A social network for AI.
Reporting electricity consumption is essential for sustainable AI.
A social path to human-like artificial intelligence.
Differentiable visual computing for inverse problems and machine learning.
Self-supervised deep learning for tracking degradation of perovskite light-emitting diodes with multispectral imaging.
AI reality check.
Battling disinformation with cryptography.
Many-body control with reinforcement learning and tensor networks.
The pitfalls of negative data bias for the T-cell epitope specificity challenge.
Reply to: The pitfalls of negative data bias for the T-cell epitope specificity challenge.
A method for multiple-sequence-alignment-free protein structure prediction using a protein language model.
Decoding speech perception from non-invasive brain recordings.
Matching algorithms for blood donation.
Improving Wikipedia verifiability with AI.
A soft-packaged and portable rehabilitation glove capable of closed-loop fine motor skills.
A taxonomy and review of generalization research in NLP.
Unlocking biomolecular intelligence.
Testing the limits of natural language models for predicting human language judgements.
From attribution maps to human-understandable explanations through Concept Relevance Propagation.
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling.
Seeking a quantum advantage for machine learning.
Taking ethics seriously in AV trajectory planning algorithms.
The TRIPOD-P reporting guideline for improving the integrity and transparency of predictive analytics in healthcare through study protocols.
Activity–weight duality in feed-forward neural networks reveals two co-determinants for generalization.
Identifying important sensory feedback for learning locomotion skills.
Language models and linguistic theories beyond words.
Addressing the harms of AI-generated inauthentic content.
Uncertainty-guided dual-views for semi-supervised volumetric medical image segmentation.
Hypergraph factorization for multi-tissue gene expression imputation.
Encoding physics to learn reaction–diffusion processes.
Self-correcting quantum many-body control using reinforcement learning with tensor networks.
Reusability report: Evaluating reproducibility and reusability of a fine-tuned model to predict drug response in cancer patient samples.
Federated benchmarking of medical artificial intelligence with MedPerf.
Publisher Correction: A neural machine code and programming framework for the reservoir computer.
A touch of virtual reality.
Judging the creative prowess of AI.
Why the European AI Act transparency obligation is insufficient.
How can LLMs transform the robotic design process?
The incentive gap in data work in the era of large models.
A 'programming' framework for recurrent neural networks.
A neural machine code and programming framework for the reservoir computer.
A super-resolution strategy for mass spectrometry imaging via transfer learning.
Morphological flexibility in robotic systems through physical polygon meshing.
Writing the rules in AI-assisted writing.
Generative AI entails a credit–blame asymmetry.
Ethical hazards of health data governance in the metaverse.
Geometric deep learning of particle motion by MAGIK.
Adversarial competition and collusion in algorithmic markets.
Recurrent graph optimal transport for learning 3D flow motion in particle tracking.
Accurate online training of dynamical spiking neural networks through Forward Propagation Through Time.