Yuhuai Wu
Artificial Intelligence · with Li · 2016–2023
A researcher in the Science corpus: 28 papers; trusts 1,281 researchers and is trusted by 1,130 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 814 citations into it; #981 of 36,961 by trust here, #630 by citations
- Natural Language Processing — 237 citations into it; #3,031 of 5,725 by trust here, #1,096 by citations
- Computer Vision and Pattern Recognition — 220 citations into it; #3,684 of 21,973 by trust here, #5,975 by citations
- Reinforcement Learning — 166 citations into it; #1,059 of 2,250 by trust here, #323 by citations
- Large Language Models — 118 citations into it; #189 of 810 by trust here, #131 by citations
- Evaluation & Benchmarks — 105 citations into it; #882 of 3,155 by trust here, #591 by citations
- Model Architectures — 96 citations into it; #1,252 of 2,288 by trust here, #793 by citations
- Computational Theory and Mathematics — 94 citations into it; #4,515 of 12,489 by trust here, #750 by citations
Whom Yuhuai Wu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Yoshua Bengio
- Geoffrey E. Hinton
- Alex Graves
- Alex Krizhevsky
- Ilya Sutskever
- Radford M. Neal
- Yann LeCun
- James Martens
- Kaiming He
Who trusts Yuhuai Wu overall
- Arash Vahdat
- Yoshua Bengio
- Yilun Du
- Sergey Levine
- Aditya Grover
- Matthew D. Hoffman
- Ali Borji
- Guodong Zhang
- Quoc V. Le
- Zhangir Azerbayev
Papers from Yuhuai Wu's perspective
Ordered by how strongly the researchers Yuhuai Wu 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
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Learning Multiple Layers of Features from Tiny Images
Their papers
- On the Opportunities and Risks of Foundation Models (2021) — 6,923 citations
- Grandmaster level in StarCraft II using multi-agent reinforcement learning (2019) — 4,437 citations
- Solving Quantitative Reasoning Problems with Language Models (2022) — 1,845 citations
- PaLM 2 Technical Report (2023) — 1,524 citations
- STaR: Bootstrapping Reasoning With Reasoning (2022) — 981 citations
- On the Quantitative Analysis of Decoder-Based Generative Models (2016) — 226 citations
- On Multiplicative Integration with Recurrent Neural Networks (2016) — 165 citations
- Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (2017) — 674 citations
- Holistic Evaluation of Language Models (2023) — 1,863 citations
- Backpropagation through the Void: Optimizing control variates for black-box gradient estimation (2017) — 317 citations
- Understanding Short-Horizon Bias in Stochastic Meta-Optimization (2018) — 146 citations
- Some Considerations on Learning to Explore via Meta-Reinforcement Learning (2018) — 130 citations
- IsarStep: a Benchmark for High-level Mathematical Reasoning (2021) — 72 citations
- Language Model Cascades (2022) — 119 citations
- Memorizing Transformers (2022) — 249 citations
- Architectural Complexity Measures of Recurrent Neural Networks (2016) — 164 citations
- LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning (2021) — 69 citations
- Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference (2017) — 225 citations
- Proof Artifact Co-training for Theorem Proving with Language Models (2021) — 170 citations
- Autoformalization with Large Language Models (2022) — 324 citations