Colin Raffel
Artificial Intelligence · 2014–2025
A researcher in the Science corpus: 53 papers; trusts 3,070 researchers and is trusted by 4,998 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,866 citations into it; #352 of 36,961 by trust here, #86 by citations
- Computer Vision and Pattern Recognition — 810 citations into it; #897 of 21,973 by trust here, #146 by citations
- Natural Language Processing — 803 citations into it; #185 of 5,725 by trust here, #55 by citations
- Large Language Models — 379 citations into it; #21 of 810 by trust here, #33 by citations
- Evaluation & Benchmarks — 291 citations into it
- Model Architectures — 246 citations into it; #401 of 2,288 by trust here, #160 by citations
- Representation & Self-Supervised Learning — 225 citations into it; #356 of 3,156 by trust here, #332 by citations
- Optimization & Training — 193 citations into it; #1,192 of 2,605 by trust here, #437 by citations
Whom Colin Raffel trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Ilya Sutskever
- Alex Graves
- Geoffrey E. Hinton
- Diederik P. Kingma
- Alex Krizhevsky
- Kaiming He
- Yann LeCun
- Sepp Hochreiter
- Dzmitry Bahdanau
Who trusts Colin Raffel overall
- Yi Tay
- Mohit Bansal
- Timo Schick
- Quoc V. Le
- Daniel Khashabi
- Adam Roberts
- Percy Liang
- Mostafa Dehghani
- Jianfeng Gao
- Zhe Gan
Papers from Colin Raffel's perspective
Ordered by how strongly the researchers Colin Raffel 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)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (2019) — 26,606 citations
- Extracting Training Data from Large Language Models (2020) — 3,168 citations
- How Much Knowledge Can You Pack into the Parameters of a Language Model? (2020) — 1,084 citations
- Multitask Prompted Training Enables Zero-Shot Task Generalization (2021) — 2,030 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer (2020) — 3,278 citations
- Emergent Abilities of Large Language Models (2022) — 3,700 citations
- Theano: A Python framework for fast computation of mathematical expressions (2016) — 2,380 citations
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (2020) — 4,872 citations
- MixMatch: A Holistic Approach to Semi-Supervised Learning (2019) — 3,592 citations
- Lasagne: First release. (2015)
- BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (2022) — 2,975 citations
- ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models (2021) — 725 citations
- Scaling Up Models and Data with t5x and seqio (2022) — 224 citations
- What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization? (2022) — 236 citations
- Deduplicating Training Data Mitigates Privacy Risks in Language Models (2022) — 419 citations
- ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring (2019) — 796 citations
- Thermometer Encoding: One Hot Way To Resist Adversarial Examples (2018) — 647 citations
- Do Transformer Modifications Transfer Across Implementations and Applications? (2021) — 138 citations
- Improving and Simplifying Pattern Exploiting Training (2021) — 157 citations