Nature Machine Intelligence

Article	Citations
Author Correction: A 5′ UTR language model for decoding untranslated regions of mRNA and function predictions	608
Author Correction: Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	605
Physical benchmarks for testing algorithms	495
Materiality and risk in the age of pervasive AI sensors	459
A challenge for the law and artificial intelligence	429
Author Correction: Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock	425
Artificial intelligence tackles the nature–nurture debate	386
Investigating machine moral judgement through the Delphi experiment	346
A multi-modal deep language model for contaminant removal from metagenome-assembled genomes	312
Physically constrained generative adversarial networks for improving precipitation fields from Earth system models	303
Tailored structured peptide design with a key-cutting machine approach	278
Towards reproducible robotics research	271
Human autonomy in the age of artificial intelligence	265
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	241
Wing-strain-based flight control of flapping-wing drones through reinforcement learning	237
Discussions of machine versus living intelligence need more clarity	232
A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit	226
A soft-packaged and portable rehabilitation glove capable of closed-loop fine motor skills	215
A question of trust for AI research in medicine	197
Advancing ethics review practices in AI research	195
A Global South perspective for ethical algorithms and the State	195
Are neural network representations universal or idiosyncratic?	194
Transformer-based protein generation with regularized latent space optimization	192
Deep neural networks with controlled variable selection for the identification of putative causal genetic variants	188
Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene	178

Reusability report: Deep learning-based analysis of images and spectroscopy data with AtomAI	172
Robust virtual staining of landmark organelles with Cytoland	167
The curious case of the test set AUROC	166
Direct conformational sampling from peptide energy landscapes through hypernetwork-conditioned diffusion	157
Large language models still struggle with false beliefs	152
Pseudodata-based molecular structure generator to reveal unknown chemicals	152
Recurrent graph optimal transport for learning 3D flow motion in particle tracking	150
Zero-shot transfer of protein sequence likelihood models to thermostability prediction	145
Maximum diffusion reinforcement learning	135
Generative AI for designing and validating easily synthesizable and structurally novel antibiotics	134
Fast and generalizable micromagnetic simulation with deep neural nets	132
AI pioneers win 2024 Nobel prizes	128
Quantum circuit optimization with AlphaTensor	127
Bringing artificial intelligence to business management	122
How to break information cocoons	121
Reshaping the discovery of self-assembling peptides with generative AI guided by hybrid deep learning	121
A new perspective on the simulation of stochastic problems in fluid mechanics with diffusion models	120
Deep spectral component filtering as a foundation model for spectral analysis demonstrated in metabolic profiling	118
Error-controlled non-additive interaction discovery in machine learning models	118
Learning from models beyond fine-tuning	116
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin	115
Codon language embeddings provide strong signals for use in protein engineering	110
Laplace neural operator for solving differential equations	107
Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock	106
Machine learning prediction of enzyme optimum pH	105
Multi-animal 3D social pose estimation, identification and behaviour embedding with a few-shot learning framework	105
What’s the next word in large language models?	104
Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments	103
AI reality check	100
Combinatorial optimization with physics-inspired graph neural networks	100
Bridging peptide presentation and T cell recognition with multi-task learning	99
What is in your LLM-based framework?	99
Unsupervised learning of topological non-Abelian braiding in non-Hermitian bands	99
Foundation models in healthcare require rethinking reliability	98
Seeking a quantum advantage for machine learning	97
Life-threatening ventricular arrhythmia detection challenge in implantable cardioverter–defibrillators	97
The TRIPOD-P reporting guideline for improving the integrity and transparency of predictive analytics in healthcare through study protocols	96
Designing a strong test for measuring true common-sense reasoning	95
Unifying multi-sample network inference from prior knowledge and omics data with CORNETO	93
Collaborative creativity in AI	93
