Xia Song
Artificial Intelligence · 2016–2023
A researcher in the Science corpus: 15 papers; trusts 420 researchers and is trusted by 28 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 464 citations into it; #19,968 of 35,345 by trust here, #3,400 by citations
- Natural Language Processing — 318 citations into it; #4,423 of 5,688 by trust here, #937 by citations
- Computer Vision and Pattern Recognition — 241 citations into it
- Large Language Models — 148 citations into it; #668 of 799 by trust here, #389 by citations
- Evaluation & Benchmarks — 118 citations into it; #848 of 3,147 by trust here, #213 by citations
- Representation & Self-Supervised Learning — 65 citations into it
- Model Architectures — 60 citations into it
- Optimization & Training — 23 citations into it
Whom Xia Song trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Yoshua Bengio
- Geoffrey E. Hinton
- Ilya Sutskever
- Kaiming He
- Alex Krizhevsky
- Yann LeCun
- Sepp Hochreiter
- Jacob Devlin
- Alex Graves
Who trusts Xia Song overall
- Sebastian Hofstätter
- Luyu Gao
- Jimmy J. Lin
- Zhuyun Dai
- Bhaskar Mitra
- Rodrigo Nogueira
- Omar Khattab
- Rajarshee Mitra
- Nick Craswell
- Jingtao Zhan
Papers from Xia Song's perspective
Ordered by how strongly the researchers Xia Song trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Attention is All you Need (Neural Information Processing Systems)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet classification with deep convolutional neural networks
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Gradient-based learning applied to document recognition
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Language Is Not All You Need: Aligning Perception with Language Models (2023) — 786 citations
- Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model (2022) — 859 citations
- COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining (2021) — 227 citations
- On the Representation Collapse of Sparse Mixture of Experts (2022) — 199 citations
- Knowledge-Aware Language Model Pretraining (2020) — 93 citations
- Foundation Transformers (2022) — 30 citations
- DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoders (2021) — 92 citations
- A Length-Extrapolatable Transformer (2022) — 176 citations
- Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators (2022) — 17 citations
- TorchScale: Transformers at Scale (2022) — 12 citations
- XLM-E: Cross-lingual Language Model Pre-training via ELECTRA (2021) — 139 citations
- InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training (2020) — 442 citations
- Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention (2020) — 125 citations
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset (2016) — 524 citations
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset (2016) — 3,491 citations