Journal & Article

Interdisciplinary Applications

I/F
# Journal I/F

Nature Machine Intelligence

Deep generative classification of blood cell morphology. Reusability report: A distributed strategy for solving combinatorial optimization problems with hypergraph neural networks. Are neural network representations universal or idiosyncratic? Accelerating molecular dynamics by going with the flow. Learning conformational flexibility of immune receptors. Overcoming classic challenges for artificial neural networks by providing incentives and practice. Towards deployment-centric multimodal AI beyond vision and language. Flow matching for accelerated simulation of atomic transport in crystalline materials. Cooperative multi-view integration with a scalable and interpretable model explainer. Tailored structured peptide design with a key-cutting machine approach. Resolving data bias improves generalization in binding affinity prediction. A neural symbolic model for space physics. Single-unit activations confer inductive biases for emergent circuit solutions to cognitive tasks. Predicting the conformational flexibility of antibody and T cell receptor complementarity-determining regions. Efficient protein structure generation with sparse denoising models Towards responsible geospatial foundation models. The importance of negative training data for robust antibody binding prediction. Training data composition determines machine learning generalization and biological rule discovery. Electron-density-informed effective and reliable de novo molecular design and optimization with ED2Mol. Emotional risks of AI companions demand attention Data meets prior knowledge for interpretable mechanistic inference in biology: Recovering biological networks Combining grasping and rotation with a spherical robot hand mechanism Designing metamaterials with programmable nonlinear responses and geometric constraints in graph space Integrating multimodal cancer data using deep latent variable path modelling Bioinspired trajectory modulation for effective slip control in robot manipulation Enhancing deep learning-based field reconstruction with a differentiable learning framework Advancing biomolecular understanding and design following human instructions Unifying multi-sample network inference from prior knowledge and omics data with CORNETO A framework to evaluate machine learning crystal stability predictions. Dimensions underlying the representational alignment of deep neural networks with humans. Robust virtual staining of landmark organelles with Cytoland. A process-centric manipulation taxonomy for the organization, classification and synthesis of tactile robot skills. Why design choices matter in recommender systems. Localizing AI in the global south Firefighting robots should be made responsibly Deep spectral component filtering as a foundation model for spectral analysis demonstrated in metabolic profiling Advancing molecular machine learning representations with stereoelectronics-infused molecular graphs Robot planning with LLMs Personalized uncertainty quantification in artificial intelligence A text-guided protein design framework. Optimal transport for generating transition states in chemical reactions Transparency (in training data) is what we want. Seeking visions for sustainable AI Physical benchmarks for testing algorithms: Causal AI. Bridging peptide presentation and T cell recognition with multi-task learning: Machine learning in immunology. Goals as reward-producing programs. Machine learning solutions looking for PDE problems Modern maxims for an AI oracle: Ai ethics. Learning from models beyond fine-tuning. Moving towards genome-wide data integration for patient stratification with Integrate Any Omics.