Soumya Sanyal

Artificial Intelligence · 2019–2023

A researcher in the Science corpus: 6 papers; trusts 182 researchers and is trusted by 1 researcher here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 177 citations into it; #32,842 of 35,345 by trust here, #11,624 by citations
• Computer Vision and Pattern Recognition — 67 citations into it
• Graph Learning — 64 citations into it
• Natural Language Processing — 51 citations into it
• Molecular Biology — 31 citations into it
• Materials Chemistry — 23 citations into it
• Model Architectures — 20 citations into it
• Representation & Self-Supervised Learning — 18 citations into it

Whom Soumya Sanyal trusts overall

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

1. Diederik P. Kingma
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Alex Krizhevsky
5. Yann LeCun
6. Ilya Sutskever
7. Kaiming He
8. Jimmy Ba
9. Max Welling
10. Thomas Kipf

Who trusts Soumya Sanyal overall

1. Jing Zhang
2. Bowen Jing
3. Raphael J. L. Townshend
4. Apoorv Saxena
5. Lan Wei
6. Lyle Regenwetter
7. Ekagra Ranjan
8. Yingmin Wu
9. Zhaocheng Zhu
10. W. Yu

Papers from Soumya Sanyal's perspective

Ordered by how strongly the researchers Soumya Sanyal 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. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
10. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)

Their papers

• Generate rather than Retrieve: Large Language Models are Strong Context Generators (2022) — 431 citations
• Composition-based Multi-Relational Graph Convolutional Networks (2019) — 1,165 citations
• ProteinGCN: Protein model quality assessment using Graph Convolutional Networks (2020) — 49 citations
• Faith and Fate: Limits of Transformers on Compositionality (2023) — 650 citations
• InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions (2019) — 399 citations
• ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations (2019) — 414 citations