Omer Levy
Artificial Intelligence · 2014–2023
A researcher in the Science corpus: 53 papers; trusts 2,759 researchers and is trusted by 8,326 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,380 citations into it; #147 of 36,961 by trust here, #67 by citations
- Natural Language Processing — 992 citations into it; #26 of 5,725 by trust here, #24 by citations
- Computer Vision and Pattern Recognition — 445 citations into it; #1,095 of 21,973 by trust here, #335 by citations
- Evaluation & Benchmarks — 229 citations into it; #79 of 3,155 by trust here, #42 by citations
- Large Language Models — 197 citations into it; #14 of 810 by trust here, #34 by citations
- Representation & Self-Supervised Learning — 180 citations into it; #74 of 3,156 by trust here, #128 by citations
- Model Architectures — 154 citations into it; #240 of 2,288 by trust here, #183 by citations
- Information Systems — 153 citations into it; #707 of 9,233 by trust here, #491 by citations
Whom Omer Levy trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Tomas Mikolov
- Yoshua Bengio
- Diederik P. Kingma
- Peter D. Turney
- Geoffrey E. Hinton
- Ilya Sutskever
- Alex Krizhevsky
- Richard Socher
- Alex Graves
- Jimmy Ba
Who trusts Omer Levy overall
- Yoav Goldberg
- Anna Rogers
- Sunipa Dev
- Oren Melamud
- Ivan Vulic
- Yonatan Belinkov
- Mohit Bansal
- Yi Tay
- Ido Dagan
- Uri Alon
Papers from Omer Levy's perspective
Ordered by how strongly the researchers Omer Levy 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
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Gradient-based learning applied to document recognition
- 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
- RoBERTa: A Robustly Optimized BERT Pretraining Approach (2019) — 30,530 citations
- GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding (2018) — 8,768 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension (2019) — 13,006 citations
- SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems (2019) — 2,854 citations
- Annotation Artifacts in Natural Language Inference Data (2018) — 1,309 citations
- Generalization through Memorization: Nearest Neighbor Language Models (2019) — 1,095 citations
- SpanBERT: Improving Pre-training by Representing and Predicting Spans (2019) — 2,196 citations
- Neural Word Embedding as Implicit Matrix Factorization (2014) — 2,040 citations
- Zero-Shot Relation Extraction via Reading Comprehension (2017) — 854 citations
- Mask-Predict: Parallel Decoding of Conditional Masked Language Models (2019) — 724 citations
- What Does BERT Look at? An Analysis of BERT’s Attention (2019) — 2,073 citations
- Dependency-Based Word Embeddings (2014) — 1,184 citations
- Are Sixteen Heads Really Better than One? (2019) — 1,419 citations
- Linguistic Regularities in Sparse and Explicit Word Representations (2014) — 738 citations
- Improving Distributional Similarity with Lessons Learned from Word Embeddings (2015) — 1,402 citations
- code2seq: Generating Sequences from Structured Representations of Code (2018) — 812 citations
- Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling (2018) — 196 citations
- Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor (2022) — 487 citations
- The Turking Test: Can Language Models Understand Instructions? (2020) — 105 citations
- Deep RNNs Encode Soft Hierarchical Syntax (2018) — 118 citations