Sang Michael Xie

Artificial Intelligence · 2015–2023

A researcher in the Science corpus: 14 papers; trusts 451 researchers and is trusted by 6 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 276 citations into it; #15,619 of 35,345 by trust here, #1,473 by citations
• Computer Vision and Pattern Recognition — 130 citations into it
• Natural Language Processing — 99 citations into it
• Large Language Models — 68 citations into it
• Safety, Robustness & Interpretability — 57 citations into it; #1,716 of 2,251 by trust here, #165 by citations
• Representation & Self-Supervised Learning — 47 citations into it
• Evaluation & Benchmarks — 45 citations into it
• Model Architectures — 22 citations into it

Whom Sang Michael Xie trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Geoffrey E. Hinton
2. Diederik P. Kingma
3. Alex Krizhevsky
4. Yoshua Bengio
5. Kaiming He
6. Ilya Sutskever
7. Ronald J. Williams
8. Yann LeCun
9. Jimmy Ba
10. Alex Graves

Who trusts Sang Michael Xie overall

1. Zhicheng Sun
2. Mengzhou Xia
3. Ananya Kumar
4. Tengyu Ma
5. Mei Wang
6. Hung-Yu Tseng
7. Percy Liang
8. Jean-Baptiste Cordonnier
9. Wenhu Chen
10. Eric Zelikman

Papers from Sang Michael Xie's perspective

Ordered by how strongly the researchers Sang Michael Xie trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Gradient-based learning applied to document recognition
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• On the Opportunities and Risks of Foundation Models (2021) — 6,923 citations
• Holistic Evaluation of Language Models (2023) — 1,863 citations
• An Explanation of In-context Learning as Implicit Bayesian Inference (2021) — 1,108 citations
• Adversarial Training Can Hurt Generalization (2019) — 257 citations
• Understanding and Mitigating the Tradeoff Between Robustness and Accuracy (2020) — 256 citations
• Data Selection for Language Models via Importance Resampling (2023) — 356 citations
• Reparameterizable Subset Sampling via Continuous Relaxations (2019) — 115 citations
• Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping (2015) — 458 citations
• DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining (2023) — 393 citations
• In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness (2020) — 68 citations
• Reward Design with Language Models (2023) — 323 citations
• Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning (2021) — 119 citations
• Combining satellite imagery and machine learning to predict poverty (2016) — 1,609 citations
• Semi-supervised deep kernel learning (2016)