stored directly in the cloud. After each trial, the cloud evaluates the tracking error and performs the ILC computation from the stored ciphertexts, so that the plant side does not need to store the accumulated trial data. The proposed framework uses distinct packing parameters for ciphertext multiplication, allowing the cloud to handle both lower-dimensional output feedback control and higher-dimensional ILC computation without decryption. While error growth in Ring-LWE based encrypted control is generally suppressed by closed-loop stability, the marginally stable ILC iterations cause the injected errors to accumulate continuously. To address this challenge, a range-space decomposition is introduced in the encrypted ILC formulation to allow evaluation under unlimited updates. Numerical simulations show that the range-space decomposition suppresses encryption-induced perturbation, while ciphertext packing improves the computational efficiency of the encrypted ILC update.

eess.SY↗

arXiv2026

AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation

Visuomotor manipulation policies trained via large-scale behavior cloning have achieved strong semantic scene understanding, yet often fail to reliably execute correct low-level actions under distribution shifts. For example, even in a simple pickup task with identical scene layouts, camera viewpoints, and illumination, performance can degrade substantially when the object is placed at unseen locations. We argue that this gap arises from insufficient action understanding, namely the inability to interpret the robot's base-frame action coordinate system in image space. To address this issue, we introduce AxisGuide, a lightweight guidance method that bridges semantic scene understanding and action-coordinate interpretation. Using camera parameters and end-effector poses, AxisGuide renders the robot base-frame axes in each camera view and augments RGB observations with a small set of cue channels that explicitly visualize the meaning of the +x, +y, and +z motions in image space. Extensive evaluations in both the LIBERO simulation and real-world environments demonstrate that AxisGuide yields substantial performance gains and improved generalization, highlighting the effectiveness of explicit action-coordinate cues for learning reliable and transferable generalist visuomotor policies.

cs.RO↗

arXiv2026

Finite element model updating of building structures under seismic excitation: A parallelized latent space-based Bayesian framework

Enhancing seismic fragility and risk assessment of nuclear power plants relies on accurate prediction of reactor building responses to seismic hazards, which can be further improved through dynamic analysis of high-fidelity finite element (FE) models. However, FE models often exhibit non-negligible discrepancies from actual structures due to various sources of uncertainty, necessitating FE model updating with rigorous quantification of associated uncertainties. This paper presents a GPU-accelerated latent space--based Bayesian framework for FE model updating of building structures. In the proposed framework, high-dimensional structural response data (e.g., time histories or frequency response functions) are projected into a low-dimensional latent space using a multimodal variational autoencoder (MVAE), thereby enabling efficient and tractable likelihood evaluation without explicit modeling in the original observation space. Once trained, the surrogate enables amortized inference, allowing posterior sampling to be performed without additional simulator evaluations. We specifically employ a sequential Monte Carlo (SMC) sampler, whose population-based formulation allows parallel evaluation of the approximate likelihood on GPUs, resulting in computational efficiency and robustness against multimodal and complex posterior distributions. The proposed framework is validated through both numerical benchmarking and experimental data from a shaking table test of a reinforced concrete building structure. The results demonstrate that the method accurately estimates structural parameters with well-quantified uncertainties, while achieving fast and efficient inference through GPU-based parallelization, and enabling robust inference even in the presence of sparse observations that induce multimodal and highly complex posterior distributions.

stat.AP↗

arXiv2026

AutoGNN: End-to-End Hardware-Driven Graph Preprocessing for Enhanced GNN Performance

