Aman Madaan

Artificial Intelligence · 2020–2023

A researcher in the Science corpus: 12 papers; trusts 148 researchers and is trusted by 14 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 376 citations into it; #12,223 of 35,345 by trust here, #2,989 by citations
• Natural Language Processing — 301 citations into it
• Evaluation & Benchmarks — 128 citations into it
• Computer Vision and Pattern Recognition — 119 citations into it
• Large Language Models — 82 citations into it
• Information Systems — 70 citations into it; #5,041 of 8,771 by trust here, #2,604 by citations
• Prompting & Reasoning — 52 citations into it; #110 of 359 by trust here, #183 by citations
• Computer Networks and Communications — 13 citations into it

Whom Aman Madaan trusts overall

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

1. Geoffrey E. Hinton
2. Yoshua Bengio
3. Diederik P. Kingma
4. Ilya Sutskever
5. Alex Krizhevsky
6. Yann LeCun
7. Kaiming He
8. Alex Graves
9. Ruslan Salakhutdinov
10. Richard Socher

Who trusts Aman Madaan overall

1. Luyu Gao
2. Xinyun Chen
3. Zhiyuan Li
4. D'idac Sur'is
5. Shuyan Zhou
6. Uri Alon
7. Geunwoo Kim
8. Xiang Yue
9. Denny Zhou
10. Jie Huang

Papers from Aman Madaan's perspective

Ordered by how strongly the researchers Aman Madaan 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. ImageNet: A large-scale hierarchical image database
8. Gradient-based learning applied to document recognition
9. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
10. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)

Their papers

• The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics (2021) — 329 citations
• Self-Refine: Iterative Refinement with Self-Feedback (2023) — 4,061 citations
• PAL: Program-aided Language Models (2022) — 774 citations
• Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango (2022) — 153 citations
• Politeness Transfer: A Tag and Generate Approach (2020) — 174 citations
• GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022) — 43 citations
• Language Models of Code are Few-Shot Commonsense Learners (2022) — 278 citations
• Learning to repair: Repairing model output errors after deployment using a dynamic memory of feedback (2021) — 45 citations
• Think about it! Improving defeasible reasoning by first modeling the question scenario. (2021) — 35 citations
• Learning Performance-Improving Code Edits (2023) — 155 citations
• Memory-assisted prompt editing to improve GPT-3 after deployment (2022) — 194 citations
• Interscript: A dataset for interactive learning of scripts through error feedback (2021) — 12 citations