Jason Phang
Artificial Intelligence · 2018–2024
A researcher in the Science corpus: 25 papers; trusts 1,155 researchers and is trusted by 408 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 955 citations into it; #1,687 of 36,961 by trust here, #799 by citations
- Natural Language Processing — 528 citations into it; #687 of 5,725 by trust here, #781 by citations
- Computer Vision and Pattern Recognition — 286 citations into it
- Evaluation & Benchmarks — 261 citations into it; #2,341 of 3,155 by trust here, #214 by citations
- Large Language Models — 234 citations into it; #518 of 810 by trust here, #111 by citations
- Representation & Self-Supervised Learning — 61 citations into it
- Prompting & Reasoning — 58 citations into it
- Model Architectures — 54 citations into it; #1,741 of 2,288 by trust here, #1,799 by citations
Whom Jason Phang trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Yoshua Bengio
- Geoffrey E. Hinton
- Ilya Sutskever
- Samuel R. Bowman
- Richard Socher
- Alex Krizhevsky
- Kaiming He
- Jacob Devlin
- Alexis Conneau
Who trusts Jason Phang overall
- Tu Vu
- Samuel R. Bowman
- Alex Warstadt
- Clara Vania
- Nikita Nangia
- Yada Pruksachatkun
- Colin Raffel
- Zhongyang Li
- Alex Wang
- Phu Mon Htut
Papers from Jason Phang's perspective
Ordered by how strongly the researchers Jason Phang trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet classification with deep convolutional neural networks
- Long Short-Term Memory
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- The Pile: An 800GB Dataset of Diverse Text for Language Modeling (2020) — 2,920 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks (2018) — 487 citations
- BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (2022) — 2,975 citations
- GPT-NeoX-20B: An Open-Source Autoregressive Language Model (2022) — 1,029 citations
- BBQ: A hand-built bias benchmark for question answering (2021) — 808 citations
- Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work? (2020) — 210 citations
- Pretraining Language Models with Human Preferences (2023) — 302 citations
- What Language Model to Train if You Have One Million GPU Hours? (2022) — 125 citations
- QuALITY: Question Answering with Long Input Texts, Yes! (2021) — 240 citations
- Investigating BERT’s Knowledge of Language: Five Analysis Methods with NPIs (2019) — 133 citations
- EleutherAI: Going Beyond "Open Science" to "Science in the Open" (2022) — 18 citations
- Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions (2022) — 21 citations
- English Intermediate-Task Training Improves Zero-Shot Cross-Lingual Transfer Too (2020) — 69 citations
- jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models (2020) — 97 citations
- Do Attention Heads in BERT Track Syntactic Dependencies? (2019) — 151 citations
- Comparing Test Sets with Item Response Theory (2021) — 64 citations
- What Do NLP Researchers Believe? Results of the NLP Community Metasurvey (2022) — 48 citations
- Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions (2022) — 17 citations
- Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair (2021) — 15 citations