Graph neural network (GNN) inference faces significant bottlenecks in preprocessing, which often dominate overall inference latency. We introduce AutoGNN, an FPGA-based accelerator designed to address these challenges by leveraging FPGA's reconfigurability and specialized components. AutoGNN adapts to diverse graph inputs, efficiently performing computationally intensive tasks such as graph conversion and sampling. By utilizing components like adder trees, AutoGNN executes reduction operations in constant time, overcoming the limitations of serialization and synchronization on GPUs. AutoGNN integrates unified processing elements (UPEs) and single-cycle reducers (SCRs) to streamline GNN preprocessing. UPEs enable scalable parallel processing for edge sorting and unique vertex selection, while SCRs efficiently handle sequential tasks such as pointer array construction and subgraph reindexing. A user-level software framework dynamically profiles graph inputs, determines optimal configurations, and reprograms AutoGNN to handle varying workloads. Implemented on a 7$n$m enterprise FPGA, AutoGNN achieves up to 9.0$\times$ and 2.1$\times$ speedup compared to conventional and GPU-accelerated preprocessing systems, respectively, enabling high-performance GNN preprocessing across diverse datasets.

cs.AR↗

arXiv2025

Transfer Learning-Based Surrogate Modeling for Nonlinear Time-History Response Analysis of High-Fidelity Structural Models

In a performance based earthquake engineering (PBEE) framework, nonlinear time-history response analysis (NLTHA) for numerous ground motions are required to assess the seismic risk of buildings or civil engineering structures. However, such numerical simulations are computationally expensive, limiting the real-world practical application of the framework. To address this issue, previous studies have used machine learning to predict the structural responses to ground motions with low computational costs. These studies typically conduct NLTHAs for a few hundreds ground motions and use the results to train and validate surrogate models. However, most of the previous studies focused on computationally-inexpensive response analysis models such as single degree of freedom. Surrogate models of high-fidelity response analysis are required to enrich the quantity and diversity of information used for damage assessment in PBEE. Notably, the computational cost of creating training and validation datasets increases if the fidelity of response analysis model becomes higher. Therefore, methods that enable surrogate modeling of high-fidelity response analysis without a large number of training samples are needed. This study proposes a framework that uses transfer learning to construct the surrogate model of a high-fidelity response analysis model. This framework uses a surrogate model of low-fidelity response analysis as the pretrained model and transfers its knowledge to construct surrogate models for high-fidelity response analysis with substantially reduced computational cost. As a case study, surrogate models that predict responses of a 20-story steel moment frame were constructed with only 20 samples as the training dataset. The responses to the ground motions predicted by constructed surrogate model were consistent with a site-specific time-based hazard.

cs.CE↗

arXiv2025

Sensor Attack Detection Method for Encrypted State Observers

This paper proposes an encrypted state observer that is capable of detecting sensor attacks without decryption. We first design a state observer that operates over a finite field of integers with the modular arithmetic. The observer generates a residue signal that indicates the presence of attacks under sparse attack and sensing redundancy conditions. Then, we develop a homomorphic encryption scheme that enables the observer to operate over encrypted data while automatically disclosing the residue signal. Unlike our previous work restricted to single-input single-output systems, the proposed scheme is applicable to general multi-input multi-output systems. Given that the disclosed residue signal remains below a prescribed threshold, the full state can be recovered as an encrypted message.

eess.SY↗

arXiv2025

Waveform-Based Probabilistic Seismic Hazard Analysis Using Ground-Motion Generative Models

In probabilistic seismic hazard analysis (PSHA), the exceedance probability of a ground-motion intensity measure (IM) is typically evaluated. However, in recent years, dynamic response analyses using ground-motion time histories as input have been increasingly common in seismic design and risk assessment, and thus there is a growing demand for representing seismic hazard in terms of ground-motion waveforms. In this study, we propose a novel PSHA framework, referred to as waveform-based PSHA, that enables the direct evaluation of the probability distribution of ground-motion waveforms by introducing ground-motion models (GMMs) based on deep generative models (ground-motion generative models; GMGMs) into the PSHA framework. In waveform-based PSHA, seismic hazard is represented, in a Monte Carlo sense, as a set of ground-motion waveforms. We propose the formulation of such a PSHA framework as well as an algorithm for performing the required Monte Carlo simulations. Three different GMGMs based on generative adversarial networks (GANs) are constructed. After verifying the performance of each GMGM, hazard evaluations using the proposed method are conducted for two numerical examples: one assuming a hypothetical area source and the other assuming an actual site and source faults in Japan. We demonstrate that seismic hazard can be represented as a set of ground-motion waveforms, and that the IM-based hazard obtained from these waveforms is consistent with the results of conventional PSHA using GMMs. Finally, nonlinear dynamic response analyses of a building model are performed using the evaluated seismic hazard as input, and it is shown that exceedance probabilities of engineering demand parameters (EDPs) as well as hazard disaggregation with respect to EDPs can be carried out in a straightforward manner within the proposed framework.

