Aditya Barua

Artificial Intelligence · 2020–2024

A researcher in the Science corpus: 4 papers; trusts 73 researchers and is trusted by 2 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 171 citations into it; #30,557 of 35,345 by trust here, #3,726 by citations
• Natural Language Processing — 128 citations into it; #5,074 of 5,688 by trust here, #1,004 by citations
• Computer Vision and Pattern Recognition — 75 citations into it
• Evaluation & Benchmarks — 40 citations into it
• Model Architectures — 21 citations into it
• Representation & Self-Supervised Learning — 13 citations into it

Whom Aditya Barua trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Yoshua Bengio
2. Geoffrey E. Hinton
3. Alex Graves
4. Diederik P. Kingma
5. Ilya Sutskever
6. Alex Krizhevsky
7. Yann LeCun
8. Kaiming He
9. J. Urgen Schmidhuber
10. Taku Kudo

Who trusts Aditya Barua overall

1. Yi Tay
2. Katikapalli Subramanyam Kalyan
3. Vinh Q. Tran

Papers from Aditya Barua's perspective

Ordered by how strongly the researchers Aditya Barua trusts endorse each paper. Same corpus, a different order for every researcher.

1. Attention is All you Need (Neural Information Processing Systems)
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. ImageNet classification with deep convolutional neural networks
5. Long Short-Term Memory
6. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
7. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
8. ImageNet: A large-scale hierarchical image database
9. Gradient-based learning applied to document recognition
10. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)

Their papers

• mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer (2020) — 3,278 citations
• ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models (2021) — 725 citations
• Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation (2022) — 75 citations
• Gemma: Open Models Based on Gemini Research and Technology (2024) — 1,150 citations