Nature Machine Intelligence

Papers
(The TQCC of Nature Machine Intelligence is 34. 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 2021-05-01 to 2025-05-01.)
ArticleCitations
Materiality and risk in the age of pervasive AI sensors425
Author Correction: Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock332
Author Correction: A 5′ UTR language model for decoding untranslated regions of mRNA and function predictions325
Artificial intelligence tackles the nature–nurture debate313
Wiring up recurrent neural networks305
Author Correction: Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence280
Physical benchmarks for testing algorithms276
Investigating machine moral judgement through the Delphi experiment272
A challenge for the law and artificial intelligence268
Wing-strain-based flight control of flapping-wing drones through reinforcement learning245
Physically constrained generative adversarial networks for improving precipitation fields from Earth system models198
A soft-packaged and portable rehabilitation glove capable of closed-loop fine motor skills185
Human autonomy in the age of artificial intelligence184
A multi-modal deep language model for contaminant removal from metagenome-assembled genomes181
Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence172
Discussions of machine versus living intelligence need more clarity170
A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit165
Robotic body augmentation164
Fast and generalizable micromagnetic simulation with deep neural nets156
A question of trust for AI research in medicine151
Reusability report: Deep learning-based analysis of images and spectroscopy data with AtomAI151
Quantum circuit optimization with AlphaTensor148
A Global South perspective for ethical algorithms and the State148
Transformer-based protein generation with regularized latent space optimization145
Deep neural networks with controlled variable selection for the identification of putative causal genetic variants144
Out-of-distribution generalization from labelled and unlabelled gene expression data for drug response prediction144
AI pioneers win 2024 Nobel prizes141
Reusability report: Learning the language of synthetic methods used in medicinal chemistry136
Recurrent graph optimal transport for learning 3D flow motion in particle tracking134
The curious case of the test set AUROC134
Sparsity provides a competitive advantage134
Advancing ethics review practices in AI research132
Maximum diffusion reinforcement learning131
Direct conformational sampling from peptide energy landscapes through hypernetwork-conditioned diffusion130
Zero-shot transfer of protein sequence likelihood models to thermostability prediction127
Bringing artificial intelligence to business management120
Generative AI for designing and validating easily synthesizable and structurally novel antibiotics120
End-to-end privacy preserving deep learning on multi-institutional medical imaging120
Learning function from structure in neuromorphic networks118
Reshaping the discovery of self-assembling peptides with generative AI guided by hybrid deep learning118
What’s the next word in large language models?117
Integrated structure prediction of protein–protein docking with experimental restraints using ColabDock116
Deep-learning-based identification, tracking, pose estimation and behaviour classification of interacting primates and mice in complex environments111
Combinatorial optimization with physics-inspired graph neural networks109
Functional mimicry of Ruffini receptors with fibre Bragg gratings and deep neural networks enables a bio-inspired large-area tactile-sensitive skin106
Learning from models beyond fine-tuning103
A human in the loop in surgery automation102
Machine learning prediction of enzyme optimum pH97
How to break information cocoons94
Codon language embeddings provide strong signals for use in protein engineering91
Laplace neural operator for solving differential equations88
Multi-animal 3D social pose estimation, identification and behaviour embedding with a few-shot learning framework88
Collaborative creativity in AI86
AI reality check86
Bridging peptide presentation and T cell recognition with multi-task learning86
Life-threatening ventricular arrhythmia detection challenge in implantable cardioverter–defibrillators84
Image-based generation for molecule design with SketchMol84
The TRIPOD-P reporting guideline for improving the integrity and transparency of predictive analytics in healthcare through study protocols82
Foundation models in healthcare require rethinking reliability82
Unsupervised learning of topological non-Abelian braiding in non-Hermitian bands81
Designing a strong test for measuring true common-sense reasoning80
Learning high-level visual representations from a child’s perspective without strong inductive biases80
A deep learning method for recovering missing signals in transcriptome-wide RNA structure profiles from probing experiments78
What is in your LLM-based framework?77
Accurate and robust protein sequence design with CarbonDesign77
Autoregressive neural-network wavefunctions for ab initio quantum chemistry76
Fitting elephants in modern machine learning by statistically consistent interpolation75
Seeking a quantum advantage for machine learning75
Algorithmic fairness and bias mitigation for clinical machine learning with deep reinforcement learning74
Neural scaling of deep chemical models72
Morphological flexibility in robotic systems through physical polygon meshing72
Tandem mass spectrum prediction for small molecules using graph transformers70
Efficient generation of protein pockets with PocketGen70
Uncertainty-guided dual-views for semi-supervised volumetric medical image segmentation69
A multi-modal pre-training transformer for universal transfer learning in metal–organic frameworks68
LLM-based agentic systems in medicine and healthcare67
A deep generative model for molecule optimization via one fragment modification66
Autonomous environment-adaptive microrobot swarm navigation enabled by deep learning-based real-time distribution planning65
A deep generative model enables automated structure elucidation of novel psychoactive substances65
Multimodal learning with graphs65
Deep learning supported discovery of biomarkers for clinical prognosis of liver cancer63
Human–AI adaptive dynamics drives the emergence of information cocoons63
Writing the rules in AI-assisted writing62
ARNLE model identifies prevalence potential of SARS-CoV-2 variants61
Advanced AI assistants that act on our behalf may not be ethically or legally feasible60
Moving towards genome-wide data integration for patient stratification with Integrate Any Omics59
Learning plastic matching of robot dynamics in closed-loop central pattern generators58
