Zobrazeno 1 - 10
of 16 137
pro vyhledávání: '"Wang, Di"'
Deep learning has made profound impacts in the domains of data mining and AI, distinguished by the groundbreaking achievements in numerous real-world applications and the innovative algorithm design philosophy. However, it suffers from the inconsiste
Externí odkaz:
http://arxiv.org/abs/2409.14174
Semantic segmentation of large-scale point clouds is of significant importance in environment perception and scene understanding. However, point clouds collected from real-world environments are usually imbalanced and small-sized objects are prone to
Externí odkaz:
http://arxiv.org/abs/2409.13983
Large Language Models (LLMs) have demonstrated significant capabilities across numerous application domains. A key challenge is to keep these models updated with latest available information, which limits the true potential of these models for the en
Externí odkaz:
http://arxiv.org/abs/2409.12257
Multiple rotation averaging plays a crucial role in computer vision and robotics domains. The conventional optimization-based methods optimize a nonlinear cost function based on certain noise assumptions, while most previous learning-based methods re
Externí odkaz:
http://arxiv.org/abs/2409.09790
Expanding the receptive field in a deep learning model for large-scale 3D point cloud segmentation is an effective technique for capturing rich contextual information, which consequently enhances the network's ability to learn meaningful features. Ho
Externí odkaz:
http://arxiv.org/abs/2409.01662
Autor:
Mai, Yifan, Croom, Scott M., Wisnioski, Emily, Vaughan, Sam P., Varidel, Mathew R., Battisti, Andrew J., Mendel, J. Trevor, Mun, Marcie, Tsukui, Takafumi, Foster, Caroline, Harborne, Katherine E., Lagos, Claudia D. P., Wang, Di, Bellstedt, Sabine, Bland-Hawthorn, Joss, Colless, Matthew, D'Eugenio, Francesco, Grasha, Kathryn, Peng, Yingjie, Santucci, Giulia, Sweet, Sarah M., Thater, Sabine, Valenzuela, Lucas M., Ziegler, Bodo
We measure the ionised gas velocity dispersions of star-forming galaxies in the MAGPI survey ($z\sim0.3$) and compare them with galaxies in the SAMI ($z\sim0.05$) and KROSS ($z\sim1$) surveys to investigate how the ionised gas velocity dispersion evo
Externí odkaz:
http://arxiv.org/abs/2408.12224
Autor:
Wang, An, Sun, Xingwu, Xie, Ruobing, Li, Shuaipeng, Zhu, Jiaqi, Yang, Zhen, Zhao, Pinxue, Han, J. N., Kang, Zhanhui, Wang, Di, Okazaki, Naoaki, Xu, Cheng-zhong
Mixture of Experts (MoE) offers remarkable performance and computational efficiency by selectively activating subsets of model parameters. Traditionally, MoE models use homogeneous experts, each with identical capacity. However, varying complexity in
Externí odkaz:
http://arxiv.org/abs/2408.10681
Autor:
Huang, Changze, Wang, Di
Gaussian Processes (GPs) provide a powerful framework for making predictions and understanding uncertainty for classification with kernels and Bayesian non-parametric learning. Building such models typically requires strong prior knowledge to define
Externí odkaz:
http://arxiv.org/abs/2408.07875
Autor:
Aggarwal, Gagan, Badanidiyuru, Ashwinkumar, Balseiro, Santiago R., Bhawalkar, Kshipra, Deng, Yuan, Feng, Zhe, Goel, Gagan, Liaw, Christopher, Lu, Haihao, Mahdian, Mohammad, Mao, Jieming, Mehta, Aranyak, Mirrokni, Vahab, Leme, Renato Paes, Perlroth, Andres, Piliouras, Georgios, Schneider, Jon, Schvartzman, Ariel, Sivan, Balasubramanian, Spendlove, Kelly, Teng, Yifeng, Wang, Di, Zhang, Hanrui, Zhao, Mingfei, Zhu, Wennan, Zuo, Song
In this survey, we summarize recent developments in research fueled by the growing adoption of automated bidding strategies in online advertising. We explore the challenges and opportunities that have arisen as markets embrace this autobidding and co
Externí odkaz:
http://arxiv.org/abs/2408.07685
Though pre-trained encoders can be easily accessed online to build downstream machine learning (ML) services quickly, various attacks have been designed to compromise the security and privacy of these encoders. While most attacks target encoders on t
Externí odkaz:
http://arxiv.org/abs/2408.02814