Tom Sercu

Molecular Biology · 2016–2025

A researcher in the Science corpus: 16 papers; trusts 745 researchers and is trusted by 41 researchers here, as inferred from the citation graph.

Subfields

• Molecular Biology — 291 citations into it; #13,658 of 17,773 by trust here, #4,050 by citations
• Computational Biology & Bioinformatics — 181 citations into it; #529 of 660 by trust here, #315 by citations
• Artificial Intelligence — 158 citations into it; #4,954 of 35,345 by trust here, #6,517 by citations
• Computer Vision and Pattern Recognition — 113 citations into it; #4,819 of 21,575 by trust here, #8,502 by citations
• Generative Models — 69 citations into it; #423 of 1,956 by trust here, #961 by citations
• Materials Chemistry — 69 citations into it
• Model Architectures — 51 citations into it
• Signal Processing — 50 citations into it; #2,682 of 7,572 by trust here, #5,086 by citations

Whom Tom Sercu trusts overall

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

1. Yann LeCun
2. Geoffrey E. Hinton
3. Alex Krizhevsky
4. Yoshua Bengio
5. Karen Simonyan
6. Diederik P. Kingma
7. Ilya Sutskever
8. Kaiming He
9. Christian Szegedy
10. Sergey Ioffe

Who trusts Tom Sercu overall

1. Dong Yu
2. Yongjun Hong
3. Jinyu Li
4. Yanmin Qian
5. Hairong Liu
6. Uiwon Hwang
7. Shi-Xiong Zhang
8. George Saon
9. Youssef Mroueh
10. Alexia Jolicoeur-Martineau

Papers from Tom Sercu's perspective

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

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

Their papers

• Fisher GAN (2017) — 134 citations
• McGan: Mean and Covariance Feature Matching GAN (2017) — 166 citations
• English Conversational Telephone Speech Recognition by Humans and Machines (2017) — 374 citations
• Dense Prediction on Sequences with Time-Dilated Convolutions for Speech Recognition (2016) — 60 citations
• Knowledge distillation across ensembles of multilingual models for low-resource languages (2017) — 61 citations
• MSA Transformer (2021) — 735 citations
• Learning inverse folding from millions of predicted structures (2022) — 618 citations
• Evolutionary-scale prediction of atomic level protein structure with a language model (2022) — 5,058 citations
• Language models enable zero-shot prediction of the effects of mutations on protein function (2021) — 898 citations
• Transformer protein language models are unsupervised structure learners (2020) — 394 citations
• Simulating 500 million years of evolution with a language model. (2025) — 309 citations
• Simulating 500 million years of evolution with a language model (2024) — 677 citations
• Accelerated antimicrobial discovery via deep generative models and molecular dynamics simulations (2021) — 398 citations
• Wasserstein Barycenter Model Ensembling (2019) — 27 citations
• PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences (2018) — 69 citations
• Advances in Very Deep Convolutional Neural Networks for LVCSR (2016) — 44 citations