Zobrazeno 1 - 10
of 897
pro vyhledávání: '"Lee Minwoo"'
In machine translation, the problem of ambiguously gendered input has been pointed out, where the gender of an entity is not available in the source sentence. To address this ambiguity issue, the task of controlled translation that takes the gender o
Externí odkaz:
http://arxiv.org/abs/2407.15154
Recently, directly using large language models (LLMs) has been shown to be the most reliable method to evaluate QA models. However, it suffers from limited interpretability, high cost, and environmental harm. To address these, we propose to use soft
Externí odkaz:
http://arxiv.org/abs/2404.15650
Autor:
Pinyoanuntapong, Ekkasit, Saleem, Muhammad Usama, Wang, Pu, Lee, Minwoo, Das, Srijan, Chen, Chen
Generating human motion from text has been dominated by denoising motion models either through diffusion or generative masking process. However, these models face great limitations in usability by requiring prior knowledge of the motion length. Conve
Externí odkaz:
http://arxiv.org/abs/2403.19435
Publikováno v:
EMNLP2024 findings
In the pursuit of developing Large Language Models (LLMs) that adhere to societal standards, it is imperative to detect the toxicity in the generated text. The majority of existing toxicity metrics rely on encoder models trained on specific toxicity
Externí odkaz:
http://arxiv.org/abs/2402.06900
Autor:
Payette, Kelly, Steger, Céline, Licandro, Roxane, de Dumast, Priscille, Li, Hongwei Bran, Barkovich, Matthew, Li, Liu, Dannecker, Maik, Chen, Chen, Ouyang, Cheng, McConnell, Niccolò, Miron, Alina, Li, Yongmin, Uus, Alena, Grigorescu, Irina, Gilliland, Paula Ramirez, Siddiquee, Md Mahfuzur Rahman, Xu, Daguang, Myronenko, Andriy, Wang, Haoyu, Huang, Ziyan, Ye, Jin, Alenyà, Mireia, Comte, Valentin, Camara, Oscar, Masson, Jean-Baptiste, Nilsson, Astrid, Godard, Charlotte, Mazher, Moona, Qayyum, Abdul, Gao, Yibo, Zhou, Hangqi, Gao, Shangqi, Fu, Jia, Dong, Guiming, Wang, Guotai, Rieu, ZunHyan, Yang, HyeonSik, Lee, Minwoo, Płotka, Szymon, Grzeszczyk, Michal K., Sitek, Arkadiusz, Daza, Luisa Vargas, Usma, Santiago, Arbelaez, Pablo, Lu, Wenying, Zhang, Wenhao, Liang, Jing, Valabregue, Romain, Joshi, Anand A., Nayak, Krishna N., Leahy, Richard M., Wilhelmi, Luca, Dändliker, Aline, Ji, Hui, Gennari, Antonio G., Jakovčić, Anton, Klaić, Melita, Adžić, Ana, Marković, Pavel, Grabarić, Gracia, Kasprian, Gregor, Dovjak, Gregor, Rados, Milan, Vasung, Lana, Cuadra, Meritxell Bach, Jakab, Andras
Segmentation is a critical step in analyzing the developing human fetal brain. There have been vast improvements in automatic segmentation methods in the past several years, and the Fetal Brain Tissue Annotation (FeTA) Challenge 2021 helped to establ
Externí odkaz:
http://arxiv.org/abs/2402.09463
Recent advances in text-to-motion generation using diffusion and autoregressive models have shown promising results. However, these models often suffer from a trade-off between real-time performance, high fidelity, and motion editability. To address
Externí odkaz:
http://arxiv.org/abs/2312.03596
Autor:
Lee, Dongryeol, Kim, Segwang, Lee, Minwoo, Lee, Hwanhee, Park, Joonsuk, Lee, Sang-Woo, Jung, Kyomin
Ambiguous questions persist in open-domain question answering, because formulating a precise question with a unique answer is often challenging. Previously, Min et al. (2020) have tackled this issue by generating disambiguated questions for all possi
Externí odkaz:
http://arxiv.org/abs/2305.13808
Autor:
Bailey, Christopher G., Gillan, Lara V., Lee, Minwoo, Sloane, Nicholas, Liu, Xu, Soufiani, Arman Mahboubi, Hao, Xiaojing, McCamey, Dane R.
The organic spacer cation plays a crucial role in determining the exciton fine structure in two-dimensional (2D) perovskites. Here, we use low-temperature magneto-optical spectroscopy to gain insight into the influence of the organic spacer on dark e
Externí odkaz:
http://arxiv.org/abs/2305.13674
Gender bias is a significant issue in machine translation, leading to ongoing research efforts in developing bias mitigation techniques. However, most works focus on debiasing bilingual models without much consideration for multilingual systems. In t
Externí odkaz:
http://arxiv.org/abs/2305.14016
Publikováno v:
Probabilistic Eng. Mech. 74 (2023) Paper No. 103516
Self-sustained oscillations are ubiquitous in nature and engineering. In this paper, we propose a novel output-only system-identification framework for identifying the system parameters of a self-sustained oscillator affected by Gaussian white noise.
Externí odkaz:
http://arxiv.org/abs/2305.02801