Zobrazeno 1 - 10
of 69 649
pro vyhledávání: '"Choe A"'
Open-vocabulary segmentation (OVS) has gained attention for its ability to recognize a broader range of classes. However, OVS models show significant performance drops when applied to unseen domains beyond the previous training dataset. Fine-tuning t
Externí odkaz:
http://arxiv.org/abs/2410.11536
Autor:
Choe, Kwang Rim, Pak, Myong Chol
Single spot radiometers are widely used to estimate temperature of body heated by high temperature, specially blast furnace, glass fusion, boiler of power plant, and so on. In previous papers on single spot radiometer a heated body was deduced accord
Externí odkaz:
http://arxiv.org/abs/2410.10916
Binary Code Similarity Analysis (BCSA) has a wide spectrum of applications, including plagiarism detection, vulnerability discovery, and malware analysis, thus drawing significant attention from the security community. However, conventional technique
Externí odkaz:
http://arxiv.org/abs/2410.10163
Machine unlearning aims to selectively remove specific knowledge from a model. Current methods, such as task arithmetic, rely on fine-tuning models on the forget set, generating a task vector, and subtracting it from the original model. However, we a
Externí odkaz:
http://arxiv.org/abs/2410.05583
Autor:
Owens, M. Riley, Kim, Keunho J., Bayliss, Matthew B., Rivera-Thorsen, T. Emil, Sharon, Keren, Rigby, Jane R., Navarre, Alexander, Florian, Michael, Gladders, Michael D., Burns, Jessica G., Khullar, Gourav, Chisholm, John, Mahler, Guillaume, Dahle, Hakon, Malhas, Christopher M., Welch, Brian, Hutchison, Taylor A., Gassis, Raven, Choe, Suhyeon, Adhikari, Prasanna
We investigate the Lyman-$\alpha$ (Ly$\alpha$) and Lyman continuum (LyC) properties of the Sunburst Arc, a $z=2.37$ gravitationally lensed galaxy with a multiply-imaged, compact region leaking LyC and a triple-peaked Ly$\alpha$ profile indicating dir
Externí odkaz:
http://arxiv.org/abs/2410.03660
Federated Learning is a promising approach for training machine learning models while preserving data privacy, but its distributed nature makes it vulnerable to backdoor attacks, particularly in NLP tasks while related research remains limited. This
Externí odkaz:
http://arxiv.org/abs/2409.14805
Autor:
Cioppa, Anthony, Giancola, Silvio, Somers, Vladimir, Joos, Victor, Magera, Floriane, Held, Jan, Ghasemzadeh, Seyed Abolfazl, Zhou, Xin, Seweryn, Karolina, Kowalczyk, Mateusz, Mróz, Zuzanna, Łukasik, Szymon, Hałoń, Michał, Mkhallati, Hassan, Deliège, Adrien, Hinojosa, Carlos, Sanchez, Karen, Mansourian, Amir M., Miralles, Pierre, Barnich, Olivier, De Vleeschouwer, Christophe, Alahi, Alexandre, Ghanem, Bernard, Van Droogenbroeck, Marc, Gorski, Adam, Clapés, Albert, Boiarov, Andrei, Afanasiev, Anton, Xarles, Artur, Scott, Atom, Lim, ByoungKwon, Yeung, Calvin, Gonzalez, Cristian, Rüfenacht, Dominic, Pacilio, Enzo, Deuser, Fabian, Altawijri, Faisal Sami, Cachón, Francisco, Kim, HanKyul, Wang, Haobo, Choe, Hyeonmin, Kim, Hyunwoo J, Kim, Il-Min, Kang, Jae-Mo, Tursunboev, Jamshid, Yang, Jian, Hong, Jihwan, Lee, Jimin, Zhang, Jing, Lee, Junseok, Zhang, Kexin, Habel, Konrad, Jiao, Licheng, Li, Linyi, Gutiérrez-Pérez, Marc, Ortega, Marcelo, Li, Menglong, Lopatto, Milosz, Kasatkin, Nikita, Nemtsev, Nikolay, Oswald, Norbert, Udin, Oleg, Kononov, Pavel, Geng, Pei, Alotaibi, Saad Ghazai, Kim, Sehyung, Ulasen, Sergei, Escalera, Sergio, Zhang, Shanshan, Yang, Shuyuan, Moon, Sunghwan, Moeslund, Thomas B., Shandyba, Vasyl, Golovkin, Vladimir, Dai, Wei, Chung, WonTaek, Liu, Xinyu, Zhu, Yongqiang, Kim, Youngseo, Li, Yuan, Yang, Yuting, Xiao, Yuxuan, Cheng, Zehua, Li, Zhihao
The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field unde
Externí odkaz:
http://arxiv.org/abs/2409.10587
This report presents a solution for the swing-up and stabilisation tasks of the acrobot and the pendubot, developed for the AI Olympics competition at IROS 2024. Our approach employs the Average-Reward Entropy Advantage Policy Optimization (AR-EAPO),
Externí odkaz:
http://arxiv.org/abs/2409.08938
Recent Vision Transformer (ViT)-based methods for Image Super-Resolution have demonstrated impressive performance. However, they suffer from significant complexity, resulting in high inference times and memory usage. Additionally, ViT models using Wi
Externí odkaz:
http://arxiv.org/abs/2409.03516
Hallucinations in Multimodal Large Language Models (MLLMs) where generated responses fail to accurately reflect the given image pose a significant challenge to their reliability. To address this, we introduce ConVis, a novel training-free contrastive
Externí odkaz:
http://arxiv.org/abs/2408.13906