Zobrazeno 1 - 10
of 1 434
pro vyhledávání: '"PARK, SUNGJIN"'
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning
Despite recent advances in large language models, open-source models often struggle to consistently perform well on complex reasoning tasks. Existing ensemble methods, whether applied at the token or output levels, fail to address these challenges. I
Externí odkaz:
http://arxiv.org/abs/2412.15797
Autor:
Park, Sungjin, Kim, Sangkyun
Publikováno v:
JMIR Serious Games, Vol 9, Iss 2, p e14746 (2021)
BackgroundGamification in education enhances learners’ motivation, problem-solving abilities, decision-making abilities, and social skills such as communication. Numerous ongoing studies are examining the application of gamification design methodol
Externí odkaz:
https://doaj.org/article/bed630ab2e1c4288801370e10f29ae22
Autor:
Park, Sungjin, Choi, Edward
Transformer-based models have significantly improved performance across a range of multimodal understanding tasks, such as visual question answering and action recognition. However, multimodal Transformers significantly suffer from a quadratic comple
Externí odkaz:
http://arxiv.org/abs/2402.15096
In real world applications, knowledge graphs (KG) are widely used in various domains (e.g. medical applications and dialogue agents). However, for fact verification, KGs have not been adequately utilized as a knowledge source. KGs can be a valuable k
Externí odkaz:
http://arxiv.org/abs/2305.06590
Recent success of pre-trained language models (PLMs) has stimulated interest in their ability to understand and work with numbers. Yet, the numerical reasoning over measurements has not been formally studied despite their importance. In this study, w
Externí odkaz:
http://arxiv.org/abs/2210.12694
Autor:
Kwon, Sujin, Hu, Qihua, Seo, Jaewon, Park, Soyoung, Moon, Jihye, Kim, Jaeuk, Park, Sungjin, Park, Yoojin, Kim, Hwajin
Publikováno v:
In Science of the Total Environment 1 January 2025 958
Although deep generative models have gained a lot of attention, most of the existing works are designed for unimodal generation. In this paper, we explore a new method for unconditional image-text pair generation. We design Multimodal Cross-Quantizat
Externí odkaz:
http://arxiv.org/abs/2204.07537
As the volume of Electronic Health Records (EHR) sharply grows, there has been emerging interest in learning the representation of EHR for healthcare applications. Representation learning of EHR requires appropriate modeling of the two dominant modal
Externí odkaz:
http://arxiv.org/abs/2203.09994
Autor:
Park, Sungjin1 (AUTHOR), Lee, June-Hee2 (AUTHOR) junelee@sch.ac.kr
Publikováno v:
PLoS ONE. 10/24/2024, Vol. 19 Issue 10, p1-14. 14p.
Publikováno v:
Journal of Applied Physics; 10/21/2024, Vol. 136 Issue 15, p1-12, 12p