physics.geo-ph↗

arXiv2025

MS2toImg: A Framework for Direct Bioactivity Prediction from Raw LC-MS/MS Data

Untargeted metabolomics using LC-MS/MS offers the potential to comprehensively profile the chemical diversity of biological samples. However, the process is fundamentally limited by the "identification bottleneck," where only a small fraction of detected features can be annotated using existing spectral libraries, leaving the majority of data uncharacterized and unused. In addition, the inherently low reproducibility of LC-MS/MS instruments introduces alignment errors between runs, making feature alignment across large datasets both error-prone and challenging. To overcome these constraints, we developed a deep learning method that eliminates the requirement for metabolite identification and reduces the influence of alignment inaccuracies. Here, we propose MS2toImg, a method that converts raw LC-MS/MS data into a two-dimensional images representing the global fragmentation pattern of each sample. These images are then used as direct input for a convolutional neural network (CNN), enabling end-to-end prediction of biological activity without explicit feature engineering or alignment. Our approach was validated using wild soybean samples and multiple bioactivity assays (e.g., DPPH, elastase inhibition). The MS2toImg-CNN model outperformed conventional machine learning baselines (e.g., Random Forest, PCA), demonstrating robust classification accuracy across diverse tasks. By transforming raw spectral data into images, our framework is inherently less sensitive to alignment errors caused by low instrument reproducibility, as it leverages the overall fragmentation landscape rather than relying on precise feature matching. This identification-free, image-based approach enables more robust and scalable bioactivity prediction from untargeted metabolomics data, offering a new paradigm for high-throughput functional screening in complex biological systems.

q-bio.QM↗

arXiv2025

CrimEdit: Controllable Editing for Counterfactual Object Removal, Insertion, and Movement

Recent works on object removal and insertion have enhanced their performance by handling object effects such as shadows and reflections, using diffusion models trained on counterfactual datasets. However, the performance impact of applying classifier-free guidance to handle object effects across removal and insertion tasks within a unified model remains largely unexplored. To address this gap and improve efficiency in composite editing, we propose CrimEdit, which jointly trains the task embeddings for removal and insertion within a single model and leverages them in a classifier-free guidance scheme -- enhancing the removal of both objects and their effects, and enabling controllable synthesis of object effects during insertion. CrimEdit also extends these two task prompts to be applied to spatially distinct regions, enabling object movement (repositioning) within a single denoising step. By employing both guidance techniques, extensive experiments show that CrimEdit achieves superior object removal, controllable effect insertion, and efficient object movement without requiring additional training or separate removal and insertion stages.

cs.CV↗

arXiv2025

Scene Graph-Guided Proactive Replanning for Failure-Resilient Embodied Agent

When humans perform everyday tasks, we naturally adjust our actions based on the current state of the environment. For instance, if we intend to put something into a drawer but notice it is closed, we open it first. However, many autonomous robots lack this adaptive awareness. They often follow pre-planned actions that may overlook subtle yet critical changes in the scene, which can result in actions being executed under outdated assumptions and eventual failure. While replanning is critical for robust autonomy, most existing methods respond only after failures occur, when recovery may be inefficient or infeasible. While proactive replanning holds promise for preventing failures in advance, current solutions often rely on manually designed rules and extensive supervision. In this work, we present a proactive replanning framework that detects and corrects failures at subtask boundaries by comparing scene graphs constructed from current RGB-D observations against reference graphs extracted from successful demonstrations. When the current scene fails to align with reference trajectories, a lightweight reasoning module is activated to diagnose the mismatch and adjust the plan. Experiments in the AI2-THOR simulator demonstrate that our approach detects semantic and spatial mismatches before execution failures occur, significantly improving task success and robustness.

