Výsledky vyhledávání - "Kim, JungHwan"

Report

Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue

Autor: Ivey, Jonathan, Kumar, Shivani, Liu, Jiayu, Shen, Hua, Rakshit, Sushrita, Raju, Rohan, Zhang, Haotian, Ananthasubramaniam, Aparna, Kim, Junghwan, Yi, Bowen, Wright, Dustin, Israeli, Abraham, Møller, Anders Giovanni, Zhang, Lechen, Jurgens, David

Studying and building datasets for dialogue tasks is both expensive and time-consuming due to the need to recruit, train, and collect data from study participants. In response, much recent work has sought to use large language models (LLMs) to simula

Externí odkaz: http://arxiv.org/abs/2409.08330

Zobrazit plný text záznamu

Report

KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge

Autor: Lee, Jiyoung, Kim, Minwoo, Kim, Seungho, Kim, Junghwan, Won, Seunghyun, Lee, Hwaran, Choi, Edward

For Large Language Models (LLMs) to be effectively deployed in a specific country, they must possess an understanding of the nation's culture and basic knowledge. To this end, we introduce National Alignment, which measures an alignment between an LL

Externí odkaz: http://arxiv.org/abs/2402.13605

Zobrazit plný text záznamu

Report

Understanding Place Identity with Generative AI

Autor: Jang, Kee Moon, Chen, Junda, Kang, Yuhao, Kim, Junghwan, Lee, Jinhyung, Duarte, Fábio

Researchers are constantly leveraging new forms of data with the goal of understanding how people perceive the built environment and build the collective place identity of cities. Latest advancements in generative artificial intelligence (AI) models

Externí odkaz: http://arxiv.org/abs/2306.04662

Zobrazit plný text záznamu

Report

Chemical Property-Guided Neural Networks for Naphtha Composition Prediction

Autor: Joo, Chonghyo, Kim, Jeongdong, Cho, Hyungtae, Lee, Jaewon, Suh, Sungho, Kim, Junghwan

The naphtha cracking process heavily relies on the composition of naphtha, which is a complex blend of different hydrocarbons. Predicting the naphtha composition accurately is crucial for efficiently controlling the cracking process and achieving max

Externí odkaz: http://arxiv.org/abs/2306.01391

Zobrazit plný text záznamu

Report

ASAP: Accurate semantic segmentation for real time performance

Autor: Park, Jaehyun, Lee, Subin, Kim, Eon, Moon, Byeongjun, Yu, Dabeen, Yu, Yeonseung, Kim, Junghwan

Feature fusion modules from encoder and self-attention module have been adopted in semantic segmentation. However, the computation of these modules is costly and has operational limitations in real-time environments. In addition, segmentation perform

Externí odkaz: http://arxiv.org/abs/2210.01323

Zobrazit plný text záznamu