Zobrazeno 1 - 10
of 4 416
pro vyhledávání: '"Sheng, Jun"'
Traditional knowledge distillation focuses on aligning the student's predicted probabilities with both ground-truth labels and the teacher's predicted probabilities. However, the transition to predicted probabilities from logits would obscure certain
Externí odkaz:
http://arxiv.org/abs/2411.08937
Autor:
Choi, Youngwoo, Kwon, Woojin, Pattle, Kate, Arzoumanian, Doris, Bourke, Tyler L., Hoang, Thiem, Hwang, Jihye, Koch, Patrick M., Sadavoy, Sarah, Bastien, Pierre, Furuya, Ray, Lai, Shih-Ping, Qiu, Keping, Ward-Thompson, Derek, Berry, David, Byun, Do-Young, Chen, Huei-Ru Vivien, Chen, Wen Ping, Chen, Mike, Chen, Zhiwei, Ching, Tao-Chung, Cho, Jungyeon, Choi, Minho, Choi, Yunhee, Coudé, Simon, Chrysostomou, Antonio, Chung, Eun Jung, Dai, Sophia, Debattista, Victor, Di Francesco, James, Diep, Pham Ngoc, Doi, Yasuo, Duan, Hao-Yuan, Duan, Yan, Eswaraiah, Chakali, Fanciullo, Lapo, Fiege, Jason, Fissel, Laura M., Franzmann, Erica, Friberg, Per, Friesen, Rachel, Fuller, Gary, Gledhill, Tim, Graves, Sarah, Greaves, Jane, Griffin, Matt, Gu, Qilao, Han, Ilseung, Hasegawa, Tetsuo, Houde, Martin, Hull, Charles L. H., Inoue, Tsuyoshi, Inutsuka, Shu-ichiro, Iwasaki, Kazunari, Jeong, Il-Gyo, Johnstone, Doug, Karoly, Janik, Könyves, Vera, Kang, Ji-hyun, Lacaille, Kevin, Law, Chi-Yan, Lee, Chang Won, Lee, Hyeseung, Lee, Chin-Fei, Lee, Jeong-Eun, Lee, Sang-Sung, Li, Dalei, Li, Di, Li, Guangxing, Li, Hua-bai, Lin, Sheng-Jun, Liu, Hong-Li, Liu, Tie, Liu, Sheng-Yuan, Liu, Junhao, Longmore, Steven, Lu, Xing, Lyo, A-Ran, Mairs, Steve, Matsumura, Masafumi, Matthews, Brenda, Moriarty-Schieven, Gerald, Nagata, Tetsuya, Nakamura, Fumitaka, Nakanishi, Hiroyuki, Ngoc, Nguyen Bich, Ohashi, Nagayoshi, Onaka, Takashi, Park, Geumsook, Parsons, Harriet, Peretto, Nicolas, Priestley, Felix, Pyo, Tae-Soo, Qian, Lei, Rao, Ramprasad, Rawlings, Jonathan, Rawlings, Mark, Retter, Brendan, Richer, John, Rigby, Andrew, Saito, Hiro, Savini, Giorgio, Seta, Masumichi, Sharma, Ekta, Shimajiri, Yoshito, Shinnaga, Hiroko, Soam, Archana, Kang, Miju, Kataoka, Akimasa, Kawabata, Koji, Kemper, Francisca, Kim, Jongsoo, Kim, Shinyoung, Kim, Gwanjeong, Kim, Kyoung Hee, Kim, Mi-Ryang, Kim, Kee-Tae, Kim, Hyosung, Kirchschlager, Florian, Kirk, Jason, Kobayashi, Masato I. N., Kusune, Takayoshi, Kwon, Jungmi, Tamura, Motohide, Tang, Ya-Wen, Tang, Xindi, Tomisaka, Kohji, Tsukamoto, Yusuke, Viti, Serena, Wang, Hongchi, Wang, Jia-Wei, Wu, Jintai, Xie, Jinjin, Yang, Meng-Zhe, Yen, Hsi-Wei, Yoo, Hyunju, Yuan, Jinghua, Yun, Hyeong-Sik, Zenko, Tetsuya, Zhang, Guoyin, Zhang, Yapeng, Zhang, Chuan-Peng, Zhou, Jianjun, Zhu, Lei, de Looze, Ilse, André, Philippe, Dowell, C. Darren, Eden, David, Eyres, Stewart, Falle, Sam, Gouellec, Valentin J. M. Le, Poidevin, Frédérick, van Loo, Sven
We present 850 $\mu$m polarization observations of the IC 348 star-forming region in the Perseus molecular cloud as part of the B-fields In STar-forming Region Observation (BISTRO) survey. We study the magnetic properties of two cores (HH 211 MMS and
Externí odkaz:
http://arxiv.org/abs/2411.01960
Active learning (AL) has achieved great success by selecting the most valuable examples from unlabeled data. However, they usually deteriorate in real scenarios where open-set noise gets involved, which is studied as open-set annotation (OSA). In thi
Externí odkaz:
http://arxiv.org/abs/2409.17607
Large language models (LLMs) have shown great potential in code-related tasks, yet open-source models lag behind their closed-source counterparts. To bridge this performance gap, existing methods generate vast amounts of synthetic data for fine-tunin
Externí odkaz:
http://arxiv.org/abs/2408.02193
Semi-supervised multi-label learning (SSMLL) is a powerful framework for leveraging unlabeled data to reduce the expensive cost of collecting precise multi-label annotations. Unlike semi-supervised learning, one cannot select the most probable label
Externí odkaz:
http://arxiv.org/abs/2407.18624
Current knowledge distillation (KD) methods primarily focus on transferring various structured knowledge and designing corresponding optimization goals to encourage the student network to imitate the output of the teacher network. However, introducin
Externí odkaz:
http://arxiv.org/abs/2407.03719
Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently. Existing AL algorithms often rely on iterative model training, which can be computationally expensive, parti
Externí odkaz:
http://arxiv.org/abs/2405.14121
Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method called \emph
Externí odkaz:
http://arxiv.org/abs/2405.14111
Publikováno v:
A&A 688, A118 (2024)
Molecular deuteration is commonly seen in starless cores and is expected to occur on a timescale comparable to that of the core contraction. Thus, the deuteration serves as a chemical clock, allowing us to investigate dynamical theories of core forma
Externí odkaz:
http://arxiv.org/abs/2405.13317
Autor:
Hemati, Hamed, Pellegrini, Lorenzo, Duan, Xiaotian, Zhao, Zixuan, Xia, Fangfang, Masana, Marc, Tscheschner, Benedikt, Veas, Eduardo, Zheng, Yuxiang, Zhao, Shiji, Li, Shao-Yuan, Huang, Sheng-Jun, Lomonaco, Vincenzo, van de Ven, Gido M.
Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world problems, the concept of repetition in the data stream is not often con
Externí odkaz:
http://arxiv.org/abs/2405.04101