OOIR: Observatory of International Research

Papers

(The H4-Index of Nature Machine Intelligence is 76. 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 2021-11-01 to 2025-11-01.)

Article	Citations
Author Correction: A 5′ UTR language model for decoding untranslated regions of mRNA and function predictions	586
Author Correction: Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	564
Physical benchmarks for testing algorithms	459
Materiality and risk in the age of pervasive AI sensors	436
A challenge for the law and artificial intelligence	408
A multi-modal deep language model for contaminant removal from metagenome-assembled genomes	401
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	373
Human autonomy in the age of artificial intelligence	337
Wing-strain-based flight control of flapping-wing drones through reinforcement learning	284
Author Correction: Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock	268
Artificial intelligence tackles the nature–nurture debate	258
Physically constrained generative adversarial networks for improving precipitation fields from Earth system models	257
Investigating machine moral judgement through the Delphi experiment	254
A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit	237
Discussions of machine versus living intelligence need more clarity	224
Tailored structured peptide design with a key-cutting machine approach	216
Towards reproducible robotics research	214
A soft-packaged and portable rehabilitation glove capable of closed-loop fine motor skills	208
A question of trust for AI research in medicine	190
A Global South perspective for ethical algorithms and the State	187
Fast and generalizable micromagnetic simulation with deep neural nets	185
Reusability report: Deep learning-based analysis of images and spectroscopy data with AtomAI	184
Quantum circuit optimization with AlphaTensor	181
Advancing ethics review practices in AI research	181
Direct conformational sampling from peptide energy landscapes through hypernetwork-conditioned diffusion	175

Are neural network representations universal or idiosyncratic?	169
Transformer-based protein generation with regularized latent space optimization	166
Out-of-distribution generalization from labelled and unlabelled gene expression data for drug response prediction	157
Robust virtual staining of landmark organelles with Cytoland	156
The curious case of the test set AUROC	147
Bringing artificial intelligence to business management	145
AI pioneers win 2024 Nobel prizes	143
Zero-shot transfer of protein sequence likelihood models to thermostability prediction	139
Deep neural networks with controlled variable selection for the identification of putative causal genetic variants	129
Recurrent graph optimal transport for learning 3D flow motion in particle tracking	126
Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene	125
Maximum diffusion reinforcement learning	122
Reshaping the discovery of self-assembling peptides with generative AI guided by hybrid deep learning	122
Generative AI for designing and validating easily synthesizable and structurally novel antibiotics	118
Machine learning prediction of enzyme optimum pH	117
What’s the next word in large language models?	117
Deep spectral component filtering as a foundation model for spectral analysis demonstrated in metabolic profiling	116
How to break information cocoons	116
Combinatorial optimization with physics-inspired graph neural networks	116
A new perspective on the simulation of stochastic problems in fluid mechanics with diffusion models	111
Error-controlled non-additive interaction discovery in machine learning models	110
Learning from models beyond fine-tuning	106
Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock	101
Laplace neural operator for solving differential equations	99
Multi-animal 3D social pose estimation, identification and behaviour embedding with a few-shot learning framework	98
Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments	97
Codon language embeddings provide strong signals for use in protein engineering	97
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin	97
Collaborative creativity in AI	96
Bridging peptide presentation and T cell recognition with multi-task learning	95
AI reality check	95
What is in your LLM-based framework?	94
Unifying multi-sample network inference from prior knowledge and omics data with CORNETO	94
Life-threatening ventricular arrhythmia detection challenge in implantable cardioverter–defibrillators	93
A deep learning method for recovering missing signals in transcriptome-wide RNA structure profiles from probing experiments	92
Uncertainty-guided dual-views for semi-supervised volumetric medical image segmentation	91
Autoregressive neural-network wavefunctions for ab initio quantum chemistry	90
Learning high-level visual representations from a child’s perspective without strong inductive biases	90
Unsupervised learning of topological non-Abelian braiding in non-Hermitian bands	88
Seeking a quantum advantage for machine learning	88
Foundation models in healthcare require rethinking reliability	85
Deep learning supported discovery of biomarkers for clinical prognosis of liver cancer	84
Efficient generation of protein pockets with PocketGen	83
Designing a strong test for measuring true common-sense reasoning	83
Tandem mass spectrum prediction for small molecules using graph transformers	82
Image-based generation for molecule design with SketchMol	81
Morphological flexibility in robotic systems through physical polygon meshing	81
Accurate and robust protein sequence design with CarbonDesign	78
Algorithmic fairness and bias mitigation for clinical machine learning with deep reinforcement learning	77
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning	77

A deep generative model enables automated structure elucidation of novel psychoactive substances	76
The TRIPOD-P reporting guideline for improving the integrity and transparency of predictive analytics in healthcare through study protocols	76
A deep generative model for molecule optimization via one fragment modification	76
A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics	76
Neural scaling of deep chemical models	76