Tie-Yan Liu
Artificial Intelligence · 2005–2023
A researcher in the Science corpus: 98 papers; trusts 3,859 researchers and is trusted by 1,804 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 2,616 citations into it; #760 of 36,961 by trust here, #375 by citations
- Computer Vision and Pattern Recognition — 1,109 citations into it; #2,120 of 21,973 by trust here, #857 by citations
- Natural Language Processing — 1,017 citations into it; #908 of 5,725 by trust here, #337 by citations
- Signal Processing — 469 citations into it; #405 of 7,592 by trust here, #129 by citations
- Model Architectures — 436 citations into it; #377 of 2,288 by trust here, #241 by citations
- Speech & Audio — 302 citations into it; #127 of 1,080 by trust here, #86 by citations
- Optimization & Training — 299 citations into it; #1,930 of 2,605 by trust here, #544 by citations
- Generative Models — 252 citations into it
Whom Tie-Yan Liu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Ilya Sutskever
- Kaiming He
- Yann LeCun
- Alex Graves
- Jimmy Ba
- Oriol Vinyals
Who trusts Tie-Yan Liu overall
- Olivier Chapelle
- Xu Tan
- Lidan Wang
- Tao Qin
- Hang Li
- Chenyan Xiong
- Bhaskar Mitra
- Thorsten Joachims
- Wayne Xin Zhao
- Jun Yu
Papers from Tie-Yan Liu's perspective
Ordered by how strongly the researchers Tie-Yan Liu 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)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
Their papers
- MASS: Masked Sequence to Sequence Pre-training for Language Generation (2019) — 1,025 citations
- Dual Learning for Machine Translation (2016) — 900 citations
- Neural Architecture Optimization (2018) — 720 citations
- Achieving Human Parity on Automatic Chinese to English News Translation (2018) — 645 citations
- Learning to rank: from pairwise approach to listwise approach (2007) — 2,421 citations
- Multilingual Neural Machine Translation with Knowledge Distillation (2019) — 267 citations
- Deliberation Networks: Sequence Generation Beyond One-Pass Decoding (2017) — 221 citations
- Learning Deep Representations for Graph Clustering (2014) — 684 citations
- Listwise approach to learning to rank: theory and algorithm (2008) — 920 citations
- LightGBM: A Highly Efficient Gradient Boosting Decision Tree (2017) — 15,550 citations
- RC-NET: A General Framework for Incorporating Knowledge into Word Representations (2014) — 205 citations
- Efficient Training of BERT by Progressively Stacking (2019) — 192 citations
- Incorporating BERT into Neural Machine Translation (2020)
- Knowledge-Powered Deep Learning for Word Embedding (2014) — 188 citations
- FRAGE: Frequency-Agnostic Word Representation (2018) — 147 citations
- Microsoft Research Asia’s Systems for WMT19 (2019) — 26 citations
- Dual Supervised Learning (2017) — 148 citations
- FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (2020) — 1,809 citations
- Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View (2019) — 234 citations
- Rethinking Positional Encoding in Language Pre-training (2020) — 366 citations