Róbert Csordás

CoRR, 2024

Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations.

[BibT_eX]

[DOI]

Christopher Potts

Christopher D. Manning

Atticus Geiger

CoRR, 2024

MoEUT: Mixture-of-Experts Universal Transformers.

[BibT_eX]

[DOI]

Christopher D. Manning

CoRR, 2024

Self-organising Neural Discrete Representation Learning à la Kohonen.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2024, 2024

2023

SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention.

[BibT_eX]

[DOI]

CoRR, 2023

Automating Continual Learning.

[BibT_eX]

[DOI]

CoRR, 2023

Mindstorms in Natural Language-Based Societies of Mind.

[BibT_eX]

[DOI]

CoRR, 2023

Topological Neural Discrete Representation Learning à la Kohonen.

[BibT_eX]

[DOI]

CoRR, 2023

Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions.

[BibT_eX]

[DOI]

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Approximating Two-Layer Feedforward Networks for Efficient Transformers.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Randomized Positional Encodings Boost Length Generalization of Transformers.

[BibT_eX]

[DOI]

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2023

2022

A Generalist Neural Algorithmic Learner.

[BibT_eX]

[DOI]

Proceedings of the Learning on Graphs Conference, 2022

A Modern Self-Referential Weight Matrix That Learns to Modify Itself.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

2021

Improving Baselines in the Wild.

[BibT_eX]

[DOI]

CoRR, 2021

Going Beyond Linear Transformers with Recurrent Fast Weight Programmers.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks.

[BibT_eX]

[DOI]

Sjoerd van Steenkiste

Proceedings of the 9th International Conference on Learning Representations, 2021

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

[BibT_eX]

[DOI]

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

2019

Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control.

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

2015

Detecting Objects Thrown over Fence in Outdoor Scenes.

[BibT_eX]

[DOI]