Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Lee Gihun"'
Developing effective text summarizers remains a challenge due to issues like hallucinations, key information omissions, and verbosity in LLM-generated summaries. This work explores using LLM-generated feedback to improve summary quality by aligning t
Externí odkaz:
http://arxiv.org/abs/2410.13116
Autor:
Kim, Beomsu, Kim, Sangbum, Kim, Minchan, Yi, Joonyoung, Ha, Sungjoo, Lee, Suhyun, Lee, Youngsoo, Yeom, Gihun, Chang, Buru, Lee, Gihun
This study introduces CUPID, a novel approach to session-based reciprocal recommendation systems designed for a real-time one-on-one social discovery platform. In such platforms, low latency is critical to enhance user experiences. However, conventio
Externí odkaz:
http://arxiv.org/abs/2410.18087
Autor:
Lee, Gihun, Jeong, Minchan, Kim, Yujin, Jung, Hojung, Oh, Jaehoon, Kim, Sangmook, Yun, Se-Young
While learning to align Large Language Models (LLMs) with human preferences has shown remarkable success, aligning these models to meet the diverse user preferences presents further challenges in preserving previous knowledge. This paper examines the
Externí odkaz:
http://arxiv.org/abs/2407.00693
Federated Learning (FL) is a collaborative method for training models while preserving data privacy in decentralized settings. However, FL encounters challenges related to data heterogeneity, which can result in performance degradation. In our study,
Externí odkaz:
http://arxiv.org/abs/2311.13267
While instruction-tuned language models have demonstrated impressive zero-shot generalization, these models often struggle to generate accurate responses when faced with instructions that fall outside their training set. This paper presents Instructi
Externí odkaz:
http://arxiv.org/abs/2311.00233
Federated Learning (FL) aggregates locally trained models from individual clients to construct a global model. While FL enables learning a model with data privacy, it often suffers from significant performance degradation when clients have heterogene
Externí odkaz:
http://arxiv.org/abs/2308.12532
Autor:
Ma, Jun, Xie, Ronald, Ayyadhury, Shamini, Ge, Cheng, Gupta, Anubha, Gupta, Ritu, Gu, Song, Zhang, Yao, Lee, Gihun, Kim, Joonkee, Lou, Wei, Li, Haofeng, Upschulte, Eric, Dickscheid, Timo, de Almeida, José Guilherme, Wang, Yixin, Han, Lin, Yang, Xin, Labagnara, Marco, Gligorovski, Vojislav, Scheder, Maxime, Rahi, Sahand Jamal, Kempster, Carly, Pollitt, Alice, Espinosa, Leon, Mignot, Tâm, Middeke, Jan Moritz, Eckardt, Jan-Niklas, Li, Wangkai, Li, Zhaoyang, Cai, Xiaochen, Bai, Bizhe, Greenwald, Noah F., Van Valen, David, Weisbart, Erin, Cimini, Beth A., Cheung, Trevor, Brück, Oscar, Bader, Gary D., Wang, Bo
Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different exp
Externí odkaz:
http://arxiv.org/abs/2308.05864
Cell segmentation is a fundamental task for computational biology analysis. Identifying the cell instances is often the first step in various downstream biomedical studies. However, many cell segmentation algorithms, including the recently emerging d
Externí odkaz:
http://arxiv.org/abs/2212.03465
Contrastive loss has significantly improved performance in supervised classification tasks by using a multi-viewed framework that leverages augmentation and label information. The augmentation enables contrast with another view of a single image but
Externí odkaz:
http://arxiv.org/abs/2106.15499
In federated learning, a strong global model is collaboratively learned by aggregating clients' locally trained models. Although this precludes the need to access clients' data directly, the global model's convergence often suffers from data heteroge
Externí odkaz:
http://arxiv.org/abs/2106.03097