Zobrazeno 1 - 10
of 14 505
pro vyhledávání: '"Xu, Yu"'
Autor:
Xu, Yu, Tang, Fan, Cao, Juan, Zhang, Yuxin, Kong, Xiaoyu, Li, Jintao, Deussen, Oliver, Lee, Tong-Yee
Diffusion Transformers (DiTs) have exhibited robust capabilities in image generation tasks. However, accurate text-guided image editing for multimodal DiTs (MM-DiTs) still poses a significant challenge. Unlike UNet-based structures that could utilize
Externí odkaz:
http://arxiv.org/abs/2411.15034
Autor:
Bai, Ai-Yu, Cai, Hanjie, Chen, Chang-Lin, Chen, Siyuan, Chen, Xurong, Chen, Yu, Cheng, Weibin, Dai, Ling-Yun, Fan, Rui-Rui, Gong, Li, Guo, Zihao, He, Yuan, Hou, Zhilong, Huang, Yinyuan, Jia, Huan, Jiang, Hao, Jing, Han-Tao, Kang, Xiaoshen, Li, Hai-Bo, Li, Jincheng, Li, Yang, Liu, Shulin, Lu, Guihao, Miao, Han, Ning, Yunsong, Niu, Jianwei, Peng, Huaxing, Petrov, Alexey A., Qin, Yuanshuai, Sun, Mingchen, Tang, Jian, Tang, Jing-Yu, Tian, Ye, Wang, Rong, Wang, Xiaodong, Wang, Zhichao, Wu, Chen, Xing, Tian-Yu, Xiong, Weizhi, Xu, Yu, Yan, Baojun, Yao, De-Liang, Yu, Tao, Yuan, Ye, Yuan, Yi, Zhang, Yao, Zhang, Yongchao, Zhang, Zhilv, Zhao, Guang, Zhao, Shihan
The spontaneous conversion of muonium to antimuonium is one of the interesting charged lepton flavor violation phenomena, offering a sensitive probe of potential new physics and serving as a tool to constrain the parameter space beyond the Standard M
Externí odkaz:
http://arxiv.org/abs/2410.18817
Autor:
Wang, Han, Sundararaman, Mukuntha Narayanan, Gungor, Onur, Xu, Yu, Kamath, Krishna, Chalasani, Rakesh, Hazra, Kurchi Subhra, Rao, Jinfeng
To improve relevance scoring on Pinterest Search, we integrate Large Language Models (LLMs) into our search relevance model, leveraging carefully designed text representations to predict the relevance of Pins effectively. Our approach uses search que
Externí odkaz:
http://arxiv.org/abs/2410.17152
The proliferation of fake news in the digital age has raised critical concerns, particularly regarding its impact on societal trust and democratic processes. Diverging from conventional agent-based simulation approaches, this work introduces an innov
Externí odkaz:
http://arxiv.org/abs/2410.13909
Large Language Models (LLMs) require precise alignment with complex instructions to optimize their performance in real-world applications. As the demand for refined instruction tuning data increases, traditional methods that evolve simple seed instru
Externí odkaz:
http://arxiv.org/abs/2410.02795
Autor:
Sun, Jiamin, Shu, Shibo, Chai, Ye, Zhu, Lin, Zhang, Lingmei, Li, Yongping, Liu, Zhouhui, Li, Zhengwei, Xu, Yu, Yan, Daikang, Guo, Weijie, Wang, Yiwen, Liu, Congzhan
Fabrication of dielectrics at low temperature is required for temperature-sensitive detectors. For superconducting detectors, such as transition edge sensors and kinetic inductance detectors, AlMn is widely studied due to its variable superconducting
Externí odkaz:
http://arxiv.org/abs/2409.09301
Autor:
Jiang, Lei, Xu, Yu, Li, Shaowei, Yan, Zhiguang, Gong, Ming, Rong, Tao, Sun, Chenyin, Sun, Tianzuo, Jiang, Tao, Deng, Hui, Zha, Chen, Lin, Jin, Chen, Fusheng, Zhu, Qingling, Ye, Yangsen, Rong, Hao, Yan, Kai, Cao, Sirui, Li, Yuan, Guo, Shaojun, Qian, Haoran, Hu, Yisen, Wu, Yulin, Li, Yuhuai, Wu, Gang, Wang, Xueshen, Wang, Shijian, Cao, Wenhui, Wang, Yeru, Li, Jinjin, Peng, Cheng-Zhi, Zhu, Xiaobo, Pan, Jian-Wei
Frequency tunable qubit plays a significant role for scalable superconducting quantum processors. The state-of-the-art room-temperature electronics for tuning qubit frequency suffers from unscalable limit, such as heating problem, linear growth of co
Externí odkaz:
http://arxiv.org/abs/2407.21415
The effective alignment of Large Language Models (LLMs) with precise instructions is essential for their application in diverse real-world scenarios. Current methods focus on enhancing the diversity and complexity of training and evaluation samples,
Externí odkaz:
http://arxiv.org/abs/2406.11301
Autor:
Xu, Yu, Alvarado-Gómez, Julián D., Tian, Hui, Poppenhäger, Katja, Guerrero, Gustavo, Liu, Xianyu
Coronal mass ejections (CMEs) on stars can change the stars' magnetic field configurations and mass loss rates during the eruption and propagation and therefore, may affect the stars' rotation properties on long time-scales. The dynamics of stellar C
Externí odkaz:
http://arxiv.org/abs/2406.08194
Autor:
Lin, Haoxin, Xu, Yu-Yan, Sun, Yihao, Zhang, Zhilong, Li, Yi-Chen, Jia, Chengxing, Ye, Junyin, Zhang, Jiaji, Yu, Yang
Model-based methods in reinforcement learning offer a promising approach to enhance data efficiency by facilitating policy exploration within a dynamics model. However, accurately predicting sequential steps in the dynamics model remains a challenge
Externí odkaz:
http://arxiv.org/abs/2405.17031