Author of the publication

The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers.

, , and . EMNLP (1), page 619-634. Association for Computational Linguistics, (2021)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

 

Other publications of authors with the same name

RWTH ASR Systems for LibriSpeech: Hybrid vs Attention., , , , , , , and . INTERSPEECH, page 231-235. ISCA, (2019)Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules., , and . NeurIPS, (2022)A Modern Self-Referential Weight Matrix That Learns to Modify Itself., , , and . ICML, volume 162 of Proceedings of Machine Learning Research, page 9660-9677. PMLR, (2022)Linear Transformers Are Secretly Fast Weight Programmers., , and . ICML, volume 139 of Proceedings of Machine Learning Research, page 9355-9366. PMLR, (2021)The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention., , and . ICML, volume 162 of Proceedings of Machine Learning Research, page 9639-9659. PMLR, (2022)Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions., , and . EMNLP, page 9455-9465. Association for Computational Linguistics, (2023)On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition., , , , , and . INTERSPEECH, page 3800-3804. ISCA, (2019)How Much Self-Attention Do We Need? Trading Attention for Feed-Forward Layers., , , and . ICASSP, page 6154-6158. IEEE, (2020)MoEUT: Mixture-of-Experts Universal Transformers., , , , and . CoRR, (2024)The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment., , , , , and . ICASSP, page 7839-7843. IEEE, (2020)