5 citations · 12 across the 8 of their papers we have counts for
10 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…
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,…
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…
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
Kanghyun Choi, Hye Yoon Lee, Deokki Hong +4
Model quantization is considered as a promising method to greatly reduce the resource requirements of deep neural networks. To deal with the performance drop induced by quantizatio…
Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples
Kanghyun Choi, Deokki Hong, Noseong Park +2
Model quantization is known as a promising method to compress deep neural networks, especially for inferences on lightweight mobile or edge devices. However, model quantization usu…
DANCE: Differentiable Accelerator/Network Co-Exploration
Kanghyun Choi, Deokki Hong, Hojae Yoon +3
To cope with the ever-increasing computational demand of the DNN execution, recent neural architecture search (NAS) algorithms consider hardware cost metrics into account, such as…