Wilker Aziz
Artificial Intelligence · 2012–2021
A researcher in the Science corpus: 12 papers; trusts 1,266 researchers and is trusted by 111 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 339 citations into it; #3,330 of 36,961 by trust here, #4,647 by citations
- Natural Language Processing — 186 citations into it; #1,930 of 5,725 by trust here, #2,143 by citations
- Computer Vision and Pattern Recognition — 124 citations into it; #5,588 of 21,973 by trust here, #4,441 by citations
- Model Architectures — 51 citations into it; #691 of 2,288 by trust here, #1,357 by citations
- Evaluation & Benchmarks — 37 citations into it
- Large Language Models — 32 citations into it; #260 of 810 by trust here, #543 by citations
- Safety, Robustness & Interpretability — 32 citations into it; #632 of 2,259 by trust here, #1,597 by citations
- Generative Models — 31 citations into it; #1,629 of 1,963 by trust here, #1,656 by citations
Whom Wilker Aziz trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yoshua Bengio
- Ilya Sutskever
- Yann LeCun
- Alex Krizhevsky
- L. Eon Bottou
- Jimmy Ba
- Ronald J. Williams
- Kaiming He
Who trusts Wilker Aziz overall
- Michael Sejr Schlichtkrull
- Nicola De Cao
- Kevin Meng
- Clara Meister
- Bodhisattwa Prasad Majumder
- Eric Mitchell
- Ana Marasovic
- Sewon Min
- Ivan Titov
- Linfeng Song
Papers from Wilker Aziz's perspective
Ordered by how strongly the researchers Wilker Aziz 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
- Gradient-based learning applied to document recognition
- 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)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Editing Factual Knowledge in Language Models (2021) — 715 citations
- Question Answering by Reasoning Across Documents with Graph Convolutional Networks (2018) — 245 citations
- Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation (2020) — 169 citations
- Graph Convolutional Encoders for Syntax-aware Neural Machine Translation (2017) — 519 citations
- Interpretable Neural Predictions with Differentiable Binary Variables (2019) — 236 citations
- PET: a Tool for Post-editing and Assessing Machine Translation (2012) — 163 citations
- Block Neural Autoregressive Flow (2019) — 142 citations
- Highly Parallel Autoregressive Entity Linking with Discriminative Correction (2021) — 41 citations
- How Do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking (2020) — 104 citations
- Moving the Eiffel Tower to ROME: Tracing and Editing Facts in GPT (2021)
- The Power Spherical distribution (2020) — 42 citations
- Cohere: A Toolkit for Local Coherence (2016) — 12 citations