Measurement of forward J/psi production cross-sections in pp collisions at root s = 13 TeV (vol 10, pg 172, 2015)
Journal of High Energy Physics（2017）
Universidade Federal do Rio de Janeiro (UFRJ) | Sezione INFN di Padova | LAL | Center for High Energy Physics | Sezione INFN di Firenze | Physik-Institut | Ecole Polytechnique Fédérale de Lausanne (EPFL) | Università di Ferrara | University of Maryland | School of Physics and Astronomy | Max-Planck-Institut für Kernphysik (MPIK) | European Organization for Nuclear Research (CERN) | Physikalisches Institut | Institute for High Energy Physics (IHEP) | Syracuse University | CPPM | Università della Basilicata | Clermont Université | Department of Physics | Universitat de Barcelona | Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio) | National Center for Nuclear Research (NCBJ) | LAPP | Sezione INFN di Pisa | Centro Brasileiro de Pesquisas Físicas (CBPF) | Nikhef National Institute for Subatomic Physics | Università di Milano Bicocca | Institute of Theoretical and Experimental Physics (ITEP) | LPNHE | Laboratori Nazionali dell’INFN di Frascati | H.H. Wills Physics Laboratory | Institute of Nuclear Physics | University of Birmingham | Fakultät Physik | Università di Modena e Reggio Emilia | Sezione INFN di Roma La Sapienza | Budker Institute of Nuclear Physics (SB RAS) and Novosibirsk State University | Sezione INFN di Cagliari | Oliver Lodge Laboratory | Sezione INFN di Ferrara | LIFAELS | Università di Bologna | Università di Roma Tor Vergata | Università di Genova | Sezione INFN di Genova | Scuola Normale Superiore | Cavendish Laboratory | Henryk Niewodniczanski Institute of Nuclear Physics Polish Academy of Sciences | Sezione INFN di Bologna | Universidad de Santiago de Compostela | Instituto de Fisica Corpuscular (IFIC) | STFC Rutherford Appleton Laboratory | School of Physics | Università di Roma La Sapienza | Imperial College London | Horia Hulubei National Institute of Physics and Nuclear Engineering | AGH - University of Science and Technology | Nikhef National Institute for Subatomic Physics and VU University Amsterdam | Petersburg Nuclear Physics Institute (PNPI) | Institut für Physik
- 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
