Shi Feng
Artificial Intelligence · with Wallace · 2018–2021
A researcher in the Science corpus: 12 papers; trusts 996 researchers and is trusted by 135 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 383 citations into it; #2,874 of 36,961 by trust here, #2,450 by citations
- Natural Language Processing — 221 citations into it; #1,901 of 5,725 by trust here, #1,054 by citations
- Computer Vision and Pattern Recognition — 130 citations into it; #18,506 of 21,973 by trust here, #12,026 by citations
- Safety, Robustness & Interpretability — 129 citations into it; #660 of 2,259 by trust here, #274 by citations
- Evaluation & Benchmarks — 71 citations into it; #2,780 of 3,155 by trust here, #2,448 by citations
- Large Language Models — 47 citations into it; #252 of 810 by trust here, #397 by citations
- Signal Processing — 30 citations into it
- Model Architectures — 26 citations into it
Whom Shi Feng trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yoshua Bengio
- Alex Graves
- Richard Socher
- Alex Krizhevsky
- Ilya Sutskever
- Yann LeCun
- Kaiming He
- J. Urgen Schmidhuber
Who trusts Shi Feng overall
- Eric Wallace
- Matt Gardner
- Alon Jacovi
- Jordan L. Boyd-Graber
- Jonathan Berant
- Yoav Goldberg
- Sameer Singh
- Emily Sheng
- Nicola De Cao
- Michael Sejr Schlichtkrull
Papers from Shi Feng's perspective
Ordered by how strongly the researchers Shi Feng 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)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Calibrate Before Use: Improving Few-Shot Performance of Language Models (2021) — 1,964 citations
- Universal Adversarial Triggers for Attacking and Analyzing NLP (2019) — 1,099 citations
- Pathologies of Neural Models Make Interpretations Difficult (2018) — 343 citations
- Trick Me If You Can: Human-in-the-Loop Generation of Adversarial Examples for Question Answering (2018) — 169 citations
- Concealed Data Poisoning Attacks on NLP Models (2021) — 234 citations
- ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation (2021) — 88 citations
- Universal Adversarial Triggers for NLP (2019) — 30 citations
- Misleading Failures of Partial-input Baselines (2019) — 41 citations
- Interpreting Neural Networks with Nearest Neighbors (2018) — 57 citations
- Customizing Triggers with Concealed Data Poisoning (2020) — 20 citations
- Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation (2019) — 63 citations
- Trick Me If You Can: Human-in-the-loop Generation of Adversarial Question Answering Examples (2019) — 28 citations