Nature Machine Intelligence

Article	Citations
Author Correction: A 5′ UTR language model for decoding untranslated regions of mRNA and function predictions	535
Author Correction: Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	485
Physical benchmarks for testing algorithms	389
Wiring up recurrent neural networks	381
Materiality and risk in the age of pervasive AI sensors	373
A multi-modal deep language model for contaminant removal from metagenome-assembled genomes	352
Investigating machine moral judgement through the Delphi experiment	336
Physically constrained generative adversarial networks for improving precipitation fields from Earth system models	317
Artificial intelligence tackles the nature–nurture debate	257
Discussions of machine versus living intelligence need more clarity	238
Author Correction: Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock	230
Wing-strain-based flight control of flapping-wing drones through reinforcement learning	226
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	224
Human autonomy in the age of artificial intelligence	218
A challenge for the law and artificial intelligence	216
A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit	192
A question of trust for AI research in medicine	186
A soft-packaged and portable rehabilitation glove capable of closed-loop fine motor skills	186
Advancing ethics review practices in AI research	178
Robotic body augmentation	178
A Global South perspective for ethical algorithms and the State	175
Fast and generalizable micromagnetic simulation with deep neural nets	169
Reusability report: Deep learning-based analysis of images and spectroscopy data with AtomAI	168
Sparsity provides a competitive advantage	168
Transformer-based protein generation with regularized latent space optimization	167

Deep neural networks with controlled variable selection for the identification of putative causal genetic variants	167
Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene	159
Maximum diffusion reinforcement learning	155
Generative AI for designing and validating easily synthesizable and structurally novel antibiotics	155
AI pioneers win 2024 Nobel prizes	153
The curious case of the test set AUROC	143
Out-of-distribution generalization from labelled and unlabelled gene expression data for drug response prediction	142
Robust virtual staining of landmark organelles with Cytoland	139
Recurrent graph optimal transport for learning 3D flow motion in particle tracking	138
Zero-shot transfer of protein sequence likelihood models to thermostability prediction	137
Bringing artificial intelligence to business management	128
Reshaping the discovery of self-assembling peptides with generative AI guided by hybrid deep learning	126
Quantum circuit optimization with AlphaTensor	118
Direct conformational sampling from peptide energy landscapes through hypernetwork-conditioned diffusion	111
How to break information cocoons	110
A new perspective on the simulation of stochastic problems in fluid mechanics with diffusion models	107
Deep spectral component filtering as a foundation model for spectral analysis demonstrated in metabolic profiling	106
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin	105
Combinatorial optimization with physics-inspired graph neural networks	105
Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments	104
Machine learning prediction of enzyme optimum pH	103
Learning from models beyond fine-tuning	102
Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock	102
Codon language embeddings provide strong signals for use in protein engineering	102
What’s the next word in large language models?	101
Laplace neural operator for solving differential equations	100
Multi-animal 3D social pose estimation, identification and behaviour embedding with a few-shot learning framework	100
Collaborative creativity in AI	95
AI reality check	91
Bridging peptide presentation and T cell recognition with multi-task learning	89
Foundation models in healthcare require rethinking reliability	89
A deep learning method for recovering missing signals in transcriptome-wide RNA structure profiles from probing experiments	88
Seeking a quantum advantage for machine learning	86
A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics	86
What is in your LLM-based framework?	86
The TRIPOD-P reporting guideline for improving the integrity and transparency of predictive analytics in healthcare through study protocols	86
Life-threatening ventricular arrhythmia detection challenge in implantable cardioverter–defibrillators	85
Unifying multi-sample network inference from prior knowledge and omics data with CORNETO	84
Unsupervised learning of topological non-Abelian braiding in non-Hermitian bands	83
Image-based generation for molecule design with SketchMol	82
Autoregressive neural-network wavefunctions for ab initio quantum chemistry	78
