Samira Abnar
Artificial Intelligence · 2019–2022
A researcher in the Science corpus: 7 papers; trusts 135 researchers and is trusted by 31 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 181 citations into it; #6,114 of 35,345 by trust here, #8,210 by citations
- Computer Vision and Pattern Recognition — 98 citations into it
- Natural Language Processing — 75 citations into it
- Model Architectures — 62 citations into it; #534 of 2,278 by trust here, #674 by citations
- Large Language Models — 43 citations into it
- Efficiency & Compression — 38 citations into it
- Evaluation & Benchmarks — 22 citations into it
- Representation & Self-Supervised Learning — 16 citations into it
Whom Samira Abnar trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Richard Socher
- Yoshua Bengio
- Ilya Sutskever
- Alex Krizhevsky
- Oriol Vinyals
- Yann LeCun
- Jimmy Ba
- Jacob Devlin
Who trusts Samira Abnar overall
- Hila Chefer
- Yi Tay
- Mostafa Dehghani
- Rohit Girdhar
- Sayak Paul
- Zizhao Zhang
- Shir Gur
- Alexander Pashevich
- Damian Pascual
- R. Thomas McCoy
Papers from Samira Abnar's perspective
Ordered by how strongly the researchers Samira Abnar 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
- Attention is All you Need (Neural Information Processing Systems)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- 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)
- 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
- Long Range Arena: A Benchmark for Efficient Transformers (2020) — 917 citations
- Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers (2021) — 152 citations
- Quantifying Attention Flow in Transformers (2020) — 1,293 citations
- Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? (2022) — 130 citations
- Transferring Inductive Biases through Knowledge Distillation (2020) — 72 citations
- Blackbox Meets Blackbox: Representational Similarity & Stability Analysis of Neural Language Models and Brains (2019) — 85 citations
- Scale Efficiently: Insights from Pretraining and Finetuning Transformers (2022) — 70 citations