Volume 7 Issue 10, October 2025

Most policy proposals aimed at managing the risks of artificial intelligence (AI)-enabled weapons rely heavily on meaningful human control or appropriate human judgment for risk mitigation. This Comment argues that there are various ways humans can exert such control over AI, and that developing a careful taxonomy of these is necessary for building actionable risk-mitigation policies for warfighting AI.

Designing and optimizing proteins by mutagenesis suffers from the overwhelming space of possible variants. A recent study developed µProtein, a reinforcement learning model coupled with a protein language model as a surrogate oracle, to accelerate this process towards high-functioning proteins.

Molecular dynamics (MD) simulations are widely used for understanding atomic motion but require substantial computational time. In new research by Nam et al., a generative artificial intelligence framework is developed to accelerate the MD simulations for crystalline materials, by reframing the task as conditional generation of atomic displacement.

Although it is possible to use deep learning models to predict static protein conformations from sequencing data, proteins are not static biochemical artefacts. ItsFlexible is a graph-based deep learning tool that is trained on a new dataset of experimentally captured protein motif conformations to classify the dynamic characteristics of proteins.

Irie and Lake present a metalearning framework that enables artificial neural networks to address classic challenges by providing both incentives to improve specific capabilities and opportunities to practice them.

Multimodal AI combines different types of data to improve decision-making in fields such as healthcare and engineering, but work so far has focused on vision and language models. To make these systems more usable in the real world, Liu et al. discuss the need to develop approaches with deployment in mind from the start, working closely with experts across relevant disciplines.

A generative framework that accelerates the simulations of atomic transport in crystalline solids is developed, enabling large-scale screening and extending simulations to larger spatiotemporal scales for energy storage materials.

Choi et al. introduce a machine learning model that integrates diverse multi-view data to predict disease phenotypes. The model includes an interpretable explainer that identifies interacting biological features, such as synergistic genes in astrocytes and microglia associated with Alzheimer’s disease.

Lancelot, a compute-efficient federated learning framework using homomorphic encryption to prevent information leakage, is presented, achieving 20 times faster processing speeds through advanced cryptographic and encrypted sorting techniques.

A sampling-based manifold learning method is proposed to study the cluster structure of high-dimensional data. Its applicability and scalability have been verified in single-cell data analysis and anomaly detection in electrocardiogram signals.

Powerful generative AI models for designing biological macromolecules are being developed, with applications in medicine, biotechnology and materials science, but these models are expensive to train and modify. Leyva et al. introduce the Key-Cutting Machine, an optimization-based platform for proteins and peptides that iteratively leverages structure prediction to match desired backbone geometries.

Jian Ma et al. present HuDiff, a diffusion-based deep learning framework that humanizes antibodies and nanobodies (a small type of antibody) without templates. The model achieves improved humanness while preserving or enhancing binding strength, and the authors show promising results in virus neutralization experiments.

Graber et al. characterize biases and data leakage in protein–ligand datasets and show that a cleanly filtered training–test split leads to improved generalization in binding affinity prediction tasks.

Ying and colleagues present PhyE2E, an AI framework incorporating symbolic search techniques for discovering physics formulas directly from data. The method has already led to improvements in space physics models when compared, for example, with NASA’s 1993 formula for solar activity.

Recurrent neural networks are widely used to model brain dynamics. Tolmachev and Engel show that single-unit activation functions influence task solutions that emerge in trained networks, raising the question of which design choices best align with biology.

ALL-conformations, a dataset capturing the full range of experimentally observed conformations of CDR loops, T cell and antibody regions interacting with antigen targets, is introduced. ITsFlexible—a deep learning tool trained on this new dataset—advances predictions of immune receptor structural dynamics.

The organizers reflect on how a multi-year, multi-country benchmark aligned AI research in road damage detection with practical and regional constraints, steering it towards deployment relevance.