3k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Samsung (South Korea)KR64 papers
- Seoul National UniversityKR20 papers
- Korea Advanced Institute of Science and TechnologyKR8 papers
- Samsung Advanced Institute of Technology (South Korea)8 papers
- Pohang University of Science and TechnologyKR7 papers
- The University of Texas at AustinUS6 papers
- Yonsei UniversityKR5 papers
- Hanyang UniversityKR4 papers
- Samsung (United States)US4 papers
- University of California San DiegoUS4 papers
- Alexandria UniversityEG3 papers
- Centre National de la Recherche ScientifiqueFR3 papers
96 papers
Experiments and Modeling of Defect Dynamics and BTI Behavior in Doped InO TFTs during C Post-Processing Forming Gas Annealing
Yu-Hsin Kuo, Chengyang Zhang, Priyankka Ravikumar +13
We investigate the impact of a monolithic three-dimensional (M3D) integration process-critical C post-processing forming gas anneal (FGA) on the electrical performance,…
SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech
Byoung Jin Choi, Myeonghun Jeong, Joun Yeop Lee +1
Zero-shot multi-speaker text-to-speech (ZSM-TTS) models aim to generate a speech sample with the voice characteristic of an unseen speaker. The main challenge of ZSM-TTS is to incr…
Successive Cancellation Decoding with Future Constraints for Polar Codes Over the Binary Erasure Channel
Min Jang, Jong-Hwan Kim, Seho Myung +1
In the conventional successive cancellation (SC) decoder for polar codes, all the future bits to be estimated later are treated as random variables. However, polar codes inevitably…
Reinforcement Learning for Vision-based Object Manipulation with Non-parametric Policy and Action Primitives
Dongwon Son, Myungsin Kim, Jaecheol Sim +1
The object manipulation is a crucial ability for a service robot, but it is hard to solve with reinforcement learning due to some reasons such as sample efficiency. In this paper,…
Grasping as Inference: Reactive Grasping in Heavily Cluttered Environment
Dongwon Son
Although, in the task of grasping via a data-driven method, closed-loop feedback and predicting 6 degrees of freedom (DoF) grasp rather than conventionally used 4DoF top-down grasp…
Transformer Network-based Reinforcement Learning Method for Power Distribution Network (PDN) Optimization of High Bandwidth Memory (HBM)
Hyunwook Park, Minsu Kim, Seongguk Kim +9
In this article, for the first time, we propose a transformer network-based reinforcement learning (RL) method for power distribution network (PDN) optimization of high bandwidth m…
Distortion-Aware Brushing for Reliable Cluster Analysis in Multidimensional Projections
Hyeon Jeon, Michaël Aupetit, Soohyun Lee +4
Brushing is a common interaction technique in 2D scatterplots, allowing users to select clustered points within a continuous, enclosed region for further analysis or filtering. How…
A Deterministic Solution of the Wigner Transport Equation with Infinite Correlation Length
Kyoung Yeon Kim, Byung-Gook Park
We propose a new formulation of the Wigner transport equation with infinite correlation length. Since the maximum correlation length is not limited to a finite value, there is no u…
Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
Myung-Joon Kwon, Seung-Hun Nam, In-Jae Yu +2
Detecting and localizing image manipulation are necessary to counter malicious use of image editing techniques. Accordingly, it is essential to distinguish between authentic and ta…
Data-free mixed-precision quantization using novel sensitivity metric
Donghyun Lee, Minkyoung Cho, Seungwon Lee +2
Post-training quantization is a representative technique for compressing neural networks, making them smaller and more efficient for deployment on edge devices. However, an inacces…
Downlink Channel Reconstruction for Spatial Multiplexing in Massive MIMO Systems
Hyeongtaek Lee, Hyuckjin Choi, Hwanjin Kim +4
To get channel state information (CSI) at a base station (BS), most of researches on massive multiple-input multiple-output (MIMO) systems consider time division duplexing (TDD) to…