cs.RO↗

arXiv2025

Open-Attribute Person Retrieval: Finding People Through Distinctive and Novel Attributes

Person retrieval in surveillance videos often depends on attributes described by witnesses or operators. However, the most useful cues in practice are not always common appearance descriptions (e.g., gender, clothing color), but rare and distinctive attributes that can sharply reduce the search space (e.g., holding a weapon, lying on the ground). Existing text-based person retrieval benchmarks and methods largely focus on identity-centric retrieval with common pedestrian descriptions, leaving such retrieval-critical attributes underexplored. In this paper, we introduce Open-Attribute Person Retrieval (OAPR), a practical retrieval setting that aims to retrieve all pedestrian instances matching a given attribute query, including rare or previously unseen visual concepts, regardless of identity. To support this task, we construct EPAD, an Expanded Pedestrian Attribute Dataset with 267,885 pedestrian images and a unified vocabulary of 65 attributes, including safety-critical actions, assistive devices, and object interactions that are rarely covered in prior benchmarks. We further propose GAP-CLIP, a lightweight CLIP-based framework that learns gated attribute-aware body-part representations for OAPR. Extensive experiments on EPAD demonstrate that GAP-CLIP achieves the strongest top-K retrieval performance on the full attribute space and on out-of-distribution attributes. The code and dataset are available at https://github.com/mlnjeongpark/Open-Attribute-Person-Retrieval.

cs.CV↗

arXiv2025

CXL-GPU: Pushing GPU Memory Boundaries with the Integration of CXL Technologies

This work introduces a GPU storage expansion solution utilizing CXL, featuring a novel GPU system design with multiple CXL root ports for integrating diverse storage media (DRAMs and/or SSDs). We developed and siliconized a custom CXL controller integrated at the hardware RTL level, achieving two-digit nanosecond roundtrip latency, the first in the field. This study also includes speculative read and deterministic store mechanisms to efficiently manage read and write operations to hide the endpoint's backend media latency variation. Performance evaluations reveal our approach significantly outperforms existing methods, marking a substantial advancement in GPU storage technology.

cs.AR↗

arXiv2025

CXL Topology-Aware and Expander-Driven Prefetching: Unlocking SSD Performance

Integrating compute express link (CXL) with SSDs allows scalable access to large memory but has slower speeds than DRAMs. We present ExPAND, an expander-driven CXL prefetcher that offloads last-level cache (LLC) prefetching from host CPU to CXL-SSDs. ExPAND uses a heterogeneous prediction algorithm for prefetching and ensures data consistency with CXL.mem's back-invalidation. We examine prefetch timeliness for accurate latency estimation. ExPAND, being aware of CXL multi-tiered switching, provides end-to-end latency for each CXL-SSD and precise prefetch timeliness estimations. Our method reduces CXL-SSD reliance and enables direct host cache access for most data. ExPAND enhances graph application performance and SPEC CPU's performance by 9.0$\times$ and 14.7$\times$, respectively, surpassing CXL-SSD pools with diverse prefetching strategies.

cs.AR↗

arXiv2025

Data augmentation using diffusion models to enhance inverse Ising inference

Identifying model parameters from observed configurations poses a fundamental challenge in data science, especially with limited data. Recently, diffusion models have emerged as a novel paradigm in generative machine learning, capable of producing new samples that closely mimic observed data. These models learn the gradient of model probabilities, bypassing the need for cumbersome calculations of partition functions across all possible configurations. We explore whether diffusion models can enhance parameter inference by augmenting small datasets. Our findings demonstrate this potential through a synthetic task involving inverse Ising inference and a real-world application of reconstructing missing values in neural activity data. This study serves as a proof-of-concept for using diffusion models for data augmentation in physics-related problems, thereby opening new avenues in data science.

