Nature Machine Intelligence

Article	Citations
Author Correction: A 5′ UTR language model for decoding untranslated regions of mRNA and function predictions	641
Author Correction: Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence	627
Physical benchmarks for testing algorithms	550
A challenge for the law and artificial intelligence	476
Towards reproducible robotics research	446
Author Correction: Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock	436
Artificial intelligence tackles the nature–nurture debate	394
A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit	354
Investigating machine moral judgement through the Delphi experiment	329
A multi-modal deep language model for contaminant removal from metagenome-assembled genomes	329
Discussions of machine versus living intelligence need more clarity	297
Physically constrained generative adversarial networks for improving precipitation fields from Earth system models	286
Human autonomy in the age of artificial intelligence	260
Materiality and risk in the age of pervasive AI sensors	241
Wing-strain-based flight control of flapping-wing drones through reinforcement learning	239
A soft-packaged and portable rehabilitation glove capable of closed-loop fine motor skills	225
Tailored structured peptide design with a key-cutting machine approach	205
AI pioneers win 2024 Nobel prizes	201
A question of trust for AI research in medicine	201
Robust virtual staining of landmark organelles with Cytoland	200
Fast and generalizable micromagnetic simulation with deep neural nets	200
Reusability report: Deep learning-based analysis of images and spectroscopy data with AtomAI	195
The curious case of the test set AUROC	185
Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene	179
Are neural network representations universal or idiosyncratic?	176

Transformer-based protein generation with regularized latent space optimization	170
Large language models still struggle with false beliefs	161
Pseudodata-based molecular structure generator to reveal unknown chemicals	161
A Global South perspective for ethical algorithms and the State	160
Maximum diffusion reinforcement learning	159
Zero-shot transfer of protein sequence likelihood models to thermostability prediction	148
Deep neural networks with controlled variable selection for the identification of putative causal genetic variants	144
Advancing ethics review practices in AI research	141
Generative AI for designing and validating easily synthesizable and structurally novel antibiotics	136
Bringing artificial intelligence to business management	133
Quantum circuit optimization with AlphaTensor	126
Direct conformational sampling from peptide energy landscapes through hypernetwork-conditioned diffusion	123
Recurrent graph optimal transport for learning 3D flow motion in particle tracking	123
Inferring spatial single-cell-level interactions through interpreting cell state and niche correlations learned by self-supervised graph transformer	122
Reshaping the discovery of self-assembling peptides with generative AI guided by hybrid deep learning	122
A new perspective on the simulation of stochastic problems in fluid mechanics with diffusion models	121
How to break information cocoons	121
Error-controlled non-additive interaction discovery in machine learning models	118
Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock	115
What’s the next word in large language models?	114
Deep spectral component filtering as a foundation model for spectral analysis demonstrated in metabolic profiling	113
Machine learning prediction of enzyme optimum pH	110
Laplace neural operator for solving differential equations	109
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin	108
Codon language embeddings provide strong signals for use in protein engineering	108
Combinatorial optimization with physics-inspired graph neural networks	107
Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments	102
Multi-animal 3D social pose estimation, identification and behaviour embedding with a few-shot learning framework	101
Learning from models beyond fine-tuning	101
AI reality check	100
What is in your LLM-based framework?	100
Unsupervised learning of topological non-Abelian braiding in non-Hermitian bands	100
Foundation models in healthcare require rethinking reliability	99
Life-threatening ventricular arrhythmia detection challenge in implantable cardioverter–defibrillators	98
Seeking a quantum advantage for machine learning	96
Algorithmic fairness and bias mitigation for clinical machine learning with deep reinforcement learning	94
Deciphering RNA–ligand binding specificity with GerNA-Bind	93
Designing a strong test for measuring true common-sense reasoning	92
Efficient generation of protein pockets with PocketGen	90
Collaborative creativity in AI	90
Bridging peptide presentation and T cell recognition with multi-task learning	89
