Nature Machine Intelligence

Article	Citations
Author Correction: A 5′ UTR language model for decoding untranslated regions of mRNA and function predictions	517
Author Correction: Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	444
Physical benchmarks for testing algorithms	378
Wiring up recurrent neural networks	359
Materiality and risk in the age of pervasive AI sensors	349
A challenge for the law and artificial intelligence	334
Human autonomy in the age of artificial intelligence	328
A multi-modal deep language model for contaminant removal from metagenome-assembled genomes	304
Discussions of machine versus living intelligence need more clarity	238
A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit	228
Author Correction: Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock	220
Investigating machine moral judgement through the Delphi experiment	213
Physically constrained generative adversarial networks for improving precipitation fields from Earth system models	207
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	204
A soft-packaged and portable rehabilitation glove capable of closed-loop fine motor skills	195
Wing-strain-based flight control of flapping-wing drones through reinforcement learning	181
Artificial intelligence tackles the nature–nurture debate	179
A question of trust for AI research in medicine	174
Robotic body augmentation	173
A Global South perspective for ethical algorithms and the State	170
Sparsity provides a competitive advantage	166
Maximum diffusion reinforcement learning	165
Advancing ethics review practices in AI research	164
Robust virtual staining of landmark organelles with Cytoland	161
Quantum circuit optimization with AlphaTensor	161

Bringing artificial intelligence to business management	161
The curious case of the test set AUROC	159
Reshaping the discovery of self-assembling peptides with generative AI guided by hybrid deep learning	151
Reusability report: Deep learning-based analysis of images and spectroscopy data with AtomAI	150
Out-of-distribution generalization from labelled and unlabelled gene expression data for drug response prediction	150
Fast and generalizable micromagnetic simulation with deep neural nets	150
Transformer-based protein generation with regularized latent space optimization	135
Direct conformational sampling from peptide energy landscapes through hypernetwork-conditioned diffusion	134
Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene	133
Deep neural networks with controlled variable selection for the identification of putative causal genetic variants	130
AI pioneers win 2024 Nobel prizes	130
Recurrent graph optimal transport for learning 3D flow motion in particle tracking	124
Zero-shot transfer of protein sequence likelihood models to thermostability prediction	119
Generative AI for designing and validating easily synthesizable and structurally novel antibiotics	116
Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock	104
What’s the next word in large language models?	104
Machine learning prediction of enzyme optimum pH	103
Combinatorial optimization with physics-inspired graph neural networks	102
Deep spectral component filtering as a foundation model for spectral analysis demonstrated in metabolic profiling	101
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin	101
How to break information cocoons	100
A new perspective on the simulation of stochastic problems in fluid mechanics with diffusion models	99
Learning from models beyond fine-tuning	98
Multi-animal 3D social pose estimation, identification and behaviour embedding with a few-shot learning framework	98
Laplace neural operator for solving differential equations	98
Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments	96
Learning function from structure in neuromorphic networks	95
Codon language embeddings provide strong signals for use in protein engineering	93
Collaborative creativity in AI	90
Foundation models in healthcare require rethinking reliability	88
Bridging peptide presentation and T cell recognition with multi-task learning	88
AI reality check	88
Accurate and robust protein sequence design with CarbonDesign	87
Designing a strong test for measuring true common-sense reasoning	87
Seeking a quantum advantage for machine learning	84
Life-threatening ventricular arrhythmia detection challenge in implantable cardioverter–defibrillators	84
A deep learning method for recovering missing signals in transcriptome-wide RNA structure profiles from probing experiments	83
Learning high-level visual representations from a child’s perspective without strong inductive biases	82
The TRIPOD-P reporting guideline for improving the integrity and transparency of predictive analytics in healthcare through study protocols	79
A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics	79
Image-based generation for molecule design with SketchMol	77
Deep learning supported discovery of biomarkers for clinical prognosis of liver cancer	76
What is in your LLM-based framework?	76
Algorithmic fairness and bias mitigation for clinical machine learning with deep reinforcement learning	75
Autoregressive neural-network wavefunctions for ab initio quantum chemistry	74
Tandem mass spectrum prediction for small molecules using graph transformers	74
Unifying multi-sample network inference from prior knowledge and omics data with CORNETO	73
A deep generative model enables automated structure elucidation of novel psychoactive substances	72
Neural scaling of deep chemical models	69
LLM-based agentic systems in medicine and healthcare	68

