Hyung Won Chung

Artificial Intelligence · 2017–2023

A researcher in the Science corpus: 21 papers; trusts 342 researchers and is trusted by 19 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 1,018 citations into it; #9,611 of 35,345 by trust here, #515 by citations
• Natural Language Processing — 608 citations into it; #5,487 of 5,688 by trust here, #1,459 by citations
• Computer Vision and Pattern Recognition — 356 citations into it; #21,509 of 21,575 by trust here, #855 by citations
• Large Language Models — 346 citations into it; #769 of 799 by trust here, #77 by citations
• Evaluation & Benchmarks — 270 citations into it; #2,856 of 3,147 by trust here, #670 by citations
• Prompting & Reasoning — 121 citations into it; #334 of 359 by trust here, #122 by citations
• Model Architectures — 110 citations into it
• Efficiency & Compression — 94 citations into it

Whom Hyung Won Chung trusts overall

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

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

Who trusts Hyung Won Chung overall

1. Yi Tay
2. Ricardo Rei
3. Markus Freitag
4. Mostafa Dehghani
5. Sebastian Gehrmann
6. Tu Vu
7. Yizhong Wang
8. Jason Wei
9. Amy Pu
10. Ji Lin

Papers from Hyung Won Chung's perspective

Ordered by how strongly the researchers Hyung Won Chung trusts endorse each paper. Same corpus, a different order for every researcher.

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

Their papers

• PaLM: Scaling Language Modeling with Pathways (2022) — 8,214 citations
• Scaling Instruction-Finetuned Language Models (2022) — 4,301 citations
• Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them (2022) — 2,044 citations
• UL2: Unifying Language Learning Paradigms (2022) — 395 citations
• The Flan Collection: Designing Data and Methods for Effective Instruction Tuning (2023) — 953 citations
• What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization? (2022) — 236 citations
• Language Models are Multilingual Chain-of-Thought Reasoners (2022) — 634 citations
• Large language models encode clinical knowledge (2022) — 4,703 citations
• Do Transformer Modifications Transfer Across Implementations and Applications? (2021) — 138 citations
• Transcending Scaling Laws with 0.1% Extra Compute (2022) — 78 citations
• Charformer: Fast Character Transformers via Gradient-based Subword Tokenization (2021) — 213 citations
• Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers (2021) — 152 citations
• Neural Data Augmentation via Example Extrapolation (2021) — 75 citations
• Learning Compact Metrics for MT (2021) — 119 citations
• Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? (2022) — 130 citations
• Rethinking embedding coupling in pre-trained language models (2020) — 187 citations
• Learning to Evaluate Translation Beyond English: BLEURT Submissions to the WMT Metrics 2020 Shared Task (2020) — 41 citations
• Scale Efficiently: Insights from Pretraining and Finetuning Transformers (2022) — 70 citations
• Scaling Up Models and Data with t5x and seqio (2022) — 224 citations
• BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (2022) — 2,975 citations