Learning high-level visual representations from a child’s perspective without strong inductive biases	89
Unifying multi-sample network inference from prior knowledge and omics data with CORNETO	89
Autoregressive neural-network wavefunctions for ab initio quantum chemistry	89
Deep learning supported discovery of biomarkers for clinical prognosis of liver cancer	88
Neural scaling of deep chemical models	86
Morphological flexibility in robotic systems through physical polygon meshing	85
Uncertainty-guided dual-views for semi-supervised volumetric medical image segmentation	85
Image-based generation for molecule design with SketchMol	85
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning	83

Accurate and robust protein sequence design with CarbonDesign	83
The TRIPOD-P reporting guideline for improving the integrity and transparency of predictive analytics in healthcare through study protocols	81
Multimodal learning with graphs	81
Tandem mass spectrum prediction for small molecules using graph transformers	80
A multi-modal pre-training transformer for universal transfer learning in metal–organic frameworks	80
Human–AI adaptive dynamics drives the emergence of information cocoons	80
LLM-based agentic systems in medicine and healthcare	79
A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics	79
ARNLE model identifies prevalence potential of SARS-CoV-2 variants	79
Foundation models and the privatization of public knowledge	77
Differentiable visual computing for inverse problems and machine learning	76
Towards generalizable and interpretable three-dimensional tracking with inverse neural rendering	76
Improving de novo molecular design with curriculum learning	76
Human-behaviour-based social locomotion model improves the humanization of social robots	75
Barriers to academic data science research in the new realm of algorithmic behaviour modification by digital platforms	74
Advanced AI assistants that act on our behalf may not be ethically or legally feasible	74
Anniversary AI reflections	73
A multimodal cell-free RNA language model for liquid biopsy applications	72
A neuro-vector-symbolic architecture for solving Raven’s progressive matrices	72
Learning plastic matching of robot dynamics in closed-loop central pattern generators	72
Moving towards genome-wide data integration for patient stratification with Integrate Any Omics	71
Synthetic data accelerates the development of generalizable learning-based algorithms for X-ray image analysis	71
ResGen is a pocket-aware 3D molecular generation model based on parallel multiscale modelling	71
Reusability report: Exploring the transferability of self-supervised learning models from single-cell to spatial transcriptomics	71
Enhancing deep learning-based field reconstruction with a differentiable learning framework	69
Model-based reinforcement learning for ultrasound-driven autonomous microrobots	69
The transformational role of GPU computing and deep learning in drug discovery	69
Writing the rules in AI-assisted writing	69
From attribution maps to human-understandable explanations through Concept Relevance Propagation	68
Reconstructing growth and dynamic trajectories from single-cell transcriptomics data	68
Geometric deep learning reveals the spatiotemporal features of microscopic motion	68
Publisher Correction: A neural machine code and programming framework for the reservoir computer	66
A social network for AI	66
A method for multiple-sequence-alignment-free protein structure prediction using a protein language model	66
Successful implementation of the EU AI Act requires interdisciplinary efforts	65
Sampling-enabled scalable manifold learning unveils the discriminative cluster structure of high-dimensional data	65
Distinguishing two features of accountability for AI technologies	65
Mask-prior-guided denoising diffusion improves inverse protein folding	65
Lessons from a challenge on forecasting epileptic seizures from non-cerebral signals	64
Leveraging language model for advanced multiproperty molecular optimization via prompt engineering	64
Learning integral operators via neural integral equations	63
Defending ChatGPT against jailbreak attack via self-reminders	63
An interaction-derived graph learning framework for scoring protein–peptide complexes	63
Benchmarking AI-powered docking methods from the perspective of virtual screening	62
Mode switching in organisms for solving explore-versus-exploit problems	61
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling	61
Advances, challenges and opportunities in creating data for trustworthy AI	61
Learning intermediate physical states for inverse metasurface design	60
Active learning for optimal intervention design in causal models	59
Closed-form continuous-time neural networks	59
Artificial intelligence-powered electronic skin	58
Delineating the effective use of self-supervised learning in single-cell genomics	58
Listening in to perceived speech with contrastive learning	57
