6 citations · 12 across the 10 of their papers we have counts for
11 papers
SePArate: Segmenting Patterns from Defects in Wafer Manufacturing Using Weak Supervision
Dain Kwon, Changmin Shin, Sunjong Park +5
In semiconductor manufacturing, defect analysis is essential, but manual inspection cannot scale. However, existing automated inspection methods remain insufficient for root-cause…
TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
Dain Kwon, Kanghyun Choi, Hyeyoon Lee +4
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…
STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation
Shingeon Kim, Hyeyoon Lee, Dain Kwon +5
The rapid expansion of low Earth orbit satellites such as Starlink is increasingly contaminating astronomical surveys. In practice, contaminated images are often identified through…
7DT Insight: Variability in Young Stellar Objects
Mi-Ryang Kim, Jeong-Eun Lee, Myungshin Im +11
Photometric variability in young stellar objects (YSOs) provides critical insight into the mechanisms of mass accretion, disk evolution, and circumstellar extinction in early stell…
Refined classification of YSOs and AGB stars by IR magnitudes, colors, and time-domain analysis with machine learning
Hyunwook Jheonn, Jeong-Eun Lee, Jinho Lee +5
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…
FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic
Kanghyun Choi, Hyeyoon Lee, SunJong Park +2
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. H…
MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity
Kanghyun Choi, Hye Yoon Lee, Dain Kwon +5
Data-free quantization (DFQ) is a technique that creates a lightweight network from its full-precision counterpart without the original training data, often through a synthetic dat…
DataFreeShield: Defending Adversarial Attacks without Training Data
Hyeyoon Lee, Kanghyun Choi, Dain Kwon +5
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,…
Slice-and-Forge: Making Better Use of Caches for Graph Convolutional Network Accelerators
Mingi Yoo, Jaeyong Song, Hyeyoon Lee +4
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…
Enabling Hard Constraints in Differentiable Neural Network and Accelerator Co-Exploration
Deokki Hong, Kanghyun Choi, Hye Yoon Lee +4
Co-exploration of an optimal neural architecture and its hardware accelerator is an approach of rising interest which addresses the computational cost problem, especially in low-pr…
Deep Composer Classification Using Symbolic Representation
Sunghyeon Kim, Hyeyoon Lee, Sunjong Park +2
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 tim…