Minkai Xu

Artificial Intelligence · 2020–2022

A researcher in the Science corpus: 7 papers; trusts 348 researchers and is trusted by 21 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 98 citations into it
• Computer Vision and Pattern Recognition — 91 citations into it
• Generative Models — 87 citations into it; #826 of 1,956 by trust here, #859 by citations
• Materials Chemistry — 67 citations into it; #1,252 of 11,513 by trust here, #4,767 by citations
• Probabilistic & Bayesian Methods — 59 citations into it
• Computational Theory and Mathematics — 55 citations into it; #4,651 of 12,182 by trust here, #1,319 by citations
• Molecular Biology — 46 citations into it; #2,219 of 17,773 by trust here, #5,320 by citations
• Graph Learning — 33 citations into it

Whom Minkai Xu trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Diederik P. Kingma
2. Yoshua Bengio
3. Geoffrey E. Hinton
4. Alex Krizhevsky
5. Yann LeCun
6. Max Welling
7. Yang Song
8. Kaiming He
9. Radford M. Neal
10. Ilya Sutskever

Who trusts Minkai Xu overall

1. Shitong Luo
2. Tian Xie
3. Chence Shi
4. Yuyang Wang
5. Octavian-Eugen Ganea
6. Bowen Jing
7. Regina Barzilay
8. Yuanqi Du
9. Gabriele Corso
10. Emiel Hoogeboom

Papers from Minkai Xu's perspective

Ordered by how strongly the researchers Minkai Xu trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. GENERATIVE ADVERSARIAL NETS
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator (2020) — 8 citations
• GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (2022) — 734 citations
• Learning Gradient Fields for Molecular Conformation Generation (2021) — 261 citations
• GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation (2020) — 553 citations
• Learning Neural Generative Dynamics for Molecular Conformation Generation (2021) — 138 citations
• Predicting Molecular Conformation via Dynamic Graph Score Matching (2021) — 120 citations
• Energy-Based Imitation Learning (2020) — 55 citations