A deep generative model enables automated structure elucidation of novel psychoactive substances	77
Learning high-level visual representations from a child’s perspective without strong inductive biases	77
Uncertainty-guided dual-views for semi-supervised volumetric medical image segmentation	76
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning	75
A deep generative model for molecule optimization via one fragment modification	74
Deep learning supported discovery of biomarkers for clinical prognosis of liver cancer	73
Designing a strong test for measuring true common-sense reasoning	73
Neural scaling of deep chemical models	73
Accurate and robust protein sequence design with CarbonDesign	72

A multi-modal pre-training transformer for universal transfer learning in metal–organic frameworks	72
Multimodal learning with graphs	71
Tandem mass spectrum prediction for small molecules using graph transformers	71
Algorithmic fairness and bias mitigation for clinical machine learning with deep reinforcement learning	70
Human–AI adaptive dynamics drives the emergence of information cocoons	69
LLM-based agentic systems in medicine and healthcare	69
Morphological flexibility in robotic systems through physical polygon meshing	69
Efficient generation of protein pockets with PocketGen	69
A method for multiple-sequence-alignment-free protein structure prediction using a protein language model	67
ARNLE model identifies prevalence potential of SARS-CoV-2 variants	66
Moving towards genome-wide data integration for patient stratification with Integrate Any Omics	66
Writing the rules in AI-assisted writing	66
Model-based reinforcement learning for ultrasound-driven autonomous microrobots	64
Anniversary AI reflections	63
Differentiable visual computing for inverse problems and machine learning	63
Synthetic data accelerates the development of generalizable learning-based algorithms for X-ray image analysis	62
Towards generalizable and interpretable three-dimensional tracking with inverse neural rendering	62
A neuro-vector-symbolic architecture for solving Raven’s progressive matrices	62
Reusability report: Exploring the transferability of self-supervised learning models from single-cell to spatial transcriptomics	62
Advanced AI assistants that act on our behalf may not be ethically or legally feasible	61
Improving de novo molecular design with curriculum learning	61
The transformational role of GPU computing and deep learning in drug discovery	61
Barriers to academic data science research in the new realm of algorithmic behaviour modification by digital platforms	61
Foundation models and the privatization of public knowledge	60
Empirical observation of negligible fairness–accuracy trade-offs in machine learning for public policy	60
Enhancing deep learning-based field reconstruction with a differentiable learning framework	60
Human-behaviour-based social locomotion model improves the humanization of social robots	59
Geometric deep learning reveals the spatiotemporal features of microscopic motion	58
Learning plastic matching of robot dynamics in closed-loop central pattern generators	58
ResGen is a pocket-aware 3D molecular generation model based on parallel multiscale modelling	57
From attribution maps to human-understandable explanations through Concept Relevance Propagation	56
Publisher Correction: A neural machine code and programming framework for the reservoir computer	56
Reconstructing growth and dynamic trajectories from single-cell transcriptomics data	56
A social network for AI	56
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning	56
Benchmarking AI-powered docking methods from the perspective of virtual screening	55
Active learning for optimal intervention design in causal models	55
Mode switching in organisms for solving explore-versus-exploit problems	55
Leveraging language model for advanced multiproperty molecular optimization via prompt engineering	55
Successful implementation of the EU AI Act requires interdisciplinary efforts	55
Defending ChatGPT against jailbreak attack via self-reminders	55
Mask-prior-guided denoising diffusion improves inverse protein folding	55
Learning integral operators via neural integral equations	54
Lessons from a challenge on forecasting epileptic seizures from non-cerebral signals	54
Distinguishing two features of accountability for AI technologies	54
Delineating the effective use of self-supervised learning in single-cell genomics	54
Closed-form continuous-time neural networks	53
Advances, challenges and opportunities in creating data for trustworthy AI	53
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling	53
Artificial intelligence-powered electronic skin	53
Interpretable meta-score for model performance	52
Improving customer decisions in web-based e-commerce through guerrilla modding	52
Listening in to perceived speech with contrastive learning	51
