| Sun Sep 05 |
Gaussian Error Linear Units (GELUs) , Hendrycks, Gimpel; 2016 |
Coding |
| Fri Sep 10 |
Adam: A Method for Stochastic Optimization , Kingma, Ba; 2014 |
Review both summaries |
| Wed Sep 15 |
Rethinking “Batch” in BatchNorm , Wu, Johnson; 2021 |
Draft Summary |
| Sun Sep 19 |
Rethinking “Batch” in BatchNorm , Wu, Johnson; 2021 |
Final Summary |
| Wed Sep 22 |
Improving Language Understanding by Generative Pre-Training , Radford, Narasimhan, Salimans, Sutskever; 2018 |
Draft Summary |
| Sun Sep 26 |
Improving Language Understanding by Generative Pre-Training , Radford, Narasimhan, Salimans, Sutskever; 2018 |
Final Summary |
| Sun Oct 03 |
LambdaNetworks: Modeling Long-Range Interactions Without Attention , Bello; 2021 |
Coding |
| Fri Oct 08 |
Perceiver: General Perception with Iterative Attention , Jaegle, Gimeno, Brock, Zisserman, Vinyals, Carreira; 2021 |
Review both summaries |
| Wed Oct 13 |
GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields , Niemeyer, Geiger; 2020 |
Draft Summary |
| Sun Oct 17 |
GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields , Niemeyer, Geiger; 2020 |
Final Summary |
| Wed Oct 20 |
End-to-End Object Detection with Transformers , Carion, Massa, Synnaeve, Usunier, Kirillov, Zagoruyko; 2020 |
Draft Summary |
| Sun Oct 24 |
End-to-End Object Detection with Transformers , Carion, Massa, Synnaeve, Usunier, Kirillov, Zagoruyko; 2020 |
Final Summary |
| Sun Oct 31 |
Center-based 3D Object Detection and Tracking , Yin, Zhou, Krähenbühl; 2020 |
Coding |
| Fri Nov 05 |
Class-Balanced Loss Based on Effective Number of Samples , Cui, Jia, Lin, Song, Belongie; 2019 |
Review both summaries |