OOIR: Observatory of International Research

Papers

(The H4-Index of Nature Machine Intelligence is 70. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2020-11-01 to 2024-11-01.)

Article	Citations
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators	884
Shortcut learning in deep neural networks	697
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans	667
An open source machine learning framework for efficient and transparent systematic reviews	336
Machine learning pipeline for battery state-of-health estimation	301
Deep learning for tomographic image reconstruction	301
Molecular contrastive learning of representations via graph neural networks	294
AI for radiographic COVID-19 detection selects shortcuts over signal	271
Geometry-enhanced molecular representation learning for property prediction	212
Inverse design of nanoporous crystalline reticular materials with deep generative models	202
Expanding functional protein sequence spaces using generative adversarial networks	202
End-to-end privacy preserving deep learning on multi-institutional medical imaging	201
Development of metaverse for intelligent healthcare	185
Advances, challenges and opportunities in creating data for trustworthy AI	163
scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data	156
Improved protein structure prediction by deep learning irrespective of co-evolution information	154
Mapping the space of chemical reactions using attention-based neural networks	147
Geometric deep learning on molecular representations	144
Concept whitening for interpretable image recognition	143
Deep learning-based prediction of the T cell receptor–antigen binding specificity	141
Three types of incremental learning	140
Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion	132
Parameter-efficient fine-tuning of large-scale pre-trained language models	128
Dual use of artificial-intelligence-powered drug discovery	124
AI-generated characters for supporting personalized learning and well-being	118

A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing	118
Machine learning and computation-enabled intelligent sensor design	116
A soft robot that adapts to environments through shape change	114
Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms	114
Towards neural Earth system modelling by integrating artificial intelligence in Earth system science	113
Code-free deep learning for multi-modality medical image classification	113
Estimation of continuous valence and arousal levels from faces in naturalistic conditions	113
Bioinspired acousto-magnetic microswarm robots with upstream motility	112
The transformational role of GPU computing and deep learning in drug discovery	112
Predicting ultrafast nonlinear dynamics in fibre optics with a recurrent neural network	109
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors	109
Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks	108
Prediction of water stability of metal–organic frameworks using machine learning	107
Automating turbulence modelling by multi-agent reinforcement learning	106
A soft thumb-sized vision-based sensor with accurate all-round force perception	105
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning	104
Stable learning establishes some common ground between causal inference and machine learning	102
Machine learning and algorithmic fairness in public and population health	102
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling	100
Learning functional properties of proteins with language models	100
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning	99
Controllable protein design with language models	98
Large-scale chemical language representations capture molecular structure and properties	97
Large pre-trained language models contain human-like biases of what is right and wrong to do	97
Human–AI collaboration enables more empathic conversations in text-based peer-to-peer mental health support	95
Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning	94
Biological underpinnings for lifelong learning machines	94
A definition, benchmark and database of AI for social good initiatives	92
Encoding of tactile information in hand via skin-integrated wireless haptic interface	88
A versatile deep learning architecture for classification and label-free prediction of hyperspectral images	87
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin	87
A geometric deep learning approach to predict binding conformations of bioactive molecules	86
Out-of-the-box deep learning prediction of pharmaceutical properties by broadly learned knowledge-based molecular representations	84
Improving performance of deep learning models with axiomatic attribution priors and expected gradients	84
Morphological and molecular breast cancer profiling through explainable machine learning	83
Governing AI safety through independent audits	81
Combinatorial optimization with physics-inspired graph neural networks	81
A transformer-based model to predict peptide–HLA class I binding and optimize mutated peptides for vaccine design	79
Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework	79
A case-based interpretable deep learning model for classification of mass lesions in digital mammography	77
Benchmarking saliency methods for chest X-ray interpretation	76
Predictive control of aerial swarms in cluttered environments	76
Teaching recurrent neural networks to infer global temporal structure from local examples	75
Molecular convolutional neural networks with DNA regulatory circuits	71
Deep neural networks identify sequence context features predictive of transcription factor binding	71
Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes	70