Ashish Vaswani
Artificial Intelligence · 2013–2022
A researcher in the Science corpus: 23 papers; trusts 2,123 researchers and is trusted by 10,565 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 720 citations into it; #112 of 36,961 by trust here, #37 by citations
- Computer Vision and Pattern Recognition — 545 citations into it; #693 of 21,973 by trust here, #408 by citations
- Model Architectures — 248 citations into it; #25 of 2,288 by trust here, #9 by citations
- Natural Language Processing — 199 citations into it; #53 of 5,725 by trust here, #16 by citations
- Optimization & Training — 87 citations into it
- Generative Models — 78 citations into it; #1,029 of 1,963 by trust here, #251 by citations
- Efficiency & Compression — 70 citations into it; #346 of 1,273 by trust here, #172 by citations
- Representation & Self-Supervised Learning — 59 citations into it
Whom Ashish Vaswani trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Kaiming He
- Ilya Sutskever
- Alex Krizhevsky
- Diederik P. Kingma
- Alex Graves
- Jimmy Ba
- Ross B. Girshick
- Yann LeCun
Who trusts Ashish Vaswani overall
- Yoshua Bengio
- Yi Tay
- Xu Tan
- Mohit Bansal
- Jianfeng Gao
- Zhe Gan
- Quoc V. Le
- Percy Liang
- Kyunghyun Cho
- Ruslan Salakhutdinov
Papers from Ashish Vaswani's perspective
Ordered by how strongly the researchers Ashish Vaswani 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
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Attention is All you Need (2017) — 185,508 citations
- Image Transformer (2018) — 1,925 citations
- Self-Attention with Relative Position Representations (2018) — 2,875 citations
- Relational inductive biases, deep learning, and graph networks (2018) — 3,656 citations
- Stand-Alone Self-Attention in Vision Models (2019) — 1,375 citations
- Attention Augmented Convolutional Networks (2019) — 1,167 citations
- Tensor2Tensor for Neural Machine Translation (2018) — 553 citations
- Efficient Content-Based Sparse Attention with Routing Transformers (2020) — 773 citations
- Bottleneck Transformers for Visual Recognition (2021) — 1,200 citations
- One Model To Learn Them All (2017) — 350 citations
- Scaling Local Self-Attention for Parameter Efficient Visual Backbones (2021) — 476 citations
- Decoding with Large-Scale Neural Language Models Improves Translation (2013) — 276 citations
- Mesh-TensorFlow: Deep Learning for Supercomputers (2018) — 439 citations
- Music Transformer: Generating Music with Long-Term Structure (2018) — 598 citations
- Fast Decoding in Sequence Models using Discrete Latent Variables (2018) — 255 citations
- Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers (2021) — 152 citations
- The Efficiency Misnomer (2021) — 121 citations
- Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation (2019) — 231 citations
- Theory and Experiments on Vector Quantized Autoencoders (2018) — 100 citations
- Scale Efficiently: Insights from Pretraining and Finetuning Transformers (2022) — 70 citations