Yang Song
Computer Vision and Pattern Recognition · International Conference on Learning Representations · 2015–2023
A researcher in the Science corpus: 26 papers; trusts 2,790 researchers and is trusted by 6,037 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 651 citations into it; #553 of 21,973 by trust here, #600 by citations
- Artificial Intelligence — 570 citations into it; #608 of 36,961 by trust here, #1,077 by citations
- Generative Models — 457 citations into it; #34 of 1,963 by trust here, #58 by citations
- Probabilistic & Bayesian Methods — 243 citations into it; #84 of 1,526 by trust here, #104 by citations
- Statistical and Nonlinear Physics — 154 citations into it; #309 of 10,175 by trust here, #105 by citations
- Statistics and Probability — 125 citations into it; #11,771 of 13,188 by trust here, #8,488 by citations
- Signal Processing — 111 citations into it
- Safety, Robustness & Interpretability — 88 citations into it; #1,289 of 2,259 by trust here, #543 by citations
Whom Yang Song trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Diederik P. Kingma
- Geoffrey E. Hinton
- Pascal Vincent
- Radford M. Neal
- Kaiming He
- Aapo Hyvärinen
- Yoshua Bengio
- Ilya Sutskever
- Yann LeCun
Who trusts Yang Song overall
- Jonathan Ho
- Arash Vahdat
- Diederik P. Kingma
- Stefano Ermon
- Prafulla Dhariwal
- Hyungjin Chung
- Alex Nichol
- Chenlin Meng
- Jiaming Song
- Dongjun Kim
Papers from Yang Song's perspective
Ordered by how strongly the researchers Yang Song 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)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Generative Modeling by Estimating Gradients of the Data Distribution (2019) — 5,774 citations
- Score-Based Generative Modeling through Stochastic Differential Equations (2020) — 11,485 citations
- Improved Techniques for Training Score-Based Generative Models (2020) — 1,493 citations
- SDEdit: Image Synthesis and Editing with Stochastic Differential Equations (2021) — 348 citations
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations (2021) — 2,301 citations
- PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples (2017) — 846 citations
- Learning Energy-Based Models by Diffusion Recovery Likelihood (2020) — 150 citations
- Sliced Score Matching: A Scalable Approach to Density and Score Estimation (2019) — 535 citations
- Maximum Likelihood Training of Score-Based Diffusion Models (2021) — 923 citations
- How to Train Your Energy-Based Models (2021) — 343 citations
- MintNet: Building Invertible Neural Networks with Masked Convolutions (2019) — 75 citations
- Permutation Invariant Graph Generation via Score-Based Generative Modeling (2020) — 373 citations
- Constructing Unrestricted Adversarial Examples with Generative Models (2018) — 356 citations
- Efficient Graph Generation with Graph Recurrent Attention Networks (2019) — 410 citations
- Generative Adversarial Examples (2018) — 24 citations
- Training Deep Neural Networks via Direct Loss Minimization (2015) — 101 citations
- Training Deep Energy-Based Models with f-Divergence Minimization (2020) — 51 citations
- Improved Techniques for Training Consistency Models (2023) — 451 citations
- On Maximum Likelihood Training of Score-Based Generative Models (2021) — 13 citations
- Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving (2020) — 50 citations