Mostafa Dehghani
Artificial Intelligence · International Conference on Learning Representations · 2017–2024
A researcher in the Science corpus: 37 papers; trusts 2,806 researchers and is trusted by 3,305 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,654 citations into it; #1,142 of 36,961 by trust here, #272 by citations
- Computer Vision and Pattern Recognition — 973 citations into it; #914 of 21,973 by trust here, #245 by citations
- Natural Language Processing — 571 citations into it; #2,883 of 5,725 by trust here, #1,469 by citations
- Model Architectures — 339 citations into it; #265 of 2,288 by trust here, #59 by citations
- Evaluation & Benchmarks — 310 citations into it
- Large Language Models — 310 citations into it
- Efficiency & Compression — 195 citations into it; #912 of 1,273 by trust here, #735 by citations
- Representation & Self-Supervised Learning — 143 citations into it; #2,836 of 3,156 by trust here, #2,185 by citations
Whom Mostafa Dehghani trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Diederik P. Kingma
- Ilya Sutskever
- Kaiming He
- Yoshua Bengio
- Alex Graves
- Yann LeCun
- Jimmy Ba
- Ross B. Girshick
Who trusts Mostafa Dehghani overall
- Yi Tay
- Anurag Arnab
- Zhuyun Dai
- Sean MacAvaney
- Hamed Zamani
- Alexey A. Gritsenko
- Matthias Minderer
- Gaurav Menghani
- Arsha Nagrani
- Samira Abnar
Papers from Mostafa Dehghani's perspective
Ordered by how strongly the researchers Mostafa Dehghani 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)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (2020) — 66,490 citations
- ViViT: A Video Vision Transformer (2021) — 3,120 citations
- Scaling Instruction-Finetuned Language Models (2022) — 4,301 citations
- Universal Transformers (2018) — 980 citations
- PaLM 2 Technical Report (2023) — 1,524 citations
- Efficient Transformers: A Survey (2020) — 1,579 citations
- Scaling Vision Transformers to 22 Billion Parameters (2023) — 911 citations
- Simple Open-Vocabulary Object Detection with Vision Transformers (2022) — 421 citations
- Long Range Arena: A Benchmark for Efficient Transformers (2020) — 917 citations
- UL2: Unifying Language Learning Paradigms (2022) — 395 citations
- Transcending Scaling Laws with 0.1% Extra Compute (2022) — 78 citations
- SCENIC: A JAX Library for Computer Vision Research and Beyond (2021) — 78 citations
- Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers (2021) — 152 citations
- The Benchmark Lottery (2021) — 147 citations
- TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? (2021) — 181 citations
- PaLI-X: On Scaling up a Multilingual Vision and Language Model (2023) — 301 citations
- Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? (2022) — 130 citations
- The Efficiency Misnomer (2021) — 121 citations
- Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks (2021) — 382 citations
- Transferring Inductive Biases through Knowledge Distillation (2020) — 72 citations