Roy Schwartz
Artificial Intelligence · with Smith · 2017–2023
A researcher in the Science corpus: 22 papers; trusts 1,767 researchers and is trusted by 970 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 686 citations into it; #1,020 of 36,961 by trust here, #1,056 by citations
- Natural Language Processing — 359 citations into it; #413 of 5,725 by trust here, #337 by citations
- Computer Vision and Pattern Recognition — 264 citations into it; #4,210 of 21,973 by trust here, #2,593 by citations
- Evaluation & Benchmarks — 126 citations into it; #164 of 3,155 by trust here, #168 by citations
- Model Architectures — 92 citations into it; #1,876 of 2,288 by trust here, #1,214 by citations
- Large Language Models — 89 citations into it; #439 of 810 by trust here, #442 by citations
- Representation & Self-Supervised Learning — 65 citations into it; #2,751 of 3,156 by trust here, #1,127 by citations
- Safety, Robustness & Interpretability — 62 citations into it
Whom Roy Schwartz trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yoshua Bengio
- Sepp Hochreiter
- Alex Krizhevsky
- Yann LeCun
- Ilya Sutskever
- Kaiming He
- Alex Graves
- J. Urgen Schmidhuber
Who trusts Roy Schwartz overall
- Rowan Zellers
- Jesse Dodge
- Eric Wallace
- James Thorne
- Timo Schick
- Yejin Choi
- Ronan Le Bras
- Kawin Ethayarajh
- Mohit Bansal
- Noah A. Smith
Papers from Roy Schwartz's perspective
Ordered by how strongly the researchers Roy Schwartz 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
- Annotation Artifacts in Natural Language Inference Data (2018) — 1,309 citations
- SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference (2018) — 795 citations
- Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping (2020) — 739 citations
- Knowledge Enhanced Contextual Word Representations (2019) — 729 citations
- Random Feature Attention (2021) — 447 citations
- Show Your Work: Improved Reporting of Experimental Results (2019) — 310 citations
- Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics (2020) — 601 citations
- Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets (2019) — 113 citations
- The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task (2017) — 121 citations
- Story Cloze Task: UW NLP System (2017) — 48 citations
- The Right Tool for the Job: Matching Model and Instance Complexities (2020) — 197 citations
- Data Contamination: From Memorization to Exploitation (2022) — 279 citations
- Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias (2022) — 45 citations
- Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand? (2021) — 83 citations
- Data Efficient Masked Language Modeling for Vision and Language (2021) — 22 citations
- A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications (2018) — 282 citations
- LSTMs Exploit Linguistic Attributes of Data (2018) — 16 citations
- RNN Architecture Learning with Sparse Regularization (2019) — 13 citations
- Bridging CNNs, RNNs, and Weighted Finite-State Machines (2018) — 24 citations
- Green AI (2019) — 1,782 citations