arXiv subjects

Hyeyoon Lee

Publications and source records attributed to Hyeyoon Lee.

9 recordsLinked to original sources

arXiv2026

TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information

Existing GNN quantization methods suffer from considerable quantization overhead, which severely limits their practical usage in real-world scenarios. To this end, we present TopGQ, an accurate post-training GNN quantization framework, alleviating redundant quantization overhead. We propose dual-axis scale absorption, which enables activation quantization along both the outer and inner dimensions by merging one into the adjacency matrix. On top of that, we introduce TopPIN, a proxy for nodes' local structure, and use it to group nodes with similar topology during quantization. Experimental results show that TopGQ reduces quantization time by an order of magnitude while preserving accuracy.

cs.LG↗

arXiv2026

SePArate: Segmenting Patterns from Defects in Wafer Manufacturing Using Weak Supervision

In semiconductor manufacturing, defect analysis is essential, but manual inspection cannot scale. However, existing automated inspection methods remain insufficient for root-cause analysis and process optimization. To this end, we present SePArate, a weakly supervised wafer defect segmentation method. SePArate enables pixel-level separation of patterns by leveraging only image-level annotations. It consists of a three-phase training: encoder pretraining, knowledge transfer to learn spatial cues, and training on synthetic mixed-defect data for accurate segmentation. Experiments demonstrate that SePArate outperforms the baselines.

cs.CV↗

arXiv2026

STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation

The rapid expansion of low Earth orbit satellites such as Starlink is increasingly contaminating astronomical surveys. In practice, contaminated images are often identified through inspection. However, modern surveys generate terabytes of data each night, making manual screening infeasible and necessitating reliable automated methods for satellite trail removal. Unfortunately, existing general-domain line detection methods fail to generalize to astronomical images due to domain mismatch, which are mostly grayscale with sparse bright stars and have a low signal-to-noise ratio. Moreover, training new models from scratch is impractical due to the lack of large-scale annotated astronomical datasets. To address these challenges, we introduce STARLINC, the first ML-based framework for satellite trail removal without requiring tedious pixel-level annotation of astronomical images. STARLINC combines synthetic satellite trail generation for training, inter-frame differential maps from temporally adjacent exposures to highlight transient trails, and heatmaps to provide additional localization cues for pixel-level segmentation. Extensive experiments on real-world data demonstrate substantial improvements over baselines, establishing STARLINC as a scalable solution for next-generation astronomical surveys. Code is available at https://github.com/starioKim/STARLINC.

cs.CV↗

arXiv2026

7DT Insight: Variability in Young Stellar Objects

Photometric variability in young stellar objects (YSOs) provides critical insight into the mechanisms of mass accretion, disk evolution, and circumstellar extinction in early stellar evolution. We present an analysis of day-timescale optical variability in the Orion A central region using two-night 7-Dimensional Telescope (7DT) medium-band photometry obtained on March 23 and 24, 2024. The 7DT observations provide optical spectral sampling with 16 medium-band filters spanning 400--825 nm, enabling direct two-epoch comparisons. To remove satellite-trail contamination, we used an SSIM-based ResNet classifier (accuracy 0.97; F1 = 0.93) to exclude affected exposures. Subsequent photometry and two-epoch variability measurements yielded a working sample of 769 YSO candidates, among which we identified 110 variables ($\sim$14\%), including seven extreme cases with $|\Delta m_\lambda|>0.5$ mag. To describe the wavelength dependence of the variability, we compared five simple templates: extinction-like changes ($R_V =$ 3.1 and 5.5), a gray (wavelength-independent) change, and two spot-like toy models (hot and cold) implemented as two-temperature surface mixtures. The best-fit results are dominated by spot-like templates (37 cold-spot and 22 hot-spot objects), with 37 sources best matched by extinction-like templates and 14 by the gray template. The m650 excess fraction is higher in the hot-spot and gray templates than in the others. This could be compatible with more frequent line/veiling-related contributions in those groups, although the m650 excess is not a direct accretion diagnostic.

astro-ph.SR↗

arXiv2025

Refined classification of YSOs and AGB stars by IR magnitudes, colors, and time-domain analysis with machine learning