Prediction of robust scientific facts from literature	51
A unified deep framework for peptide–major histocompatibility complex–T cell receptor binding prediction	51
A new eye on inherited retinal disease	50
On board with COMET to improve omics prediction models	49
Data-driven discovery of movement-linked heterogeneity in neurodegenerative diseases	49
The incentive gap in data work in the era of large models	49
Unsupervised ensemble-based phenotyping enhances discoverability of genes related to left-ventricular morphology	48
Mitigating the missing-fragmentation problem in de novo peptide sequencing with a two-stage graph-based deep learning model	48
A computational framework for neural network-based variational Monte Carlo with Forward Laplacian	48
Incorporating physics into data-driven computer vision	48
A generalizable deep learning framework for inferring fine-scale germline mutation rate maps	48
Fast, scale-adaptive and uncertainty-aware downscaling of Earth system model fields with generative machine learning	48
Machine learning-enabled globally guaranteed evolutionary computation	48
Lossless data compression by large models	48
Invalid SMILES are beneficial rather than detrimental to chemical language models	47
Deep learning for predicting rate-induced tipping	47
Deep transfer operator learning for partial differential equations under conditional shift	46
Augmenting large language models with chemistry tools	46
Large language models challenge the future of higher education	45
Molecular contrastive learning of representations via graph neural networks	45
AI podcasts for the summer	45
Three types of incremental learning	45
Automated causal inference in application to randomized controlled clinical trials	44
Realistic morphology-preserving generative modelling of the brain	44
Space missions out of this world with AI	44
A process-centric manipulation taxonomy for the organization, classification and synthesis of tactile robot skills	44
Hierarchical deep reinforcement learning reveals a modular mechanism of cell movement	44

Publisher Correction: Advancing ethics review practices in AI research	44
Microscopy analysis neural network to solve detection, enumeration and segmentation from image-level annotations	44
Design of prime-editing guide RNAs with deep transfer learning	43
Discovering neural policies to drive behaviour by integrating deep reinforcement learning agents with biological neural networks	43
Multiscale topology-enabled structure-to-sequence transformer for protein–ligand interaction predictions	43
Deep learning-based prediction of the selection factors for quantifying selection in immune receptor repertoires	42
Synergy-based robotic quadruped leveraging passivity for natural intelligence and behavioural diversity	42
The importance of negative training data for robust antibody binding prediction	42
Physics-based machine learning for subcellular segmentation in living cells	41
Visual speech recognition for multiple languages in the wild	41
Generalized biological foundation model with unified nucleic acid and protein language	41
Predicting the prevalence of complex genetic diseases from individual genotype profiles using capsule networks	41
Automated construction of cognitive maps with visual predictive coding	41
Labelling instructions matter in biomedical image analysis	41
A soft touch for robots	40
Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition	40
Reply to: Inability of a graph neural network heuristic to outperform greedy algorithms in solving combinatorial optimization problems	40
Deconstructing the generalization gap	40
Ethics methods are required as part of reporting guidelines for artificial intelligence in healthcare	39
Author Correction: Predicting equilibrium distributions for molecular systems with deep learning	39
Geometric deep learning of particle motion by MAGIK	38
Why design choices matter in recommender systems	38
No chemical killer AI (yet)	37
A framework for tool cognition in robots without prior tool learning or observation	37
A disease-specific language model for variant pathogenicity in cardiac and regulatory genomics	37
On the caveats of AI autophagy	37
Weak signal extraction enabled by deep neural network denoising of diffraction data	36
Towards unveiling sensitive and decisive patterns in explainable AI with a case study in geometric deep learning	36
Type II mechanoreceptors and cuneate spiking neuronal network enable touch localization on a large-area e-skin	36
Embodied large language models enable robots to complete complex tasks in unpredictable environments	36
Iterative human and automated identification of wildlife images	35
DishBrain plays Pong and promises more	35
Parameter-efficient fine-tuning of large-scale pre-trained language models	35
Testing the limits of SMILES-based de novo molecular generation with curriculum and deep reinforcement learning	34
