33 citations · 34 across the 8 of their papers we have counts for
8 papers
d-DQIVAR: Data-centric Visual Analytics and Reasoning for Data Quality Improvement
Hyein Hong, Sangbong Yoo, SeokHwan Choi +5
Approaches to enhancing data quality (DQ) are classified into two main categories: data- and process-driven. However, prior research has predominantly utilized batch data preproces…
Using Cross-Domain Detection Loss to Infer Multi-Scale Information for Improved Tiny Head Tracking
Jisu Kim, Alex Mattingly, Eung-Joo Lee +1
Head detection and tracking are essential for downstream tasks, but current methods often require large computational budgets, which increase latencies and ties up resources (e.g.,…
Memorization or Reasoning? Exploring the Idiom Understanding of LLMs
Jisu Kim, Youngwoo Shin, Uiji Hwang +3
Idioms have long posed a challenge due to their unique linguistic properties, which set them apart from other common expressions. While recent studies have leveraged large language…
Control Token with Dense Passage Retrieval
Juhwan Lee, Jisu Kim
This study addresses the hallucination problem in large language models (LLMs). We adopted Retrieval-Augmented Generation(RAG) (Lewis et al., 2020), a technique that involves embed…
Strategic Data Ordering: Enhancing Large Language Model Performance through Curriculum Learning
Jisu Kim, Juhwan Lee
The rapid advancement of Large Language Models (LLMs) has improved text understanding and generation but poses challenges in computational resources. This study proposes a curricul…
One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations
Yoonjoo Lee, Kihoon Son, Tae Soo Kim +4
As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may corre…
Semi-Supervised Domain Adaptation for Wildfire Detection
JooYoung Jang, Youngseo Cha, Jisu Kim +5
Recently, both the frequency and intensity of wildfires have increased worldwide, primarily due to climate change. In this paper, we propose a novel protocol for wildfire detection…
The Hall of Singularity: VR Experience of Prophecy by AI
Jisu Kim, Kirak Kim
"The Hall of Singularity" is an immersive art that creates personalized experiences of receiving prophecies from an AI deity through an integration of Artificial Intelligence (AI)…