Výsledky vyhledávání - "Park, Subeen"

Report

Benchmarking Foundation Models on Exceptional Cases: Dataset Creation and Validation

Autor: Kang, Suho, Park, Jungyang, Ha, Joonseo, Kim, SoMin, Kim, JinHyeong, Park, Subeen, Song, Kyungwoo

Foundation models (FMs) have achieved significant success across various tasks, leading to research on benchmarks for reasoning abilities. However, there is a lack of studies on FMs performance in exceptional scenarios, which we define as out-of-dist

Externí odkaz: http://arxiv.org/abs/2410.18001

Zobrazit plný text záznamu

Report

Sufficient Invariant Learning for Distribution Shift

Autor: Kim, Taero, Park, Subeen, Lim, Sungjun, Jung, Yonghan, Muandet, Krikamol, Song, Kyungwoo

Learning robust models under distribution shifts between training and test datasets is a fundamental challenge in machine learning. While learning invariant features across environments is a popular approach, it often assumes that these features are

Externí odkaz: http://arxiv.org/abs/2210.13533

Zobrazit plný text záznamu

Report

Exploring the Effects of AI-assisted Emotional Support Processes in Online Mental Health Community

Autor: Shin, Donghoon, Park, Subeen, Kim, Esther Hehsun, Kim, Soomin, Seo, Jinwook, Hong, Hwajung

Social support in online mental health communities (OMHCs) is an effective and accessible way of managing mental wellbeing. In this process, sharing emotional supports is considered crucial to the thriving social supports in OMHCs, yet often difficul

Externí odkaz: http://arxiv.org/abs/2202.10065

Zobrazit plný text záznamu