Aurko Roy
Artificial Intelligence · 2016–2023
A researcher in the Science corpus: 10 papers; trusts 774 researchers and is trusted by 811 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 356 citations into it; #2,108 of 36,961 by trust here, #1,887 by citations
- Computer Vision and Pattern Recognition — 157 citations into it; #2,149 of 21,973 by trust here, #1,953 by citations
- Natural Language Processing — 133 citations into it; #5,682 of 5,725 by trust here, #2,305 by citations
- Safety, Robustness & Interpretability — 73 citations into it; #702 of 2,259 by trust here, #334 by citations
- Evaluation & Benchmarks — 57 citations into it
- Model Architectures — 50 citations into it; #1,197 of 2,288 by trust here, #789 by citations
- Generative Models — 39 citations into it
- Large Language Models — 36 citations into it
Whom Aurko Roy trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Diederik P. Kingma
- Ilya Sutskever
- Dimitri P. Bertsekas
- Alex Graves
- Ronald J. Williams
- Alex Krizhevsky
- Jimmy Ba
- Richard S. Sutton
Who trusts Aurko Roy overall
- Kalpesh Krishna
- Wei Ping
- Yi Tay
- Markus Norman Rabe
- Ting-Li Chen
- Tri Dao
- Alex Nichol
- Yoshua Bengio
- Diederik P. Kingma
- Ali Hassani
Papers from Aurko Roy's perspective
Ordered by how strongly the researchers Aurko Roy trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- 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
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
Their papers
- Efficient Content-Based Sparse Attention with Routing Transformers (2020) — 773 citations
- PaLM 2 Technical Report (2023) — 1,524 citations
- Learning to Remember Rare Events (2017) — 388 citations
- Thermometer Encoding: One Hot Way To Resist Adversarial Examples (2018) — 647 citations
- Fast Decoding in Sequence Models using Discrete Latent Variables (2018) — 255 citations
- Adversarial Patch (2017) — 1,317 citations
- Hurdles to Progress in Long-form Question Answering (2021) — 237 citations
- Technical Report on the CleverHans v2.1.0 Adversarial Examples Library (2016) — 544 citations
- Theory and Experiments on Vector Quantized Autoencoders (2018) — 100 citations
- Reinforcement Learning under Model Mismatch (2017) — 94 citations