Zhiyuan Li
Artificial Intelligence · International Conference on Learning Representations · 2018–2024
A researcher in the Science corpus: 13 papers; trusts 1,044 researchers and is trusted by 102 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 366 citations into it; #3,693 of 36,961 by trust here, #3,605 by citations
- Computer Vision and Pattern Recognition — 184 citations into it; #3,861 of 21,973 by trust here, #2,499 by citations
- Optimization & Training — 156 citations into it; #1,243 of 2,605 by trust here, #1,351 by citations
- Scaling & Learning Theory — 90 citations into it; #74 of 429 by trust here, #65 by citations
- Model Architectures — 57 citations into it
- Statistical Learning Theory — 51 citations into it; #968 of 1,040 by trust here, #293 by citations
- Computational Mechanics — 34 citations into it
- Large Language Models — 29 citations into it; #357 of 810 by trust here, #477 by citations
Whom Zhiyuan Li trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yoshua Bengio
- Ilya Sutskever
- Sergey Ioffe
- Jimmy Ba
- Yann LeCun
- X. Zhang
Who trusts Zhiyuan Li overall
- Yuanzhi Li
- Zeyuan Allen-Zhu
- Bin Shi
- Byeonghwi Kim
- Seyed Iman Mirzadeh
- Simon Shaolei Du
- Mustafa Burak Gurbuz
- Greg Yang
- Amnon Geifman
- Colin Wei
Papers from Zhiyuan Li's perspective
Ordered by how strongly the researchers Zhiyuan Li 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)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks (2019) — 1,081 citations
- Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks (2018) — 403 citations
- On Exact Computation with an Infinitely Wide Neural Net (2019) — 1,059 citations
- An Exponential Learning Rate Schedule for Deep Learning (2019) — 272 citations
- Theoretical Analysis of Auto Rate-Tuning by Batch Normalization (2018) — 146 citations
- Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee (2019) — 143 citations
- Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks (2019) — 171 citations
- Enhanced Convolutional Neural Tangent Kernels (2019) — 138 citations
- Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training (2023) — 300 citations
- Chain of Thought Empowers Transformers to Solve Inherently Serial Problems (2024) — 299 citations
- Continual Learning with Laplace Operator Based Node-Importance Dynamic Architecture Neural Network (2021) — 3 citations
- DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection (2021) — 314 citations
- Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets (2019) — 106 citations