Zihang Dai
Artificial Intelligence · 2017–2022
A researcher in the Science corpus: 22 papers; trusts 2,590 researchers and is trusted by 3,512 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 914 citations into it; #482 of 36,961 by trust here, #338 by citations
- Computer Vision and Pattern Recognition — 657 citations into it; #1,296 of 21,973 by trust here, #958 by citations
- Natural Language Processing — 262 citations into it; #478 of 5,725 by trust here, #190 by citations
- Model Architectures — 261 citations into it; #262 of 2,288 by trust here, #151 by citations
- Representation & Self-Supervised Learning — 225 citations into it; #1,082 of 3,156 by trust here, #747 by citations
- Optimization & Training — 119 citations into it
- Large Language Models — 104 citations into it; #42 of 810 by trust here, #69 by citations
- Multimodal Learning — 83 citations into it; #794 of 1,215 by trust here, #457 by citations
Whom Zihang Dai trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Alex Krizhevsky
- Diederik P. Kingma
- Kaiming He
- Alex Graves
- Ilya Sutskever
- Yann LeCun
- Tomas Mikolov
- Ross B. Girshick
Who trusts Zihang Dai overall
- Yi Tay
- Quoc V. Le
- Mohit Bansal
- Yoshua Bengio
- Yonatan Belinkov
- Jianfeng Gao
- Zhe Gan
- Percy Liang
- Dacheng Tao
- Ruslan Salakhutdinov
Papers from Zihang Dai's perspective
Ordered by how strongly the researchers Zihang Dai 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
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- XLNet: Generalized Autoregressive Pretraining for Language Understanding (2019) — 9,461 citations
- Transformer-XL: Attentive Language Models beyond a Fixed-Length Context (2019) — 4,418 citations
- SimVLM: Simple Visual Language Model Pretraining with Weak Supervision (2021) — 965 citations
- Breaking the Softmax Bottleneck: A High-Rank RNN Language Model (2017) — 428 citations
- Unsupervised Data Augmentation for Consistency Training (2019) — 2,706 citations
- Unsupervised Data Augmentation (2019) — 219 citations
- CoAtNet: Marrying Convolution and Attention for All Data Sizes (2021) — 1,668 citations
- Good Semi-supervised Learning That Requires a Bad GAN (2017) — 507 citations
- Meta Pseudo Labels (2020) — 774 citations
- Combined Scaling for Zero-shot Transfer Learning (2021) — 248 citations
- Primer: Searching for Efficient Transformers for Language Modeling (2021) — 224 citations
- Transformer-XL: Language Modeling with Longer-Term Dependency (2018) — 73 citations
- Calibrating Energy-based Generative Adversarial Networks (2017) — 111 citations
- Wiki-40B: Multilingual Language Model Dataset (2020) — 139 citations
- Pay Attention to MLPs (2021) — 883 citations
- SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation (2018) — 210 citations
- Combiner: Full Attention Transformer with Sparse Computation Cost (2021) — 99 citations
- Characterizing and Avoiding Negative Transfer (2018) — 510 citations
- Controllable Invariance through Adversarial Feature Learning (2017) — 312 citations
- Combined Scaling for Open-Vocabulary Image Classification (2022)