PaperNote (Total 10 articles)
ICPC-2018 Deep code comment generation
GTC-2020 Megatron-LM:Training Multi-Billion Parameter Language Models Using Model Parallelism
NIPS-2019 GPipe:Efficient Training of Giant Neural Networks using Pipeline Parallelism
EMNLP-2021 Rethinking Data Augmentation for Low-Resource Neural Machine Translation:A Multi-Task Learning Approach
ACL-2019 Improving Robustness of Neural Machine Translation with Multi-task Learning
Google-2022 Pathways:Asynchronous Distributed Dataflow for ML
ICML-2021 Is Space-Time Attention All You Need for Video Understanding
ICCV-2019 SlowFast Networks for Video Recognition
CVPR-2018 A Closer Look at Spatiotemporal Convolutions for Action Recognition
CVPR-2018 Non-local Neural Networks