In vitro convolutional neural networks	34
AI safety for everyone	34
Clinical large language models with misplaced focus	33
Publisher Correction: The curious case of the test set AUROC	33
Personalized uncertainty quantification in artificial intelligence	32
Efficient rare event sampling with unsupervised normalizing flows	32
Learning fast in autonomous drone racing	32
A ‘programming’ framework for recurrent neural networks	32
Boosting the predictive power of protein representations with a corpus of text annotations	31
Learning motif-based graphs for drug–drug interaction prediction via local–global self-attention	31
An adaptive graph learning method for automated molecular interactions and properties predictions	31
Design of potent antimalarials with generative chemistry	31
Automatic strain sensor design via active learning and data augmentation for soft machines	30
PocketFlow is a data-and-knowledge-driven structure-based molecular generative model	30
Large pre-trained language models contain human-like biases of what is right and wrong to do	30
Leveraging ancestral sequence reconstruction for protein representation learning	30
Controllable protein design with language models	29
Categorizing robots by performance fitness into the tree of robots	29
A soft skin with self-decoupled three-axis force-sensing taxels	29
Sliding-attention transformer neural architecture for predicting T cell receptor–antigen–human leucocyte antigen binding	29
Deep learning-based prediction of the T cell receptor–antigen binding specificity	29
Language and culture internalization for human-like autotelic AI	29
Catching up with missing particles	28
Accurate online training of dynamical spiking neural networks through Forward Propagation Through Time	28
Bridging the neutralization gap for unseen antibodies	28
Neural Error Mitigation of Near-Term Quantum Simulations	28
Towards a personalized AI assistant to learn machine learning	27
Inferring transcription factor regulatory networks from single-cell ATAC-seq data based on graph neural networks	26
Modern graph neural networks do worse than classical greedy algorithms in solving combinatorial optimization problems like maximum independent set	26
Rigorous integration of single-cell ATAC-seq data using regularized barycentric mapping	26
Low-power object-detection challenge on unmanned aerial vehicles	26
Self-iterative multiple-instance learning enables the prediction of CD4+ T cell immunogenic epitopes	26
Generation of 3D molecules in pockets via a language model	26
Kernel approximation using analogue in-memory computing	26
Sparse learned kernels for interpretable and efficient medical time series processing	26
Uncertainty quantification via a memristor Bayesian deep neural network for risk-sensitive reinforcement learning	26
A multilevel generative framework with hierarchical self-contrasting for bias control and transparency in structure-based ligand design	25
Predicting unseen antibodies’ neutralizability via adaptive graph neural networks	25
Enabling large language models for real-world materials discovery	25
Estimating treatment effects for time-to-treatment antibiotic stewardship in sepsis	25
Geometry-enhanced pretraining on interatomic potentials	25
Bioinspired trajectory modulation for effective slip control in robot manipulation	24
The future of open human feedback	24
What comparing deep neural networks can teach us about human vision	24
Author Correction: End-to-end cryo-EM complex structure determination with high accuracy and ultra-fast speed	24
A bioactivity foundation model using pairwise meta-learning	24
On responsible machine learning datasets emphasizing fairness, privacy and regulatory norms with examples in biometrics and healthcare	24
The promise of generative AI for suicide prevention in India	24
Realizing full-body control of humanoid robots	24
Neuromorphic visual scene understanding with resonator networks	24
Spatially embedded recurrent neural networks reveal widespread links between structural and functional neuroscience findings	23
High-speed quadrupedal locomotion by imitation-relaxation reinforcement learning	23
Multitask joint strategies of self-supervised representation learning on biomedical networks for drug discovery	23
Kolmogorov–Arnold graph neural networks for molecular property prediction	23
Multiple stakeholders drive diverse interpretability requirements for machine learning in healthcare	23
Human-like object concept representations emerge naturally in multimodal large language models	23
Reply to: The pitfalls of negative data bias for the T-cell epitope specificity challenge	23
Prediction of mechanistic subtypes of Parkinson’s using patient-derived stem cell models	23
Pick your AI poison	22
A cautionary tale about the adoption of medical AI in Sweden	22
Cognitive maps from predictive vision	22