Octavian-Eugen Ganea
Artificial Intelligence · 2017–2022
A researcher in the Science corpus: 10 papers; trusts 463 researchers and is trusted by 69 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 125 citations into it; #4,281 of 36,961 by trust here, #9,549 by citations
- Molecular Biology — 118 citations into it; #7,933 of 17,836 by trust here, #9,423 by citations
- Computational Theory and Mathematics — 101 citations into it; #5,203 of 12,489 by trust here, #2,583 by citations
- Materials Chemistry — 94 citations into it; #9,009 of 11,531 by trust here, #8,534 by citations
- Natural Language Processing — 57 citations into it; #1,176 of 5,725 by trust here, #2,487 by citations
- Computer Vision and Pattern Recognition — 38 citations into it; #7,908 of 21,973 by trust here, #19,167 by citations
- Graph Learning — 34 citations into it; #695 of 700 by trust here, #520 by citations
- Representation & Self-Supervised Learning — 34 citations into it
Whom Octavian-Eugen Ganea trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Silvere Bonnabel
- Yoshua Bengio
- Maximilian Nickel
- Jimmy Ba
- Max Welling
- Ilya Sutskever
- Alex Krizhevsky
- Yann LeCun
Who trusts Octavian-Eugen Ganea overall
- Gary Bécigneul
- Phong Le
- A. Tifrea
- Ines Chami
- Nicola De Cao
- Ivana Balazevic
- Ledell Yu Wu
- Ivan Titov
- Yasumasa Onoe
- Pedro Henrique Martins
Papers from Octavian-Eugen Ganea's perspective
Ordered by how strongly the researchers Octavian-Eugen Ganea 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
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- Deep Joint Entity Disambiguation with Local Neural Attention (2017) — 358 citations
- End-to-End Neural Entity Linking (2018) — 288 citations
- Riemannian Adaptive Optimization Methods (2018) — 355 citations
- Hyperbolic Neural Networks (2018) — 842 citations
- Poincaré GloVe: Hyperbolic Word Embeddings (2018) — 343 citations
- GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles (2021) — 176 citations
- EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction (2022) — 380 citations
- Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking (2021) — 174 citations
- Crystal Diffusion Variational Autoencoder for Periodic Material Generation (2021) — 444 citations
- Hyperbolic Entailment Cones for Learning Hierarchical Embeddings (2018) — 360 citations