physics.data-an↗

arXiv2024

Three-dimensional nucleation and growth of deformation twins in magnesium

At two-thirds the weight of aluminum, magnesium alloys have the potential to significantly reduce the fuel consumption of transportation vehicles. These advancements depend on our ability to optimize the desirable versus undesirable effects of deformation twins: three dimensional (3D) microstructural domains that form under mechanical stresses. Previously only characterized using surface or thin-film measurements, here, we present the first 3D in-situ characterization of deformation twinning inside an embedded grain over mesoscopic fields of view using dark-field X-ray microscopy supported by crystal plasticity finite element analysis. The results reveal the important role of triple junctions on twin nucleation, that twin growth behavior is irregular and can occur in several directions simultaneously, and that twin-grain and twin-twin junctions are the sites of localized dislocation accumulation, a necessary precursor to crack initiation.

cond-mat.mtrl-sci↗

arXiv2024

Latent Space-based Stochastic Model Updating

Model updating of engineering systems inevitably involves handling both aleatory or inherent randomness and epistemic uncertainties or uncertainities arising from a lack of knowledge or information about the system. Addressing these uncertainties poses significant challenges, particularly when data and simulations are limited. This study proposes a novel latent space-based method for stochastic model updating that leverages limited data to effectively quantify uncertainties in engineering applications. By extending the latent space-based approach to multiobservation and multisimulation frameworks, the proposed method circumvents the need for probability estimations at each iteration of MCMC, relying instead on an amortized probabilistic model trained using a variational autoencoder (VAE). This method was validated through numerical experiments on a two-degree-of-freedom shear spring model, demonstrating superior efficiency and accuracy compared to existing methods in terms of uncertainty quantification (UQ) metrics, such as Bhattacharyya and Euclidean distances. Moreover, the applicability of the method to time-series data was verified using the model calibration problem of the NASA UQ Challenge 2019. The results underscore the potential of the latent space-based method in practical engineering applications, providing a robust framework for uncertainty quantification with fewer data requirements, and demonstrating its effectiveness in handling high-dimensional data.

stat.AP↗

arXiv2024

Bayesian Structural Model Updating with Multimodal Variational Autoencoder

A novel framework for Bayesian structural model updating is presented in this study. The proposed method utilizes the surrogate unimodal encoders of a multimodal variational autoencoder (VAE). The method facilitates an approximation of the likelihood when dealing with a small number of observations. It is particularly suitable for high-dimensional correlated simultaneous observations applicable to various dynamic analysis models. The proposed approach was benchmarked using a numerical model of a single-story frame building with acceleration and dynamic strain measurements. Additionally, an example involving a Bayesian update of nonlinear model parameters for a three-degree-of-freedom lumped mass model demonstrates computational efficiency when compared to using the original VAE, while maintaining adequate accuracy for practical applications.

stat.ML↗

arXiv2024

Site-Specific Ground Motion Generative Model for Crustal Earthquakes in Japan Based on Generative Adversarial Networks

We develop a site-specific ground-motion model (GMM) for crustal earthquakes in Japan that can directly model the probability distribution of ground motion acceleration time histories based on generative adversarial networks (GANs). The proposed model can generate ground motions conditioned on moment magnitude, rupture distance, and detailed site conditions defined by the average shear-wave velocity in the top 5 m, 10 m, and 20 m ($V_{\mathrm{S}5}$, $V_{\mathrm{S}10}$, $V_{\mathrm{S}20}$) and the depth to shear-wave velocities of 1.0 km/s and 1.4 km/s ($Z_{1.0}$, $Z_{1.4}$). We construct the neural networks based on styleGAN2 and introduce a novel neural network architecture to generate ground motions considering the effect of source, path, and such detailed site conditions. 5% damped spectral acceleration of ground motions generated by the proposed GMM is consistent with empirical GMMs in terms of magnitude and distance scaling. The proposed GMM can also generate ground motions accounting for the shear-wave velocity profiles of surface soil with different magnitudes and distances, and represent characteristic that are not explained solely by $V_{\mathrm{S}30}$.

physics.geo-ph↗