Zobrazeno 1 - 10
of 16 664
pro vyhledávání: '"P, Tsui"'
Autor:
Shao, Kunming, Tian, Fengshi, Wang, Xiaomeng, Zheng, Jiakun, Chen, Jia, He, Jingyu, Wu, Hui, Chen, Jinbo, Guan, Xihao, Deng, Yi, Tu, Fengbin, Yang, Jie, Sawan, Mohamad, Cheng, Tim Kwang-Ting, Tsui, Chi-Ying
Digital Computing-in-Memory (DCIM) is an innovative technology that integrates multiply-accumulation (MAC) logic directly into memory arrays to enhance the performance of modern AI computing. However, the need for customized memory cells and logic co
Externí odkaz:
http://arxiv.org/abs/2411.16806
Substantial efforts have been devoted to alleviating the impact of the long-tailed class distribution in federated learning. In this work, we observe an interesting phenomenon that weak classes consistently exist even for class-balanced learning. The
Externí odkaz:
http://arxiv.org/abs/2411.15403
In time-series analysis, many recent works seek to provide a unified view and representation for time-series across multiple domains, leading to the development of foundation models for time-series data. Despite diverse modeling techniques, existing
Externí odkaz:
http://arxiv.org/abs/2411.01006
Autor:
Sun, Chung-En, Liu, Xiaodong, Yang, Weiwei, Weng, Tsui-Wei, Cheng, Hao, San, Aidan, Galley, Michel, Gao, Jianfeng
Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended responses. Current
Externí odkaz:
http://arxiv.org/abs/2410.18469
With the rapid growth of black-box models in machine learning, Shapley values have emerged as a popular method for model explanations due to their theoretical guarantees. Shapley values locally explain a model to an input query using additive feature
Externí odkaz:
http://arxiv.org/abs/2410.19236
Identifying and localizing objects within images is a fundamental challenge, and numerous efforts have been made to enhance model accuracy by experimenting with diverse architectures and refining training strategies. Nevertheless, a prevalent limitat
Externí odkaz:
http://arxiv.org/abs/2410.15346
This work is a portable MetaVerse implementation, and we use 3D pose estimation with AI to make virtual avatars do synchronized actions and interact with the environment. The motivation is that we find it inconvenient to use joysticks and sensors whe
Externí odkaz:
http://arxiv.org/abs/2410.15343
It is a common problem in robotics to specify the position of each joint of the robot so that the endpoint reaches a certain target in space. This can be solved in two ways, forward kinematics method and inverse kinematics method. However, inverse ki
Externí odkaz:
http://arxiv.org/abs/2410.15341
Autor:
Collaboration, Super-Kamiokande, Taniuchi, N., Abe, K., Abe, S., Asaoka, Y., Bronner, C., Harada, M., Hayato, Y., Hiraide, K., Hosokawa, K., Ieki, K., Ikeda, M., Kameda, J., Kanemura, Y., Kaneshima, R., Kashiwagi, Y., Kataoka, Y., Miki, S., Mine, S., Miura, M., Moriyama, S., Nakahata, M., Nakayama, S., Noguchi, Y., Pronost, G., Okamoto, K., Sato, K., Sekiya, H., Shiba, H., Shimizu, K., Shiozawa, M., Sonoda, Y., Suzuki, Y., Takeda, A., Takemoto, Y., Takenaka, A., Tanaka, H., Watanabe, S., Yano, T., Kajita, T., Okumura, K., Tashiro, T., Tomiya, T., Wang, X., Yoshida, S., Megias, G. D., Fernandez, P., Labarga, L., Ospina, N., Zaldivar, B., Pointon, B. W., Kearns, E., Mirabito, J., Raaf, J. L., Wan, L., Wester, T., Bian, J., Griskevich, N. J., Kropp, W. R., Locke, S., Smy, M. B., Sobel, H. W., Takhistov, V., Yankelevich, A., Hill, J., Jang, M. C., Kim, J. Y., Lee, S. H., Lim, I. T., Moon, D. H., Park, R. G., Yang, B. S., Bodur, B., Scholberg, K., Walter, C. W., Beauchêne, A., Bernard, L., Coffani, A., Drapier, O., Hedri, S. El, Giampaolo, A., Mueller, Th. A., Santos, A. D., Paganini, P., Rogly, R., Nakamura, T., Jang, J. S., Machado, L. N., Learned, J. G., Choi, K., Iovine, N., Cao, S., Anthony, L. H. V., Martin, D., Prouse, N. W., Scott, M., Sztuc, A. A., Uchida, Y., Berardi, V., Calabria, N. F., Catanesi, M. G., Radicioni, E., Langella, A., De