OOIR: Observatory of International Research

Papers

(The H4-Index of Nature Machine Intelligence is 71. 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 2021-04-01 to 2025-04-01.)

Article	Citations
Visual cognition in multimodal large language models	413
AI on the beach	373
A unified deep framework for peptide–major histocompatibility complex–T cell receptor binding prediction	319
On board with COMET to improve omics prediction models	310
Physical benchmarks for testing algorithms	292
Investigating machine moral judgement through the Delphi experiment	279
Calibrated geometric deep learning improves kinase–drug binding predictions	259
Asymmetric predictive relationships across histone modifications	258
Influencing human–AI interaction by priming beliefs about AI can increase perceived trustworthiness, empathy and effectiveness	257
Systematic analysis of 32,111 AI model cards characterizes documentation practice in AI	255
Machine learning for practical quantum error mitigation	222
Incorporating physics into data-driven computer vision	192
A multi-modal deep language model for contaminant removal from metagenome-assembled genomes	179
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	170
Large language models that replace human participants can harmfully misportray and flatten identity groups	169
Explainable AI reveals Clever Hans effects in unsupervised learning models	168
Safe driving cars	164
A challenge for the law and artificial intelligence	162
A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit	159
A year of racing ahead with AI and not breaking things	159
A cautionary tale about the adoption of medical AI in Sweden	148
Meta-learning for T cell receptor binding specificity and beyond	147
Connecting molecular properties with plain language	143
Publisher Correction: Dimensionality reduction to maximize prediction generalization capability	141
Improving customer decisions in web-based e-commerce through guerrilla modding	140

Learning equilibria in symmetric auction games using artificial neural networks	140
A new regulatory framework for algorithm-powered recommendation services in China	139
Mitigating allocative tradeoffs and harms in an environmental justice data tool	139
AI model transferability in healthcare: a sociotechnical perspective	135
Author Correction: Automatic strain sensor design via active learning and data augmentation for soft machines	133
Listening in to perceived speech with contrastive learning	130
A generalizable deep learning framework for inferring fine-scale germline mutation rate maps	130
Adversarial competition and collusion in algorithmic markets	129
The democratization of global AI governance and the role of tech companies	128
Artificial intelligence tackles the nature–nurture debate	126
Data-driven discovery of movement-linked heterogeneity in neurodegenerative diseases	123
High-resolution real-space reconstruction of cryo-EM structures using a neural field network	121
Reusability report: Uncovering associations in biomedical bipartite networks via a bilinear attention network with domain adaptation	121
Deep learning models for predicting RNA degradation via dual crowdsourcing	118
Deep learning for predicting rate-induced tipping	115
AtomAI framework for deep learning analysis of image and spectroscopy data in electron and scanning probe microscopy	115
Reply to: Limitations in odour recognition and generalization in a neuromorphic olfactory circuit	113
Many-body control with reinforcement learning and tensor networks	109
Playing with symmetry with neural networks	107
When and how convolutional neural networks generalize to out-of-distribution category–viewpoint combinations	106
Author Correction: Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	103
Interpretable meta-score for model performance	100
Publisher Correction: Back to the future with machine learning	100
Resource-efficient inference for particle physics	97
Deep reinforcement learning-designed radiofrequency waveform in MRI	96
Dynamic particle swarm optimization of biomolecular simulation parameters with flexible objective functions	91
Epistemic fragmentation poses a threat to the governance of online targeting	91
Wiring up recurrent neural networks	91
A teachable moment for dual-use	86
Author Correction: A 5′ UTR language model for decoding untranslated regions of mRNA and function predictions	85
Pre-training with fractional denoising to enhance molecular property prediction	83
Supervised learning of high-confidence phenotypic subpopulations from single-cell data	82
Author Correction: Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock	82
Scalable and robust DNA-based storage via coding theory and deep learning	81
Cognitive maps from predictive vision	80
A comprehensive large-scale biomedical knowledge graph for AI-powered data-driven biomedical research	79
Physically constrained generative adversarial networks for improving precipitation fields from Earth system models	78
Towards highly sensitive deep learning-based end-to-end database search for tandem mass spectrometry	78
Ethical hazards of health data governance in the metaverse	78
New deepfake regulations in China are a tool for social stability, but at what cost?	77
Pick your AI poison	77
Improving Wikipedia verifiability with AI	74
AI reflections in 2021	74
Invalid SMILES are beneficial rather than detrimental to chemical language models	73
Wing-strain-based flight control of flapping-wing drones through reinforcement learning	72
Encoding of tactile information in hand via skin-integrated wireless haptic interface	71