Efficient generation of protein pockets with PocketGen	88
Image-based generation for molecule design with SketchMol	88
A deep generative model for molecule optimization via one fragment modification	88
Learning high-level visual representations from a child’s perspective without strong inductive biases	87
A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics	87
Algorithmic fairness and bias mitigation for clinical machine learning with deep reinforcement learning	86
A multi-modal pre-training transformer for universal transfer learning in metal–organic frameworks	85
Deep learning supported discovery of biomarkers for clinical prognosis of liver cancer	85
Accurate and robust protein sequence design with CarbonDesign	84
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning	84

Neural scaling of deep chemical models	82
Morphological flexibility in robotic systems through physical polygon meshing	81
Tandem mass spectrum prediction for small molecules using graph transformers	81
Multimodal learning with graphs	79
Uncertainty-guided dual-views for semi-supervised volumetric medical image segmentation	79
Autoregressive neural-network wavefunctions for ab initio quantum chemistry	78
LLM-based agentic systems in medicine and healthcare	77
ARNLE model identifies prevalence potential of SARS-CoV-2 variants	77
Human–AI adaptive dynamics drives the emergence of information cocoons	77
Improving de novo molecular design with curriculum learning	76
Differentiable visual computing for inverse problems and machine learning	75
Foundation models and the privatization of public knowledge	75
Reusability report: Exploring the transferability of self-supervised learning models from single-cell to spatial transcriptomics	74
Towards generalizable and interpretable three-dimensional tracking with inverse neural rendering	74
Writing the rules in AI-assisted writing	72
Barriers to academic data science research in the new realm of algorithmic behaviour modification by digital platforms	72
A neuro-vector-symbolic architecture for solving Raven’s progressive matrices	71
Enhancing deep learning-based field reconstruction with a differentiable learning framework	70
Anniversary AI reflections	70
Advanced AI assistants that act on our behalf may not be ethically or legally feasible	70
Model-based reinforcement learning for ultrasound-driven autonomous microrobots	69
Learning plastic matching of robot dynamics in closed-loop central pattern generators	68
Synthetic data accelerates the development of generalizable learning-based algorithms for X-ray image analysis	68
Moving towards genome-wide data integration for patient stratification with Integrate Any Omics	68
ResGen is a pocket-aware 3D molecular generation model based on parallel multiscale modelling	67
Geometric deep learning reveals the spatiotemporal features of microscopic motion	67
A method for multiple-sequence-alignment-free protein structure prediction using a protein language model	67
The transformational role of GPU computing and deep learning in drug discovery	67
From attribution maps to human-understandable explanations through Concept Relevance Propagation	66
Reconstructing growth and dynamic trajectories from single-cell transcriptomics data	66
A social network for AI	65
Human-behaviour-based social locomotion model improves the humanization of social robots	65
Publisher Correction: A neural machine code and programming framework for the reservoir computer	65
Lessons from a challenge on forecasting epileptic seizures from non-cerebral signals	64
Mask-prior-guided denoising diffusion improves inverse protein folding	64
Mode switching in organisms for solving explore-versus-exploit problems	64
Sampling-enabled scalable manifold learning unveils the discriminative cluster structure of high-dimensional data	64
Active learning for optimal intervention design in causal models	64
Distinguishing two features of accountability for AI technologies	63
Successful implementation of the EU AI Act requires interdisciplinary efforts	63
An interaction-derived graph learning framework for scoring protein–peptide complexes	63
Learning integral operators via neural integral equations	62
Defending ChatGPT against jailbreak attack via self-reminders	61
Leveraging language model for advanced multiproperty molecular optimization via prompt engineering	61
Delineating the effective use of self-supervised learning in single-cell genomics	61
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling	61
Benchmarking AI-powered docking methods from the perspective of virtual screening	60
Closed-form continuous-time neural networks	60
Artificial intelligence-powered electronic skin	60
Advances, challenges and opportunities in creating data for trustworthy AI	59