Rosa, G., Collazuol, G., Feltre, M., Iacob, F., Lamoureux, M., Mattiazzi, M., Ludovici, L., Gonin, M., Périssé, L., Quilain, B., Fujisawa, C., Horiuchi, S., Kobayashi, M., Liu, Y. M., Maekawa, Y., Nishimura, Y., Okazaki, R., Akutsu, R., Friend, M., Hasegawa, T., Ishida, T., Kobayashi, T., Jakkapu, M., Matsubara, T., Nakadaira, T., Nakamura, K., Oyama, Y., Yrey, A. Portocarrero, Sakashita, K., Sekiguchi, T., Tsukamoto, T., Bhuiyan, N., Boschi, T., Burton, G. T., Di Lodovico, F., Gao, J., Goldsack, A., Katori, T., Migenda, J., Ramsden, R. M., Taani, M., Xie, Z., Zsoldos, S., Kotsar, Y., Ozaki, H., Suzuki, A. T., Takagi, Y., Takeuchi, Y., Yamamoto, S., Zhong, H., Feng, J., Feng, L., Han, S., Hu, J. R., Hu, Z., Kawaue, M., Kikawa, T., Mori, M., Nakaya, T., Wendell, R. A., Yasutome, K., Jenkins, S. J., McCauley, N., Mehta, P., Tarrant, A., Wilking, M. J., Fukuda, Y., Itow, Y., Menjo, H., Ninomiya, K., Yoshioka, Y., Lagoda, J., Mandal, M., Mijakowski, P., Prabhu, Y. S., Zalipska, J., Jia, M., Jiang, J., Jung, C. K., Shi, W., Yanagisawa, C., Hino, Y., Ishino, H., Ito, S., Kitagawa, H., Koshio, Y., Ma, W., Nakanishi, F., Sakai, S., Tada, T., Tano, T., Ishizuka, T., Barr, G., Barrow, D., Cook, L., Samani, S., Wark, D., Holin, A., Nova, F., Jung, S., Yang, J. Y., Yoo, J., Fannon, J. E. P., Kneale, L., Malek, M., McElwee, J. M., Stone, O., Stowell, P., Thiesse, M. D., Thompson, L. F., Wilson, S. T., Okazawa, H., Lakshmi, S. M., Kim, S. B., Kwon, E., Lee, M. W., Seo, J. W., Yu, I., Ichikawa, A. K., Nakamura, K. D., Tairafune, S., Nishijima, K., Koshiba, M., Eguchi, A., Goto, S., Iwamoto, K., Mizuno, Y., Muro, T., Nakagiri, K., Nakajima, Y., Shima, S., Watanabe, E., Yokoyama, M., de Perio, P., Fujita, S., Jesús-Valls, C., Martens, K., Marti, Ll., Tsui, K. M., Vagins, M. R., Xia, J., Izumiyama, S., Kuze, M., Matsumoto, R., Terada, K., Asaka, R., Inomoto, M., Ishitsuka, M., Ito, H., Kinoshita, T., Ommura, Y., Shigeta, N., Shinoki, M., Suganuma, T., Yamauchi, K., Yoshida, T., Nakano, Y., Martin, J. F., Tanaka, H. A., Towstego, T., Gaur, R., Gousy-Leblanc, V., Hartz, M., Konaka, A., Li, X., Chen, S., Wu, Y., Xu, B. D., Zhang, A. Q., Zhang, B., Posiadala-Zezula, M., Boyd, S. B., Edwards, R., Hadley, D., Nicholson, M., O'Flaherty, M., Richards, B., Ali, A., Jamieson, B., Amanai, S., Minamino, A., Pintaudi, G., Sano, S., Sasaki, R., Shibayama, R., Shimamura, R., Suzuki, S., Wada, K.
A search for proton decay into $e^+/\mu^+$ and a $\eta$ meson has been performed using data from a 0.373 Mton$\cdot$year exposure (6050.3 live days) of Super-Kamiokande. Compared to previous searches this work introduces an improved model of the intr
Externí odkaz:
http://arxiv.org/abs/2409.19633
Autor:
Kulkarni, Akshay, Weng, Tsui-Wei
We propose a novel and low-cost test-time adversarial defense by devising interpretability-guided neuron importance ranking methods to identify neurons important to the output classes. Our method is a training-free approach that can significantly imp
Externí odkaz:
http://arxiv.org/abs/2409.15190