Ji Xin

Artificial Intelligence · 2020–2021

A researcher in the Science corpus: 3 papers; trusts 52 researchers and is trusted by 12 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 51 citations into it; #11,315 of 35,345 by trust here, #13,544 by citations
• Computer Vision and Pattern Recognition — 29 citations into it; #15,896 of 21,575 by trust here, #11,498 by citations
• Efficiency & Compression — 26 citations into it; #424 of 1,264 by trust here, #722 by citations
• Large Language Models — 20 citations into it; #639 of 799 by trust here, #770 by citations
• Natural Language Processing — 19 citations into it; #4,699 of 5,688 by trust here, #4,983 by citations
• Model Architectures — 16 citations into it
• Information Retrieval & Search — 8 citations into it

Whom Ji Xin trusts overall

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

1. Alex Graves
2. Geoffrey E. Hinton
3. Jacob Devlin
4. Yoshua Bengio
5. Surat Teerapittayanon
6. Diederik P. Kingma
7. Alex Krizhevsky
8. Ilya Sutskever
9. Kaiming He
10. Yann LeCun

Who trusts Ji Xin overall

1. Canwen Xu
2. Tal Schuster
3. Julian McAuley
4. Wangchunshu Zhou
5. Adam Fisch
6. Yoshitomo Matsubara
7. Young Jin Kim
8. Tao Ge
9. Xipeng Qiu
10. Xinyin Ma

Papers from Ji Xin's perspective

Ordered by how strongly the researchers Ji Xin 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. Attention is All you Need (Neural Information Processing Systems)
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
8. Gradient-based learning applied to document recognition
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)

Their papers

• DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference (2020) — 534 citations
• Early Exiting BERT for Efficient Document Ranking (2020) — 49 citations
• BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression (2021) — 165 citations