56 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Seoul National UniversityKR5 papers
- Korea Advanced Institute of Science and TechnologyKR3 papers
- Korea Telecom (South Korea)KR3 papers
- Chungnam National UniversityKR2 papers
- Electronics and Telecommunications Research InstituteKR2 papers
- Hanyang UniversityKR2 papers
- Seoul National University of Science and TechnologyKR2 papers
- SK Hynix (South Korea)KR2 papers
- Ajou UniversityKR1 paper
- Beth Israel Deaconess Medical CenterUS1 paper
- Carnegie Mellon UniversityUS1 paper
- Centre for Artificial Intelligence and RoboticsIN1 paper
19 papers
Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services
Yonghyun Jun, Jimin Lee, Hwan Chang +3
Automatic Speech Recognition (ASR) technology is fundamental to customer service automation and large-scale transcription. However, even advanced ASR models exhibit inevitable erro…
PROBE: Probabilistic Occupancy BEV Encoding with Analytical Translation Robustness for 3D Place Recognition
Jinseop Lee, Byoungho Lee, Gichul Yoo
We present PROBE (PRobabilistic Occupancy BEV Encoding), a learning-free LiDAR place recognition descriptor that models each BEV cell's occupancy as a Bernoulli random variable. Ra…
MoSKA: Mixture of Shared KV Attention for Efficient Long-Sequence LLM Inference
Myunghyun Rhee, Sookyung Choi, Euiseok Kim +3
The escalating context length in Large Language Models (LLMs) creates a severe performance bottleneck around the Key-Value (KV) cache, whose memory-bound nature leads to significan…
Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
Sangwoo Jeon, Juchul Shin, Gyeong-Tae Kim +2
Generalized planning using deep reinforcement learning (RL) combined with graph neural networks (GNNs) has shown promising results in various symbolic planning domains described by…
DiaryPlay: AI-Assisted Authoring of Interactive Vignettes for Everyday Storytelling
Jiangnan Xu, Haeseul Cha, Gosu Choi +6
An interactive vignette is a popular and immersive visual storytelling approach that invites viewers to role-play a character and influences the narrative in an interactive environ…
A comprehensive approach to incorporating intermolecular dispersion into the openCOSMO-RS model. Part 2: Atomic polarizabilities
Daria Grigorash, Simon Müller, Esther Heid +8
openCOSMO-RS is an open-source predictive thermodynamic model that can be applied to a broad range of systems in various chemical and biochemical engineering domains. This study fo…
IANUS: Integrated Accelerator based on NPU-PIM Unified Memory System
Minseok Seo, Xuan Truong Nguyen, Seok Joong Hwang +18
Accelerating end-to-end inference of transformer-based large language models (LLMs) is a critical component of AI services in datacenters. However, diverse compute characteristics…
M6(GPT)3: Generating Multitrack Modifiable Multi-Minute MIDI Music from Text using Genetic algorithms, Probabilistic methods and GPT Models in any Progression and Time Signature
Jakub Poćwiardowski, Mateusz Modrzejewski, Marek S. Tatara
This work introduces the M6(GPT)3 composer system, capable of generating complete, multi-minute musical compositions with complex structures in any time signature, in the MIDI doma…
Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge
Gregory Holste, Yiliang Zhou, Song Wang +22
Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" $\unicode{x2013}$ there are a few common findings followed by many more rela…
Dialogue Possibilities between a Human Supervisor and UAM Air Traffic Management: Route Alteration
Jeongseok Kim, Kangjin Kim
This paper introduces a novel approach to detour management in Urban Air Traffic Management (UATM) using knowledge representation and reasoning. It aims to understand the complexit…
PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image Sensors
Minhyeok Cho, Haechang Lee, Hyunwoo Je +3
Deep learning-based image signal processor (ISP) models for mobile cameras can generate high-quality images that rival those of professional DSLR cameras. However, their computatio…
Learning to Discriminate Information for Online Action Detection: Analysis and Application
Sumin Lee, Hyunjun Eun, Jinyoung Moon +4
Online action detection, which aims to identify an ongoing action from a streaming video, is an important subject in real-world applications. For this task, previous methods use re…
Non-Compression Auto-Encoder for Detecting Road Surface Abnormality via Vehicle Driving Noise
YeongHyeon Park, JongHee Jung
Road accident can be triggered by wet road because it decreases skid resistance. To prevent the road accident, detecting road surface abnomality is highly useful. In this paper, we…
An In-Module Disturbance Barrier for Mitigating Write Disturbance in Phase-Change Memory
Hyokeun Lee, Seungyong Lee, Byeongki Song +4
Write disturbance error (WDE) appears as a serious reliability problem preventing phase-change memory (PCM) from general commercialization, and therefore several studies have been…
Restore from Restored: Single Image Denoising with Pseudo Clean Image
Seunghwan Lee, Dongkyu Lee, Donghyeon Cho +2
In this study, we propose a simple and effective fine-tuning algorithm called "restore-from-restored", which can greatly enhance the performance of fully pre-trained image denoisin…
Self-Supervised Fast Adaptation for Denoising via Meta-Learning
Seunghwan Lee, Donghyeon Cho, Jiwon Kim +1
Under certain statistical assumptions of noise, recent self-supervised approaches for denoising have been introduced to learn network parameters without true clean images, and thes…
Multimodal Dual Attention Memory for Video Story Question Answering
Kyung-Min Kim, Seong-Ho Choi, Jin-Hwa Kim +1
We propose a video story question-answering (QA) architecture, Multimodal Dual Attention Memory (MDAM). The key idea is to use a dual attention mechanism with late fusion. MDAM use…
Paraphrase Thought: Sentence Embedding Module Imitating Human Language Recognition
Myeongjun Jang, Pilsung Kang
Sentence embedding is an important research topic in natural language processing. It is essential to generate a good embedding vector that fully reflects the semantic meaning of a…
Quantum messages with signatures forgeable in arbitrated quantum signature schemes
Taewan Kim, Jeong Woon Choi, Nam-Su Jho +1
Even though a method to perfectly sign quantum messages has not been known, the arbitrated quantum signature scheme has been considered as one of good candidates. However, its forg…