William Fedus
Artificial Intelligence · 2009–2025
A researcher in the Science corpus: 27 papers; trusts 1,680 researchers and is trusted by 700 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 925 citations into it; #1,288 of 36,961 by trust here, #708 by citations
- Computer Vision and Pattern Recognition — 444 citations into it; #6,269 of 21,973 by trust here, #3,323 by citations
- Natural Language Processing — 225 citations into it; #1,809 of 5,725 by trust here, #1,702 by citations
- Model Architectures — 189 citations into it
- Large Language Models — 185 citations into it; #87 of 810 by trust here, #101 by citations
- Reinforcement Learning — 166 citations into it
- Evaluation & Benchmarks — 107 citations into it
- Efficiency & Compression — 96 citations into it; #136 of 1,273 by trust here, #194 by citations
Whom William Fedus trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Alex Krizhevsky
- Richard S. Sutton
- Yoshua Bengio
- Ilya Sutskever
- Kaiming He
- Yann LeCun
- Alex Graves
- Jimmy Ba
Who trusts William Fedus overall
- Yi Tay
- Barret Zoph
- Mostafa Dehghani
- Irwan Bello
- Timo Schick
- Sergey I. Nikolenko
- Yoshua Bengio
- Michael Lewis
- Joan Puigcerver
- James Lee-Thorp
Papers from William Fedus's perspective
Ordered by how strongly the researchers William Fedus 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)
- ImageNet Large Scale Visual Recognition Challenge
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity (2021) — 4,336 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- Scaling Instruction-Finetuned Language Models (2022) — 4,301 citations
- Emergent Abilities of Large Language Models (2022) — 3,700 citations
- Revisiting ResNets: Improved Training and Scaling Strategies (2021) — 365 citations
- MaskGAN: Better Text Generation via Filling in the ______ (2018) — 489 citations
- Recall Traces: Backtracking Models for Efficient Reinforcement Learning (2018) — 69 citations
- Do Transformer Modifications Transfer Across Implementations and Applications? (2021) — 138 citations
- Language GANs Falling Short (2018) — 240 citations
- Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers (2021) — 152 citations
- Designing Effective Sparse Expert Models (2022) — 118 citations
- Deep Graph Infomax (2018) — 3,051 citations
- Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? (2022) — 130 citations
- Hyperbolic Discounting and Learning over Multiple Horizons (2019) — 123 citations
- Disentangling the independently controllable factors of variation by interacting with the world (2018) — 69 citations
- A Review of Sparse Expert Models in Deep Learning (2022) — 209 citations
- ST-MoE: Designing Stable and Transferable Sparse Expert Models (2022) — 423 citations
- Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction (2019) — 32 citations
- Revisiting Fundamentals of Experience Replay (2020) — 318 citations
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step (2017) — 218 citations