Prem Devanbu

Artificial Intelligence · 2020–2024

A researcher in the Science corpus: 6 papers; trusts 205 researchers and is trusted by 5 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 119 citations into it; #17,922 of 35,345 by trust here, #20,377 by citations
• Information Systems — 103 citations into it; #3,625 of 8,771 by trust here, #4,341 by citations
• Natural Language Processing — 90 citations into it; #3,255 of 5,688 by trust here, #4,601 by citations
• Software — 70 citations into it
• Code Generation & Program Synthesis — 37 citations into it; #170 of 220 by trust here, #177 by citations
• Large Language Models — 35 citations into it
• Computer Vision and Pattern Recognition — 34 citations into it
• Program Analysis & Verification — 34 citations into it; #132 of 301 by trust here, #220 by citations

Whom Prem Devanbu trusts overall

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

1. Miltiadis Allamanis
2. Ilya Sutskever
3. Jacob Devlin
4. Geoffrey E. Hinton
5. Yoshua Bengio
6. Rico Sennrich
7. Chin-Yew Lin
8. Diederik P. Kingma
9. Alex Krizhevsky
10. Yann LeCun

Who trusts Prem Devanbu overall

1. Ming-Ho Yee
2. Federico Cassano
3. Kevin Jesse
4. Chun Xia
5. Arjun Guha
6. Amir M. Mir
7. Toufique Ahmed

Papers from Prem Devanbu's perspective

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

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

Their papers

• Learning type annotation: is big data enough? (2021) — 43 citations
• RepairAgent: An Autonomous, LLM-Based Agent for Program Repair (2024) — 387 citations
• Learning to Predict User-Defined Types (2023) — 13 citations
• Few-shot training LLMs for project-specific code-summarization (2022) — 359 citations
• Multilingual training for Software Engineering (2021) — 97 citations
• Patching as Translation: the Data and the Metaphor (2020) — 77 citations