148 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Seoul National UniversityKR34 papers
- Sungkyunkwan UniversityKR17 papers
- Yonsei UniversityKR16 papers
- Korea UniversityKR15 papers
- Korea Institute for Advanced StudyKR14 papers
- University of PittsburghUS14 papers
- High Energy Accelerator Research OrganizationJP11 papers
- Kyungpook National UniversityKR11 papers
- Institute for Basic ScienceKR10 papers
- New Generation University CollegeET10 papers
- Tohoku UniversityJP10 papers
- Chonnam National UniversityKR9 papers
237 papers
Unbalanced Optimal Transport for Efficient Visual Document Retrieval
Hoyeon Shin, Jeongyeon Kim, Yeong Jun Koh +2
Vision-Language Models(VLMs)have advanced Visual Document Retrieval (VDR) by enabling OCR-free, multi-vector representations. However, these models generate excessive tokens to pre…
TELLME: Test-Enhanced Learning for Language Model Enrichment
Minjun Kim, Inho Won, Hyeonseok Lim +6
Continual pre-training (CPT) has been widely adopted as a method for domain adaptation in large language models. However, CPT has consistently been accompanied by challenges, such…
Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning
Duy Tran Thanh, Thien-Phuc Doan, Long Nguyen-Vu +1
Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text…
Edges Before Embeddings: A Confidence-Aware Blur Gate for Vision-Language Pipelines
Duy Tran Thanh
Production vision pipelines silently degrade on blurry input, wasting compute on downstream OCR, retrieval, and vision-language model (VLM) calls that cannot recover a usable outpu…
Selective Correlation Based Knowledge Distillation for Ground Reaction Force Estimation
Eun Som Jeon, Jisoo Lee, Huisu Lim +3
Wearable sensor-based human gait analysis holds great promise in healthcare, rehabilitation, clinical diagnosis and monitoring, and sports activities. Specifically, ground reaction…
Gyrokinetic simulations on zonal flow-turbulence spreading coupling
Min Ki Jung, Sumin Yi, Taik Soo Hahm +1
Zonal flows and turbulence spreading play important roles in magnetic fusion plasma confinement, yet their coupling mechanisms remain elusive. Using global nonlinear gyrokinetic si…
IBEX: Internal Bandwidth-Efficient Compression Architecture for Scalable CXL Memory Expansion
Younghoon Ko, Hyemin Park, Hyuk-Jae Lee +1
As the memory channel count is confined by physical dimensions, memory expanders appear to be a promising approach to extending memory capacity and channels by augmenting the exist…
"Don't Look, But I Know You Do": Norms and Observer Effects in Shared LLM Accounts
Ji Eun Song, Eunchae Lee, Juhee Im +3
Account sharing is common in subscription services and is now extending to generative AI platforms, which are still primarily designed for individual use. Sharing often requires wo…
IgPose: A Generative Data-Augmented Pipeline for Robust Immunoglobulin-Antigen Binding Prediction
Tien-Cuong Bui, Injae Chung, Wonjun Lee +2
Predicting immunoglobulin-antigen (Ig-Ag) binding remains a significant challenge due to the paucity of experimentally-resolved complexes and the limited accuracy of de novo Ig str…
Reading the Mood Behind Words: Integrating Prosody-Derived Emotional Context into Socially Responsive VR Agents
SangYeop Jeong, Yeongseo Na, Seung Gyu Jeong +2
In VR interactions with embodied conversational agents, users' emotional intent is often conveyed more by how something is said than by what is said. However, most VR agent pipelin…
Fate of under Reflection Symmetry in Light of the First JUNO Results
Ranjeet Kumar
The recent Jiangmen Underground Neutrino Observatory (JUNO) measurements of and open a new avenue for probing flavor symmetric structures in the lepton sector.…
ODIN: Clustering Properties of Ly Blobs at 2.4 and 3.1
Byeongha Moon, Yujin Yang, Eric Gawiser +18
Spatially extended Ly nebulae, known as Ly blobs (LABs), are a rare population at that are thought to trace proto-groups or the progenitors of massive galaxies in the…
Minimal A4 Type-II Seesaw Realization of Testable Neutrino Mass Sum Rules
Salvador Centelles Chuliá, Ranjeet Kumar
We propose a flavour model based on an symmetry combined with a type-II seesaw mechanism for neutrino mass generation. The resulting neutrino mass matrix obeys a sum rule tha…
XPRESS: X-Band Radar Place Recognition via Elliptical Scan Shaping
Hyesu Jang, Wooseong Yang, Ayoung Kim +2
X-band radar serves as the primary sensor on maritime vessels, however, its application in autonomous navigation has been limited due to low sensor resolution and insufficient info…
Generalized Zero-Shot Learning for Point Cloud Segmentation with Evidence-Based Dynamic Calibration
Hyeonseok Kim, Byeongkeun Kang, Yeejin Lee
Generalized zero-shot semantic segmentation of 3D point clouds aims to classify each point into both seen and unseen classes. A significant challenge with these models is their ten…
LegiGPT: Party Politics and Transport Policy with Large Language Model
Hyunsoo Yun, Eun Hak Lee
Given the significant influence of lawmakers' political ideologies on legislative decision-making, analyzing their impact on transportation-related policymaking is of critical impo…
Ground Reaction Force Estimation via Time-aware Knowledge Distillation
Eun Som Jeon, Sinjini Mitra, Jisoo Lee +4
Human gait analysis with wearable sensors has been widely used in various applications, such as daily life healthcare, rehabilitation, physical therapy, and clinical diagnostics an…
Long-Tailed Learning for Generalized Category Discovery
Cuong Manh Hoang
Generalized Category Discovery (GCD) utilizes labeled samples of known classes to discover novel classes in unlabeled samples. Existing methods show effective performance on artifi…
Generating Diverse Challenging Terrains for Legged Robots Using Quality-Diversity Algorithm
Arthur Esquerre-Pourtère, Minsoo Kim, Jaeheung Park
While legged robots have achieved significant advancements in recent years, ensuring the robustness of their controllers on unstructured terrains remains challenging. It requires g…
Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding
Yeonkyoung So, Gyuseong Lee, Sungmok Jung +4
Negation is a fundamental linguistic phenomenon that poses ongoing challenges for Large Language Models (LLMs), particularly in tasks requiring deep semantic understanding. Current…
Intra-class Patch Swap for Self-Distillation
Hongjun Choi, Eun Som Jeon, Ankita Shukla +1
Knowledge distillation (KD) is a valuable technique for compressing large deep learning models into smaller, edge-suitable networks. However, conventional KD frameworks rely on pre…
Evaluation of Thermal Control Based on Spatial Thermal Comfort with Reconstructed Environmental Data
Youngkyu Kim, Byounghyun Yoo, Ji Young Yun +4
Achieving thermal comfort while maintaining energy efficiency is a critical objective in building system control. Conventional thermal comfort models, such as the Predicted Mean Vo…
A Charged and Neutral Spin- Currents in the Grassmannian-like Coset Model
Changhyun Ahn, Minsu Kang
By calculating the second order pole in the operator product expansion (OPE) of the charged spin- current with the neutral spin- current in the Grassmannian-like coset model,…
GC-Fed: Gradient Centralized Federated Learning with Partial Client Participation
Jungwon Seo, Ferhat Ozgur Catak, Chunming Rong +2
Federated Learning (FL) enables privacy-preserving multi-source information fusion (MSIF) but is challenged by client drift in highly heterogeneous data settings. Many existing dri…