Zobrazeno 1 - 10
of 5 201
pro vyhledávání: '"Sungjun An"'
Recent advances in audio understanding tasks leverage the reasoning capabilities of LLMs. However, adapting LLMs to learn audio concepts requires massive training data and substantial computational resources. To address these challenges, Retrieval-Au
Externí odkaz:
http://arxiv.org/abs/2410.10913
When solving forecasting problems including multiple time-series features, existing approaches often fall into two extreme categories, depending on whether to utilize inter-feature information: univariate and complete-multivariate models. Unlike univ
Externí odkaz:
http://arxiv.org/abs/2408.09703
Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora. However, this poses risk of privacy and copyright violations, highlighting the need for efficient machine unlear
Externí odkaz:
http://arxiv.org/abs/2408.06621
Conventional uncertainty-aware temporal difference (TD) learning methods often rely on simplistic assumptions, typically including a zero-mean Gaussian distribution for TD errors. Such oversimplification can lead to inaccurate error representations a
Externí odkaz:
http://arxiv.org/abs/2408.02295
Music generation introduces challenging complexities to large language models. Symbolic structures of music often include vertical harmonization as well as horizontal counterpoint, urging various adaptations and enhancements for large-scale Transform
Externí odkaz:
http://arxiv.org/abs/2407.19900
This study proposes an effective method to predict technology development from an evolutionary perspective. Product evolution is the result of technological evolution and market selection. A phylogenetic network is the main method to study product ev
Externí odkaz:
http://arxiv.org/abs/2407.10206
With the advent of automation, many manufacturing industries have transitioned to data-centric methodologies, giving rise to an unprecedented influx of data during the manufacturing process. This data has become instrumental in analyzing the quality
Externí odkaz:
http://arxiv.org/abs/2406.19575
Autor:
Lim, Sungjun, Yeom, Jeyoon, Kim, Sooyon, Byun, Hoyoon, Kang, Jinho, Jung, Yohan, Jung, Jiyoung, Song, Kyungwoo
Bayesian neural network (BNN) approximates the posterior distribution of model parameters and utilizes the posterior for prediction via Bayesian Model Averaging (BMA). The quality of the posterior approximation is critical for achieving accurate and
Externí odkaz:
http://arxiv.org/abs/2406.15664
Autor:
Hyun-Kyu Cho, Yong-Myung Kang, Mingeun Sagong, Juhun Kim, Hyunjun Kim, Sungjun An, Youn-Jeong Lee, Hyun-Mi Kang
Publikováno v:
Vaccines, Vol 11, Iss 3, p 538 (2023)
Prior to the identification of low pathogenic avian influenza H9N2 viruses belonging to the Y280 lineage in 2020, Y439 lineage viruses had been circulating in the Republic of Korea since 1996. Here, we developed a whole inactivated vaccine (vac564) b
Externí odkaz:
https://doaj.org/article/f19e4038328c496dacacfea29442b7fa
Autor:
Cho, Sungjun, Kim, Beomjun, Cho, Hyunuk, Seo, Gyeongseob, Mutlu, Onur, Kim, Myungsuk, Park, Jisung
This work investigates a new erase scheme in NAND flash memory to improve the lifetime and performance of modern solid-state drives (SSDs). In NAND flash memory, an erase operation applies a high voltage (e.g., > 20 V) to flash cells for a long time
Externí odkaz:
http://arxiv.org/abs/2404.10355