Periocular Embedding Learning with Consistent Knowledge Distillation from Face
Yoon Gyo Jung, Jaewoo Park, Cheng Yaw Low +3
Periocular biometric, the peripheral area of the ocular, is a collaborative alternative to the face, especially when the face is occluded or masked. However, in practice, sole peri…
Multi-Agent Deep Reinforcement Learning for Distributed Resource Management in Wirelessly Powered Communication Networks
Sangwon Hwang, Hanjin Kim, Hoon Lee +1
This paper studies multi-agent deep reinforcement learning (MADRL) based resource allocation methods for multi-cell wireless powered communication networks (WPCNs) where multiple h…
Massive MIMO Channel Prediction: Kalman Filtering vs. Machine Learning
Hwanjin Kim, Sucheol Kim, Hyeongtaek Lee +3
This paper focuses on channel prediction techniques for massive multiple-input multiple-output (MIMO) systems. Previous channel predictors are based on theoretical channel models,…
HEAAN Demystified: Accelerating Fully Homomorphic Encryption Through Architecture-centric Analysis and Optimization
Wonkyung Jung, Eojin Lee, Sangpyo Kim +5
Homomorphic Encryption (HE) draws a significant attention as a privacy-preserving way for cloud computing because it allows computation on encrypted messages called ciphertexts. Am…
Robust Full-FoV Depth Estimation in Tele-wide Camera System
Kai Guo, Seongwook Song, Soonkeun Chang +3
Tele-wide camera system with different Field of View (FoV) lenses becomes very popular in recent mobile devices. Usually it is difficult to obtain full-FoV depth based on tradition…
Optimal work extraction and mutual information in a generalized Szilárd engine
Juyong Song, Susanne Still, Rafael Díaz Hernández Rojas +2
A 1929 Gedankenexperiment proposed by Szilárd, often referred to as "Szilárd's engine", has served as a foundation for computing fundamental thermodynamic bounds to information pro…
TMA: Tera-MACs/W Neural Hardware Inference Accelerator with a Multiplier-less Massive Parallel Processor
Hyunbin Park, Dohyun Kim, Shiho Kim
Computationally intensive Inference tasks of Deep neural networks have enforced revolution of new accelerator architecture to reduce power consumption as well as latency. The key f…
Ensemble-Based Deep Reinforcement Learning for Chatbots
Heriberto Cuayáhuitl, Donghyeon Lee, Seonghan Ryu +7
Trainable chatbots that exhibit fluent and human-like conversations remain a big challenge in artificial intelligence. Deep Reinforcement Learning (DRL) is promising for addressing…
Beam Codebook Design for 5G mmWave Terminals
Jianhua Mo, Boon Loong Ng, Sanghyun Chang +6
A beam codebook of 5G millimeter wave (mmWave) for data communication consists of multiple high-peak-gain beams to compensate the high pathloss at the mmWave bands. These beams als…
Automatic Registration between Cone-Beam CT and Scanned Surface via Deep-Pose Regression Neural Networks and Clustered Similarities
Minyoung Chung, Jingyu Lee, Wisoo Song +4
Computerized registration between maxillofacial cone-beam computed tomography (CT) images and a scanned dental model is an essential prerequisite in surgical planning for dental im…
Plug-in, Trainable Gate for Streamlining Arbitrary Neural Networks
Jaedeok Kim, Chiyoun Park, Hyun-Joo Jung +1
Architecture optimization, which is a technique for finding an efficient neural network that meets certain requirements, generally reduces to a set of multiple-choice selection pro…
Stabilizing the virtual response time in single-server processor sharing queues with slowly time-varying arrival rates
Yongkyu Cho, Young Myoung Ko
Motivated by the work of Whitt, who studied stabilization of the mean virtual waiting time (excluding service time) in a queue, this paper investigates the stabi…
Sym-parameterized Dynamic Inference for Mixed-Domain Image Translation
Simyung Chang, SeongUk Park, John Yang +1
Recent advances in image-to-image translation have led to some ways to generate multiple domain images through a single network. However, there is still a limit in creating an imag…