Kelvin Guu
Artificial Intelligence · 2015–2025
A researcher in the Science corpus: 20 papers; trusts 1,660 researchers and is trusted by 1,469 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 723 citations into it; #797 of 36,961 by trust here, #882 by citations
- Natural Language Processing — 458 citations into it; #650 of 5,725 by trust here, #863 by citations
- Computer Vision and Pattern Recognition — 277 citations into it; #2,865 of 21,973 by trust here, #1,186 by citations
- Evaluation & Benchmarks — 111 citations into it; #922 of 3,155 by trust here, #2,101 by citations
- Large Language Models — 96 citations into it; #423 of 810 by trust here, #199 by citations
- Information Retrieval & Search — 94 citations into it; #140 of 1,022 by trust here, #78 by citations
- Information Systems — 66 citations into it; #7,736 of 9,233 by trust here, #3,191 by citations
- Representation & Self-Supervised Learning — 63 citations into it
Whom Kelvin Guu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Yoshua Bengio
- Geoffrey E. Hinton
- Ilya Sutskever
- Richard Socher
- Alex Krizhevsky
- Tomas Mikolov
- Ronald J. Williams
- Alex Graves
- Oriol Vinyals
Who trusts Kelvin Guu overall
- Percy Liang
- Gautier Izacard
- Sewon Min
- Graham Neubig
- Luyu Gao
- Kalpesh Krishna
- Danqi Chen
- Patrick Lewis
- Panupong Pasupat
- Michihiro Yasunaga
Papers from Kelvin Guu's perspective
Ordered by how strongly the researchers Kelvin Guu trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Finetuned Language Models Are Zero-Shot Learners (2021) — 5,221 citations
- REALM: Retrieval-Augmented Language Model Pre-Training (2020) — 3,207 citations
- Generating Sentences by Editing Prototypes (2017) — 326 citations
- From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood (2017) — 199 citations
- Traversing Knowledge Graphs in Vector Space (2015) — 367 citations
- Transforming Question Answering Datasets Into Natural Language Inference Datasets (2018) — 187 citations
- KERMIT: Generative Insertion-Based Modeling for Sequences (2019) — 67 citations
- Dialog Inpainting: Turning Documents into Dialogs (2022) — 77 citations
- Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration (2018) — 349 citations
- Neural Data Augmentation via Example Extrapolation (2021) — 75 citations
- Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations (2021) — 72 citations
- Attributed Text Generation via Post-hoc Research and Revision (2022) — 27 citations
- Controllable Semantic Parsing via Retrieval Augmentation (2021) — 50 citations
- RARR: Researching and Revising What Language Models Say, Using Language Models (2022) — 339 citations
- Tracing Knowledge in Language Models Back to the Training Data (2022) — 29 citations
- Mapping natural language commands to web elements (2018) — 52 citations
- Promptagator: Few-shot Dense Retrieval From 8 Examples (2022) — 350 citations
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
- Towards Tracing Knowledge in Language Models Back to the Training Data (2022) — 71 citations
- A Retrieve-and-Edit Framework for Predicting Structured Outputs (2018) — 188 citations