Kushal Arora

Artificial Intelligence · 2022

A researcher in the Science corpus: 4 papers; trusts 86 researchers and is trusted by 3 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 153 citations into it; #25,671 of 35,345 by trust here, #13,353 by citations
• Natural Language Processing — 126 citations into it; #4,227 of 5,688 by trust here, #2,846 by citations
• Computer Vision and Pattern Recognition — 49 citations into it
• Safety, Robustness & Interpretability — 31 citations into it
• Retrieval-Augmented Generation — 8 citations into it
• Reinforcement Learning — 8 citations into it
• Management Science and Operations Research — 5 citations into it
• Optimization & Training — 5 citations into it

Whom Kushal Arora trusts overall

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

1. Diederik P. Kingma
2. Emily Dinan
3. Geoffrey E. Hinton
4. Jason Aaron Edward Weston
5. Yoshua Bengio
6. Stéphane Ross
7. Ilya Sutskever
8. Jimmy Ba
9. Alex Krizhevsky
10. Eric Michael Smith

Who trusts Kushal Arora overall

1. Jing Xu
2. Weiyan Shi
3. Kurt Shuster
4. Nicholas Meade
5. Emily Dinan
6. Mojtaba Komeili
7. Megan Ung
8. Jason Aaron Edward Weston

Papers from Kushal Arora's perspective

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

1. Attention is All you Need (Neural Information Processing Systems)
2. ImageNet classification with deep convolutional neural networks
3. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
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. Gradient-based learning applied to document recognition
8. ImageNet: A large-scale hierarchical image database
9. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
10. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)

Their papers

• BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage (2022) — 297 citations
• Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback (2022) — 47 citations
• Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation (2022) — 131 citations
• Director: Generator-Classifiers For Supervised Language Modeling (2022) — 51 citations