Interpretable meta-score for model performance	56
On board with COMET to improve omics prediction models	56
A new eye on inherited retinal disease	55
A generalizable deep learning framework for inferring fine-scale germline mutation rate maps	55
Prediction of robust scientific facts from literature	55
The incentive gap in data work in the era of large models	55
Mitigating the missing-fragmentation problem in de novo peptide sequencing with a two-stage graph-based deep learning model	55
A unified deep framework for peptide–major histocompatibility complex–T cell receptor binding prediction	54
Deep transfer operator learning for partial differential equations under conditional shift	54
Deep learning for predicting rate-induced tipping	54
Machine learning-enabled globally guaranteed evolutionary computation	53
A computational framework for neural network-based variational Monte Carlo with Forward Laplacian	53
Solving sparse finite element problems on neuromorphic hardware	53
Lossless data compression by large models	52
Data-driven discovery of movement-linked heterogeneity in neurodegenerative diseases	52
Versatile cardiovascular signal generation with a unified diffusion transformer	52
Incorporating physics into data-driven computer vision	52
Fast, scale-adaptive and uncertainty-aware downscaling of Earth system model fields with generative machine learning	51
Predicting the conformational flexibility of antibody and T cell receptor complementarity-determining regions	51
Three types of incremental learning	50
Large language models challenge the future of higher education	50
Current-diffusion model for metasurface structure discoveries with spatial-frequency dynamics	50
Molecular contrastive learning of representations via graph neural networks	50
Invalid SMILES are beneficial rather than detrimental to chemical language models	49
Augmenting large language models with chemistry tools	48
Unsupervised ensemble-based phenotyping enhances discoverability of genes related to left-ventricular morphology	48
AI podcasts for the summer	47

Predicting the prevalence of complex genetic diseases from individual genotype profiles using capsule networks	47
Deep learning-based prediction of the selection factors for quantifying selection in immune receptor repertoires	47
Publisher Correction: Advancing ethics review practices in AI research	47
Deconstructing the generalization gap	46
A process-centric manipulation taxonomy for the organization, classification and synthesis of tactile robot skills	46
Space missions out of this world with AI	45
Microscopy analysis neural network to solve detection, enumeration and segmentation from image-level annotations	44
Synergy-based robotic quadruped leveraging passivity for natural intelligence and behavioural diversity	44
Automated construction of cognitive maps with visual predictive coding	44
The importance of negative training data for robust antibody binding prediction	44
Discovering neural policies to drive behaviour by integrating deep reinforcement learning agents with biological neural networks	43
Automated causal inference in application to randomized controlled clinical trials	43
Realistic morphology-preserving generative modelling of the brain	43
Design of prime-editing guide RNAs with deep transfer learning	43
Labelling instructions matter in biomedical image analysis	42
Aligning generalization between humans and machines	42
Generalized biological foundation model with unified nucleic acid and protein language	41
Hierarchical deep reinforcement learning reveals a modular mechanism of cell movement	41
Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition	40
Visual speech recognition for multiple languages in the wild	40
Multiscale topology-enabled structure-to-sequence transformer for protein–ligand interaction predictions	40
Reply to: Inability of a graph neural network heuristic to outperform greedy algorithms in solving combinatorial optimization problems	39
Why design choices matter in recommender systems	39
Author Correction: Predicting equilibrium distributions for molecular systems with deep learning	38
Weak signal extraction enabled by deep neural network denoising of diffraction data	38
Accelerating protein engineering with fitness landscape modelling and reinforcement learning	38
A disease-specific language model for variant pathogenicity in cardiac and regulatory genomics	38
Type II mechanoreceptors and cuneate spiking neuronal network enable touch localization on a large-area e-skin	37
Towards unveiling sensitive and decisive patterns in explainable AI with a case study in geometric deep learning	37
A soft touch for robots	37
No chemical killer AI (yet)	37
Embodied large language models enable robots to complete complex tasks in unpredictable environments	37
Ethics methods are required as part of reporting guidelines for artificial intelligence in healthcare	37
