Neutrino Physics with JUNO
Journal of Physics G: Nuclear and Particle Physics(2016)
E China Univ Sci & Technol | Inst High Energy Phys | Univ Sci & Technol China | Ist Nazl Fis Nucl | Univ Strasbourg | Ohio State Univ | Russian Acad Sci | Natl Taiwan Univ | Univ Padua | Ecole Polytech | Ctr Phys Particules Marseille | CEA | Wuhan Univ | Natl United Univ | Tsinghua Univ | Nanjing Univ | North China Elect Power Univ | Univ Libre Bruxelles | MIT | Argonne Natl Lab | Univ Hawaii | Univ Oulu | Wuyi Univ | Tech Univ Munich | Chinese Acad Geol Sci | Joint Inst Nucl Res | Forschungszentrum Julich | Shanghai Jiao Tong Univ | Beijing Normal Univ | Univ Hamburg | China Inst Atom Energy | Shandong Univ | Harbin Inst Technol | Yerevan Phys Inst | Univ Maryland | Dongguan Univ Technol | Univ Tubingen | Charles Univ Prague | Chongqing Univ | Sun Yat Sen Univ | Natl Chiao Tung Univ | Univ Houston | Guangxi Univ | Univ Chinese Acad Sci | Jilin Univ | Xiamen Univ | Univ Ferrara | Peking Univ | Univ Rome Tre | Pontificia Univ Catolica Chile | Univ Illinois | Brookhaven Natl Lab | Max Planck Inst Phys & Astrophys | Columbia Univ | Rhein Westfal TH Aachen | Univ Jyvaskyla | Johannes Gutenberg Univ Mainz | Sichuan Univ | Univ Nantes | Nankai Univ | Xi An Jiao Tong Univ | Acad Sinica
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

被引用47 | 浏览
被引用72 | 浏览
被引用283 | 浏览
被引用1709 | 浏览
被引用81 | 浏览
被引用74 | 浏览