We introduce a binary classification model, {\it the Double Filter Model}, utilizing various machine learning and deep learning methods to classify Young Stellar Objects (YSOs) and Asymptotic Giant Branch (AGB) stars. Since YSOs and AGB stars share similar infrared (IR) photometric characteristics due to comparable temperatures and the presence of circumstellar dust, distinguishing them is challenging and often leads to misclassification. While machine learning and deep learning techniques have helped reduce YSO-AGB misclassifications, achieving a reliable separation remains challenging. Given that YSOs and AGB stars exhibit distinct light curves resulting from different variability mechanisms, our Double Filter Model leverages light curve data to enhance classification accuracy. This approach uncovered YSOs and AGB stars that were misclassified in IR photometry and was validated against Taurus YSOs and spectroscopically confirmed AGB stars. We applied the model to the {\it Spitzer/IRAC Candidate YSO Catalog for the Inner Galactic Midplane} (SPICY) catalog for catalog refinement and identified potential AGB star contaminants.

astro-ph.SR↗

arXiv2025

FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic

Low-bit floating-point (FP) formats, such as FP8, provide significant acceleration and memory savings in model training thanks to native hardware support on modern GPUs and NPUs. However, we analyze that FP8 quantization offers speedup primarily for large-dimensional matrix multiplications, while inherent quantization overheads diminish speedup when applied to low-rank adaptation (LoRA), which uses small-dimensional matrices for efficient fine-tuning of large language models (LLMs). To address this limitation, we propose FALQON, a novel framework that eliminates the quantization overhead from separate LoRA computational paths by directly merging LoRA adapters into an FP8-quantized backbone during fine-tuning. Furthermore, we reformulate the forward and backward computations for merged adapters to significantly reduce quantization overhead, and introduce a row-wise proxy update mechanism that efficiently integrates substantial updates into the quantized backbone. Experimental evaluations demonstrate that FALQON achieves approximately a 3$\times$ training speedup over existing quantized LoRA methods with a similar level of accuracy, providing a practical solution for efficient large-scale model fine-tuning. Moreover, FALQON's end-to-end FP8 workflow removes the need for post-training quantization, facilitating efficient deployment. Code is available at https://github.com/iamkanghyunchoi/falqon.

cs.LG↗

arXiv2024

DataFreeShield: Defending Adversarial Attacks without Training Data

Recent advances in adversarial robustness rely on an abundant set of training data, where using external or additional datasets has become a common setting. However, in real life, the training data is often kept private for security and privacy issues, while only the pretrained weight is available to the public. In such scenarios, existing methods that assume accessibility to the original data become inapplicable. Thus we investigate the pivotal problem of data-free adversarial robustness, where we try to achieve adversarial robustness without accessing any real data. Through a preliminary study, we highlight the severity of the problem by showing that robustness without the original dataset is difficult to achieve, even with similar domain datasets. To address this issue, we propose DataFreeShield, which tackles the problem from two perspectives: surrogate dataset generation and adversarial training using the generated data. Through extensive validation, we show that DataFreeShield outperforms baselines, demonstrating that the proposed method sets the first entirely data-free solution for the adversarial robustness problem.

cs.LG↗

arXiv2023

Slice-and-Forge: Making Better Use of Caches for Graph Convolutional Network Accelerators

Graph convolutional networks (GCNs) are becoming increasingly popular as they can process a wide variety of data formats that prior deep neural networks cannot easily support. One key challenge in designing hardware accelerators for GCNs is the vast size and randomness in their data access patterns which greatly reduces the effectiveness of the limited on-chip cache. Aimed at improving the effectiveness of the cache by mitigating the irregular data accesses, prior studies often employ the vertex tiling techniques used in traditional graph processing applications. While being effective at enhancing the cache efficiency, those approaches are often sensitive to the tiling configurations where the optimal setting heavily depends on target input datasets. Furthermore, the existing solutions require manual tuning through trial-and-error or rely on sub-optimal analytical models. In this paper, we propose Slice-and-Forge (SnF), an efficient hardware accelerator for GCNs which greatly improves the effectiveness of the limited on-chip cache. SnF chooses a tiling strategy named feature slicing that splits the features into vertical slices and processes them in the outermost loop of the execution. This particular choice results in a repetition of the identical computational patterns over irregular graph data over multiple rounds. Taking advantage of such repetitions, SnF dynamically tunes its tile size. Our experimental results reveal that SnF can achieve 1.73x higher performance in geomean compared to prior work on multi-engine settings, and 1.46x higher performance in geomean on small scale settings, without the need for off-line analyses.

cs.LG↗

arXiv2020

Deep Composer Classification Using Symbolic Representation

In this study, we train deep neural networks to classify composer on a symbolic domain. The model takes a two-channel two-dimensional input, i.e., onset and note activations of time-pitch representation, which is converted from MIDI recordings and performs a single-label classification. On the experiments conducted on MAESTRO dataset, we report an F1 value of 0.8333 for the classification of 13~classical composers.

cs.SD↗