Dustin Tran
Artificial Intelligence · 2014–2023
A researcher in the Science corpus: 31 papers; trusts 1,862 researchers and is trusted by 2,544 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 955 citations into it; #724 of 36,961 by trust here, #1,126 by citations
- Computer Vision and Pattern Recognition — 393 citations into it; #1,320 of 21,973 by trust here, #961 by citations
- Probabilistic & Bayesian Methods — 392 citations into it; #90 of 1,526 by trust here, #69 by citations
- Statistics and Probability — 240 citations into it
- Generative Models — 146 citations into it; #387 of 1,963 by trust here, #249 by citations
- Optimization & Training — 135 citations into it; #2,464 of 2,605 by trust here, #1,588 by citations
- Evaluation & Benchmarks — 105 citations into it
- Model Architectures — 103 citations into it
Whom Dustin Tran trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Radford M. Neal
- Alex Krizhevsky
- Yoshua Bengio
- Rajesh Ranganath
- Danilo Jimenez Rezende
- David M. Blei
- Kaiming He
- Ilya Sutskever
Who trusts Dustin Tran overall
- Rajesh Ranganath
- Jiaxin Shi
- David M. Blei
- Diederik P. Kingma
- Qiang Liu
- Danijar Hafner
- Tianfu Wu
- Takeru Miyato
- Max Welling
- Jun Zhu
Papers from Dustin Tran's perspective
Ordered by how strongly the researchers Dustin Tran 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Image Transformer (2018) — 1,925 citations
- Scaling Vision Transformers to 22 Billion Parameters (2023) — 911 citations
- Hierarchical Variational Models (2015) — 365 citations
- The Variational Gaussian Process (2015) — 194 citations
- Mesh-TensorFlow: Deep Learning for Supercomputers (2018) — 439 citations
- Deep and Hierarchical Implicit Models (2017) — 101 citations
- Automatic Differentiation Variational Inference (2016) — 827 citations
- Discrete Flows: Invertible Generative Models of Discrete Data (2019) — 133 citations
- BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning (2020) — 586 citations
- Operator Variational Inference (2016) — 121 citations
- Edward: A library for probabilistic modeling, inference, and criticism (2016) — 306 citations
- Deep Probabilistic Programming (2017) — 203 citations
- Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches (2018) — 353 citations
- Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors (2018) — 77 citations
- Larger language models do in-context learning differently (2023) — 488 citations
- Analyzing the role of model uncertainty for electronic health records (2019) — 123 citations
- Hyperparameter Ensembles for Robustness and Uncertainty Quantification (2020) — 256 citations
- Measuring Calibration in Deep Learning (2019) — 692 citations
- Revisiting the Calibration of Modern Neural Networks (2021) — 562 citations
- Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors (2020) — 240 citations