Tao Lei
Artificial Intelligence · with Barzilay · 2012–2022
A researcher in the Science corpus: 14 papers; trusts 1,797 researchers and is trusted by 646 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 493 citations into it; #1,300 of 36,961 by trust here, #2,226 by citations
- Natural Language Processing — 261 citations into it; #477 of 5,725 by trust here, #598 by citations
- Computer Vision and Pattern Recognition — 193 citations into it; #19,855 of 21,973 by trust here, #13,584 by citations
- Model Architectures — 127 citations into it; #1,034 of 2,288 by trust here, #967 by citations
- Efficiency & Compression — 41 citations into it
- Optimization & Training — 35 citations into it; #2,244 of 2,605 by trust here, #1,807 by citations
- Large Language Models — 30 citations into it; #524 of 810 by trust here, #688 by citations
- Representation & Self-Supervised Learning — 30 citations into it
Whom Tao Lei trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yann LeCun
- Ilya Sutskever
- Yoon Kim
- Alex Krizhevsky
- Richard Socher
- Kyunghyun Cho
- Kaiming He
Who trusts Tao Lei overall
- Sarah Wiegreffe
- Tommi S. Jaakkola
- Regina Barzilay
- Wengong Jin
- Hongyu Guo
- Piyawat Lertvittayakumjorn
- David Alvarez-Melis
- Kristjan Arumae
- Percy Liang
- Shiyu Chang
Papers from Tao Lei's perspective
Ordered by how strongly the researchers Tao Lei 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- 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
- Rationalizing Neural Predictions (2016) — 880 citations
- Style Transfer from Non-Parallel Text by Cross-Alignment (2017) — 829 citations
- Deriving Neural Architectures from Sequence and Graph Kernels (2017) — 147 citations
- Semi-supervised Question Retrieval with Gated Convolutions (2015) — 112 citations
- Molding CNNs for text: non-linear, non-consecutive convolutions (2015) — 148 citations
- Training Language Models with Memory Augmentation (2022) — 153 citations
- Learning High-Level Planning from Text (2012) — 75 citations
- From Natural Language Specifications to Program Input Parsers (2013) — 48 citations
- Simple Recurrent Units for Highly Parallelizable Recurrence (2017) — 309 citations
- Training RNNs as Fast as CNNs (2017) — 179 citations
- Structured Pruning of Large Language Models (2019) — 354 citations
- Autoregressive Knowledge Distillation through Imitation Learning (2020) — 72 citations
- High-Order Low-Rank Tensors for Semantic Role Labeling (2015) — 50 citations
- Denoising Bodies to Titles: Retrieving Similar Questions with Recurrent Convolutional Models (2015) — 14 citations