Foundation models and the privatization of public knowledge57
Geometric deep learning reveals the spatiotemporal features of microscopic motion57
Differentiable visual computing for inverse problems and machine learning55
Empirical observation of negligible fairness–accuracy trade-offs in machine learning for public policy55
From attribution maps to human-understandable explanations through Concept Relevance Propagation55
Improving de novo molecular design with curriculum learning55
Reconstructing growth and dynamic trajectories from single-cell transcriptomics data54
ResGen is a pocket-aware 3D molecular generation model based on parallel multiscale modelling54
A method for multiple-sequence-alignment-free protein structure prediction using a protein language model54
A neuro-vector-symbolic architecture for solving Raven’s progressive matrices54
Anniversary AI reflections54
Segmentation of neurons from fluorescence calcium recordings beyond real time53
Synthetic data accelerates the development of generalizable learning-based algorithms for X-ray image analysis53
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning52
The transformational role of GPU computing and deep learning in drug discovery52
Barriers to academic data science research in the new realm of algorithmic behaviour modification by digital platforms52
Successful implementation of the EU AI Act requires interdisciplinary efforts51
Human-behaviour-based social locomotion model improves the humanization of social robots51
Publisher Correction: A neural machine code and programming framework for the reservoir computer51
A social network for AI51
Lessons from a challenge on forecasting epileptic seizures from non-cerebral signals50
Mode switching in organisms for solving explore-versus-exploit problems50
Active learning for optimal intervention design in causal models50
Leveraging language model for advanced multiproperty molecular optimization via prompt engineering49
Closed-form continuous-time neural networks49
Learning integral operators via neural integral equations49
Distinguishing two features of accountability for AI technologies49
Benchmarking AI-powered docking methods from the perspective of virtual screening48
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling48
Delineating the effective use of self-supervised learning in single-cell genomics47
Improving customer decisions in web-based e-commerce through guerrilla modding47
Defending ChatGPT against jailbreak attack via self-reminders47
Deep learning for predicting rate-induced tipping47
Advances, challenges and opportunities in creating data for trustworthy AI47
Artificial intelligence-powered electronic skin47
Machine learning-enabled globally guaranteed evolutionary computation47
Epistemic fragmentation poses a threat to the governance of online targeting46
Interpretable meta-score for model performance46
Listening in to perceived speech with contrastive learning46
On board with COMET to improve omics prediction models45
A computational framework for neural network-based variational Monte Carlo with Forward Laplacian45
Prediction of robust scientific facts from literature45
Unsupervised ensemble-based phenotyping enhances discoverability of genes related to left-ventricular morphology45
Incorporating physics into data-driven computer vision44
Mitigating the missing-fragmentation problem in de novo peptide sequencing with a two-stage graph-based deep learning model44
A unified deep framework for peptide–major histocompatibility complex–T cell receptor binding prediction43
Fast, scale-adaptive and uncertainty-aware downscaling of Earth system model fields with generative machine learning42
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors42
A generalizable deep learning framework for inferring fine-scale germline mutation rate maps42
Three types of incremental learning41
Data-driven discovery of movement-linked heterogeneity in neurodegenerative diseases41
Deep transfer operator learning for partial differential equations under conditional shift41
Invalid SMILES are beneficial rather than detrimental to chemical language models40
The incentive gap in data work in the era of large models40
Molecular contrastive learning of representations via graph neural networks40
Augmenting large language models with chemistry tools40
Large language models challenge the future of higher education40
AI podcasts for the summer39
Discovering neural policies to drive behaviour by integrating deep reinforcement learning agents with biological neural networks39
Automated construction of cognitive maps with visual predictive coding39
Space missions out of this world with AI38
Microscopy analysis neural network to solve detection, enumeration and segmentation from image-level annotations38
Deconstructing the generalization gap38
Hierarchical deep reinforcement learning reveals a modular mechanism of cell movement38
Automated causal inference in application to randomized controlled clinical trials37
Publisher Correction: Advancing ethics review practices in AI research37
Labelling instructions matter in biomedical image analysis36
Improved protein structure prediction by deep learning irrespective of co-evolution information36
Realistic morphology-preserving generative modelling of the brain36
Pan-Peptide Meta Learning for T-cell receptor–antigen binding recognition36
Predicting the prevalence of complex genetic diseases from individual genotype profiles using capsule networks36
Multiscale topology-enabled structure-to-sequence transformer for protein–ligand interaction predictions36
Physics-based machine learning for subcellular segmentation in living cells35
Visual speech recognition for multiple languages in the wild35
Towards unveiling sensitive and decisive patterns in explainable AI with a case study in geometric deep learning35
Synergy-based robotic quadruped leveraging passivity for natural intelligence and behavioural diversity35
A soft touch for robots35
Design of prime-editing guide RNAs with deep transfer learning35
No chemical killer AI (yet)34
Weak signal extraction enabled by deep neural network denoising of diffraction data34
A framework for tool cognition in robots without prior tool learning or observation34
Simultaneous deep generative modelling and clustering of single-cell genomic data34
Reply to: Inability of a graph neural network heuristic to outperform greedy algorithms in solving combinatorial optimization problems34
Ethics methods are required as part of reporting guidelines for artificial intelligence in healthcare34
On the caveats of AI autophagy34
Author Correction: Predicting equilibrium distributions for molecular systems with deep learning34
0.44457101821899