Percy Liang
Artificial Intelligence · 2005–2025
A researcher in the Science corpus: 160 papers; trusts 5,403 researchers and is trusted by 16,660 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 4,560 citations into it; #42 of 36,961 by trust here, #36 by citations
- Natural Language Processing — 1,915 citations into it; #12 of 5,725 by trust here, #25 by citations
- Computer Vision and Pattern Recognition — 1,673 citations into it; #470 of 21,973 by trust here, #140 by citations
- Safety, Robustness & Interpretability — 562 citations into it; #11 of 2,259 by trust here, #8 by citations
- Evaluation & Benchmarks — 561 citations into it; #32 of 3,155 by trust here, #28 by citations
- Representation & Self-Supervised Learning — 478 citations into it; #333 of 3,156 by trust here, #529 by citations
- Large Language Models — 474 citations into it; #281 of 810 by trust here, #81 by citations
- Information Systems — 352 citations into it; #231 of 9,233 by trust here, #142 by citations
Whom Percy Liang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yoshua Bengio
- Ilya Sutskever
- Kaiming He
- Michael Collins
- Richard Socher
- Alex Graves
- Yann LeCun
Who trusts Percy Liang overall
- Mohit Bansal
- Jonathan Berant
- Quoc V. Le
- Luke S. Zettlemoyer
- Jacob Andreas
- Christopher D. Manning
- Yoshua Bengio
- Jianfeng Gao
- Yonatan Belinkov
- Graham Neubig
Papers from Percy Liang's perspective
Ordered by how strongly the researchers Percy Liang 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)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- SQuAD: 100,000+ Questions for Machine Comprehension of Text (2016) — 9,586 citations
- Semantic Parsing on Freebase from Question-Answer Pairs (2013) — 2,231 citations
- Know What You Don’t Know: Unanswerable Questions for SQuAD (2018) — 3,369 citations
- Adversarial Examples for Evaluating Reading Comprehension Systems (2017) — 1,727 citations
- On the Opportunities and Risks of Foundation Models (2021) — 6,923 citations
- Learning Dependency-Based Compositional Semantics (2011) — 618 citations
- Prefix-Tuning: Optimizing Continuous Prompts for Generation (2021) — 6,083 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- Understanding Black-box Predictions via Influence Functions (2017) — 3,706 citations
- Emergent Abilities of Large Language Models (2022) — 3,700 citations
- QuAC: Question Answering in Context (2018) — 904 citations
- Learning Language Games through Interaction (2016) — 197 citations
- Semantic Parsing via Paraphrasing (2014) — 568 citations
- Compositional Semantic Parsing on Semi-Structured Tables (2015) — 1,061 citations
- Generating Sentences by Editing Prototypes (2017) — 326 citations
- Data Recombination for Neural Semantic Parsing (2016) — 480 citations
- Dropout Training as Adaptive Regularization (2013) — 645 citations
- Learning Semantic Correspondences with Less Supervision (2009) — 361 citations
- Video Event Understanding Using Natural Language Descriptions (2013) — 61 citations
- From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood (2017) — 199 citations