An integrated framework to accelerate protein design through mutagenesis	37
Geometric deep learning of particle motion by MAGIK	37
A framework for tool cognition in robots without prior tool learning or observation	37
South Asian biases in language and vision models	36
Clinical large language models with misplaced focus	36
DishBrain plays Pong and promises more	36
Parameter-efficient fine-tuning of large-scale pre-trained language models	36
On the caveats of AI autophagy	36
Publisher Correction: The curious case of the test set AUROC	36
In vitro convolutional neural networks	35
Boosting the predictive power of protein representations with a corpus of text annotations	35
A ‘programming’ framework for recurrent neural networks	34
An adaptive graph learning method for automated molecular interactions and properties predictions	34
Testing the limits of SMILES-based de novo molecular generation with curriculum and deep reinforcement learning	34
Leveraging ancestral sequence reconstruction for protein representation learning	34
Large pre-trained language models contain human-like biases of what is right and wrong to do	33
PocketFlow is a data-and-knowledge-driven structure-based molecular generative model	33
Efficient rare event sampling with unsupervised normalizing flows	33
Personalized uncertainty quantification in artificial intelligence	33
AI safety for everyone	33
A soft skin with self-decoupled three-axis force-sensing taxels	32
Controllable protein design with language models	32
Author Correction: Scalable and robust DNA-based storage via coding theory and deep learning	32
Design of potent antimalarials with generative chemistry	31
Automatic strain sensor design via active learning and data augmentation for soft machines	31
Sliding-attention transformer neural architecture for predicting T cell receptor–antigen–human leucocyte antigen binding	31
Learning motif-based graphs for drug–drug interaction prediction via local–global self-attention	31
A multilevel generative framework with hierarchical self-contrasting for bias control and transparency in structure-based ligand design	30
Catching up with missing particles	30
Sparse learned kernels for interpretable and efficient medical time series processing	30
Language and culture internalization for human-like autotelic AI	30
Bridging the neutralization gap for unseen antibodies	30
Low-power object-detection challenge on unmanned aerial vehicles	30
Towards a personalized AI assistant to learn machine learning	30
Rigorous integration of single-cell ATAC-seq data using regularized barycentric mapping	29
Modern graph neural networks do worse than classical greedy algorithms in solving combinatorial optimization problems like maximum independent set	29
Categorizing robots by performance fitness into the tree of robots	29
Estimating treatment effects for time-to-treatment antibiotic stewardship in sepsis	29
Predicting unseen antibodies’ neutralizability via adaptive graph neural networks	29
Neural Error Mitigation of Near-Term Quantum Simulations	29
Accurate online training of dynamical spiking neural networks through Forward Propagation Through Time	28
Uncertainty quantification via a memristor Bayesian deep neural network for risk-sensitive reinforcement learning	28
Enabling large language models for real-world materials discovery	28
Self-iterative multiple-instance learning enables the prediction of CD4+ T cell immunogenic epitopes	28
Inferring transcription factor regulatory networks from single-cell ATAC-seq data based on graph neural networks	28
Generation of 3D molecules in pockets via a language model	28
Kernel approximation using analogue in-memory computing	28
Geometry-enhanced pretraining on interatomic potentials	27
The promise of generative AI for suicide prevention in India	27
Bioinspired trajectory modulation for effective slip control in robot manipulation	27
Author Correction: End-to-end cryo-EM complex structure determination with high accuracy and ultra-fast speed	27
Reply to: The pitfalls of negative data bias for the T-cell epitope specificity challenge	26
Realizing full-body control of humanoid robots	26
The future of open human feedback	26
Neuromorphic visual scene understanding with resonator networks	26
On responsible machine learning datasets emphasizing fairness, privacy and regulatory norms with examples in biometrics and healthcare	25
Multitask joint strategies of self-supervised representation learning on biomedical networks for drug discovery	25
What comparing deep neural networks can teach us about human vision	25
High-speed quadrupedal locomotion by imitation-relaxation reinforcement learning	25
Prediction of mechanistic subtypes of Parkinson’s using patient-derived stem cell models	25
A bioactivity foundation model using pairwise meta-learning	25
Efficient protein structure generation with sparse denoising models	25