Unsupervised learning of topological non-Abelian braiding in non-Hermitian bands	68
Multimodal learning with graphs	68
A deep generative model for molecule optimization via one fragment modification	68
Morphological flexibility in robotic systems through physical polygon meshing	67
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning	67
A multi-modal pre-training transformer for universal transfer learning in metal–organic frameworks	67
Efficient generation of protein pockets with PocketGen	66
Uncertainty-guided dual-views for semi-supervised volumetric medical image segmentation	65
Reconstructing growth and dynamic trajectories from single-cell transcriptomics data	64
Human–AI adaptive dynamics drives the emergence of information cocoons	64
Synthetic data accelerates the development of generalizable learning-based algorithms for X-ray image analysis	63
A method for multiple-sequence-alignment-free protein structure prediction using a protein language model	63
ResGen is a pocket-aware 3D molecular generation model based on parallel multiscale modelling	62
ARNLE model identifies prevalence potential of SARS-CoV-2 variants	61
Writing the rules in AI-assisted writing	61
Advanced AI assistants that act on our behalf may not be ethically or legally feasible	61
Moving towards genome-wide data integration for patient stratification with Integrate Any Omics	61
Human-behaviour-based social locomotion model improves the humanization of social robots	61
Barriers to academic data science research in the new realm of algorithmic behaviour modification by digital platforms	60
A neuro-vector-symbolic architecture for solving Raven’s progressive matrices	60
Improving de novo molecular design with curriculum learning	59
Differentiable visual computing for inverse problems and machine learning	59
Empirical observation of negligible fairness–accuracy trade-offs in machine learning for public policy	59
Anniversary AI reflections	58
Model-based reinforcement learning for ultrasound-driven autonomous microrobots	58
Enhancing deep learning-based field reconstruction with a differentiable learning framework	58
The transformational role of GPU computing and deep learning in drug discovery	57
Geometric deep learning reveals the spatiotemporal features of microscopic motion	57
Foundation models and the privatization of public knowledge	57
Learning plastic matching of robot dynamics in closed-loop central pattern generators	57
From attribution maps to human-understandable explanations through Concept Relevance Propagation	57
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning	57
A social network for AI	55
Publisher Correction: A neural machine code and programming framework for the reservoir computer	55
Lessons from a challenge on forecasting epileptic seizures from non-cerebral signals	54
Learning integral operators via neural integral equations	54
Benchmarking AI-powered docking methods from the perspective of virtual screening	54
Mask-prior-guided denoising diffusion improves inverse protein folding	54
Distinguishing two features of accountability for AI technologies	53
Delineating the effective use of self-supervised learning in single-cell genomics	53
Successful implementation of the EU AI Act requires interdisciplinary efforts	53
Artificial intelligence-powered electronic skin	53
Leveraging language model for advanced multiproperty molecular optimization via prompt engineering	53
Closed-form continuous-time neural networks	52
Active learning for optimal intervention design in causal models	52
Defending ChatGPT against jailbreak attack via self-reminders	52
Mode switching in organisms for solving explore-versus-exploit problems	51
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling	51
Advances, challenges and opportunities in creating data for trustworthy AI	51
Improving customer decisions in web-based e-commerce through guerrilla modding	50
Interpretable meta-score for model performance	50
On board with COMET to improve omics prediction models	49
Listening in to perceived speech with contrastive learning	49
Data-driven discovery of movement-linked heterogeneity in neurodegenerative diseases	49
Deep learning for predicting rate-induced tipping	48
Prediction of robust scientific facts from literature	48
A generalizable deep learning framework for inferring fine-scale germline mutation rate maps	48
The incentive gap in data work in the era of large models	48
Lossless data compression by large models	48
A new eye on inherited retinal disease	47
Incorporating physics into data-driven computer vision	47
A computational framework for neural network-based variational Monte Carlo with Forward Laplacian	47
Unsupervised ensemble-based phenotyping enhances discoverability of genes related to left-ventricular morphology	47
Mitigating the missing-fragmentation problem in de novo peptide sequencing with a two-stage graph-based deep learning model	46
Machine learning-enabled globally guaranteed evolutionary computation	46
Augmenting large language models with chemistry tools	46
A unified deep framework for peptide–major histocompatibility complex–T cell receptor binding prediction	45
Molecular contrastive learning of representations via graph neural networks	45
Fast, scale-adaptive and uncertainty-aware downscaling of Earth system model fields with generative machine learning	45
Three types of incremental learning	44
Large language models challenge the future of higher education	44
Publisher Correction: Advancing ethics review practices in AI research	43
AI podcasts for the summer	43
Deconstructing the generalization gap	43
Invalid SMILES are beneficial rather than detrimental to chemical language models	43
Space missions out of this world with AI	43
Deep transfer operator learning for partial differential equations under conditional shift	43
Automated causal inference in application to randomized controlled clinical trials	42
Predicting the prevalence of complex genetic diseases from individual genotype profiles using capsule networks	42
Design of prime-editing guide RNAs with deep transfer learning	42

Microscopy analysis neural network to solve detection, enumeration and segmentation from image-level annotations	41
Generalized biological foundation model with unified nucleic acid and protein language	41
Physics-based machine learning for subcellular segmentation in living cells	41
A process-centric manipulation taxonomy for the organization, classification and synthesis of tactile robot skills	40
Automated construction of cognitive maps with visual predictive coding	40
Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition	40
Labelling instructions matter in biomedical image analysis	40
Realistic morphology-preserving generative modelling of the brain	40
Hierarchical deep reinforcement learning reveals a modular mechanism of cell movement	40
Discovering neural policies to drive behaviour by integrating deep reinforcement learning agents with biological neural networks	40
Multiscale topology-enabled structure-to-sequence transformer for protein–ligand interaction predictions	40
A soft touch for robots	39
Synergy-based robotic quadruped leveraging passivity for natural intelligence and behavioural diversity	39
Reply to: Inability of a graph neural network heuristic to outperform greedy algorithms in solving combinatorial optimization problems	39
Visual speech recognition for multiple languages in the wild	39
Ethics methods are required as part of reporting guidelines for artificial intelligence in healthcare	38
No chemical killer AI (yet)	38
Author Correction: Predicting equilibrium distributions for molecular systems with deep learning	38
Why design choices matter in recommender systems	38
On the caveats of AI autophagy	37
Geometric deep learning of particle motion by MAGIK	37
Embodied large language models enable robots to complete complex tasks in unpredictable environments	37
A disease-specific language model for variant pathogenicity in cardiac and regulatory genomics	37