Listening in to perceived speech with contrastive learning	59
Interpretable meta-score for model performance	58
On board with COMET to improve omics prediction models	57
A new eye on inherited retinal disease	57
The incentive gap in data work in the era of large models	56
Predicting the conformational flexibility of antibody and T cell receptor complementarity-determining regions	56
A unified deep framework for peptide–major histocompatibility complex–T cell receptor binding prediction	56
Improving customer decisions in web-based e-commerce through guerrilla modding	55
Deep learning for predicting rate-induced tipping	55
A generalizable deep learning framework for inferring fine-scale germline mutation rate maps	54
Solving sparse finite element problems on neuromorphic hardware	54
Unsupervised ensemble-based phenotyping enhances discoverability of genes related to left-ventricular morphology	53
Invalid SMILES are beneficial rather than detrimental to chemical language models	53
Fast, scale-adaptive and uncertainty-aware downscaling of Earth system model fields with generative machine learning	53
Data-driven discovery of movement-linked heterogeneity in neurodegenerative diseases	53
Machine learning-enabled globally guaranteed evolutionary computation	53
Lossless data compression by large models	53
Prediction of robust scientific facts from literature	52
A computational framework for neural network-based variational Monte Carlo with Forward Laplacian	51
Mitigating the missing-fragmentation problem in de novo peptide sequencing with a two-stage graph-based deep learning model	51
Incorporating physics into data-driven computer vision	51
Three types of incremental learning	50
Molecular contrastive learning of representations via graph neural networks	50
Deep transfer operator learning for partial differential equations under conditional shift	50
Large language models challenge the future of higher education	50
AI podcasts for the summer	49
Augmenting large language models with chemistry tools	49
Deep learning-based prediction of the selection factors for quantifying selection in immune receptor repertoires	48
Publisher Correction: Advancing ethics review practices in AI research	48
Deconstructing the generalization gap	47

Microscopy analysis neural network to solve detection, enumeration and segmentation from image-level annotations	47
A process-centric manipulation taxonomy for the organization, classification and synthesis of tactile robot skills	47
Realistic morphology-preserving generative modelling of the brain	46
Space missions out of this world with AI	46
Predicting the prevalence of complex genetic diseases from individual genotype profiles using capsule networks	45
The importance of negative training data for robust antibody binding prediction	45
Hierarchical deep reinforcement learning reveals a modular mechanism of cell movement	44
Labelling instructions matter in biomedical image analysis	44
Automated construction of cognitive maps with visual predictive coding	44
Automated causal inference in application to randomized controlled clinical trials	44
Physics-based machine learning for subcellular segmentation in living cells	44
Synergy-based robotic quadruped leveraging passivity for natural intelligence and behavioural diversity	44
Visual speech recognition for multiple languages in the wild	43
Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition	42
Multiscale topology-enabled structure-to-sequence transformer for protein–ligand interaction predictions	42
Discovering neural policies to drive behaviour by integrating deep reinforcement learning agents with biological neural networks	42
Design of prime-editing guide RNAs with deep transfer learning	42
Aligning generalization between humans and machines	41
Generalized biological foundation model with unified nucleic acid and protein language	41
Reply to: Inability of a graph neural network heuristic to outperform greedy algorithms in solving combinatorial optimization problems	40
Why design choices matter in recommender systems	40
Author Correction: Predicting equilibrium distributions for molecular systems with deep learning	39
Accelerating protein engineering with fitness landscape modelling and reinforcement learning	38
On the caveats of AI autophagy	38
A soft touch for robots	38
Type II mechanoreceptors and cuneate spiking neuronal network enable touch localization on a large-area e-skin	38
No chemical killer AI (yet)	37
Geometric deep learning of particle motion by MAGIK	37
An integrated framework to accelerate protein design through mutagenesis	37
Ethics methods are required as part of reporting guidelines for artificial intelligence in healthcare	37
Towards unveiling sensitive and decisive patterns in explainable AI with a case study in geometric deep learning	37