Contemporary quantum devices are reaching new limits in size and complexity, allowing for the experimental exploration of emergent quantum modes. However, this increased complexity introduces significant challenges in device tuning and control. Here, we demonstrate autonomous tuning of emergent Poor Man’s Majorana zero modes in a minimal realization of a Kitaev chain. We achieve this task using cross-platform transfer learning. First, we train a tuning model on a theory model. Next, we retrain it using a Kitaev chain realization in a two-dimensional electron gas. Finally, we apply this model to tune a Kitaev chain realized in quantum dots coupled through a semiconductor-superconductor section in a one-dimensional nanowire. Utilizing a convolutional neural network, we predict the tunneling and Cooper pair splitting rates from differential conductance measurements, employing these predictions to adjust the electrochemical potential to a Poor Man’s Majorana sweet spot. The algorithm successfully converges to an immediate vicinity of a sweet spot (within $\pm 1.5\mathrm{m}\mathrm{V}$ in 67.6% of attempts and within $\pm 4.5\mathrm{m}\mathrm{V}$ in 80.9% of cases), typically finding a sweet spot in 45 min or less. This advancement is a stepping stone toward autonomous tuning of emergent modes in interacting systems, and toward foundational tuning machine learning models that can be deployed across a range of experimental platforms.

We propose a clustering approach for point cloud segmentation based on supervised contrastive metric learning (CML). Rather than predicting cluster assignments or object-centric variables, the method learns a latent representation in which points belonging to the same object are embedded nearby, while unrelated points are separated. Clusters are then reconstructed using a density-based readout in the learned metric space, decoupling representation learning from cluster formation and enabling flexible inference. The approach is evaluated on simulated data from a highly granular calorimeter, where the task is to separate highly overlapping particle showers represented as sets of calorimeter hits. A direct comparison with object condensation (OC) is performed using identical graph neural network backbones and equal latent dimensionality, isolating the effect of the learning objective. The CML method produces a more stable and separable embedding geometry for both electromagnetic and hadronic particle showers, leading to improved local neighborhood consistency, a more reliable separation of overlapping showers, and better generalization when extrapolating to unseen multiplicities and energies. This translates directly into higher reconstruction efficiency and purity, particularly in high-multiplicity regimes, as well as improved energy resolution. In mixed-particle environments, CML maintains strong performance, suggesting stable learning of the shower topology across particle types, while OC exhibits significant degradation. These results demonstrate that similarity-based representation learning combined with density-based aggregation is a promising alternative to object-centric approaches for point cloud segmentation in highly granular detectors.

van der Waals (vdW) interactions are essential for describing molecules and materials, from drug design and catalysis to battery applications. These omnipresent interactions must also be accurately included in machine-learned (ML) force fields. The many-body dispersion (MBD) method stands out as one of the most accurate and transferable approaches to capture vdW interactions, requiring only atomic $C_6$ coefficients and polarizabilities as input. We present MBD-ML, a pretrained message-passing neural network that predicts these atomic properties directly from structures with demonstrated transferability across molecular systems and organic condensed phases. Through seamless integration with libMBD, our method enables the immediate calculation of MBD-inclusive total energies, forces, and stress tensors. By eliminating the need for intermediate electronic-structure calculations, MBD-ML offers a practical and streamlined tool that simplifies the incorporation of state-of-the-art vdW interactions into any electronic-structure code, as well as empirical and machine-learned force fields.

Neural quantum states (NQS) have gained prominence in variational quantum Monte Carlo methods in approximating ground-state wavefunctions. Despite their success, they face limitations in optimization, scalability, and expressivity in addressing certain problems. In this work, we propose a quantum-neural hybrid framework that combines parametrized quantum circuits with neural networks to model quantum many-body wavefunctions. This approach combines the efficient sampling and optimization capabilities of autoregressive neural networks with the enhanced expressivity provided by quantum circuits. Numerical simulations demonstrate the scalability and accuracy of the hybrid ansatz in spin systems and quantum chemistry problems. Our results reveal that the hybrid method achieves notably lower relative energy compared to stand-alone NQS. These findings underscore the potential of quantum-neural hybrid methods for tackling challenging problems in quantum many-body simulations.

Simulations of quantum matter rely mainly on Kohn-Sham density functional theory (DFT), which often fails for strongly correlated systems. Quantum embedding (QE) theories address this limitation by mapping the system onto an auxiliary embedding Hamiltonian (EH) describing fragment-environment interactions, but the EH is typically large and its iterative solution is the primary computational bottleneck. We introduce a linear foundation model for QE that utilizes principal component analysis to compress the space of quantum states needed to solve the EH within a small variational subspace. Using a data-driven active-learning scheme, we learn this subspace from EH ground states and reduce each embedding solution to a deterministic ground-state eigenvalue problem in the reduced space. Within the ghost-Gutzwiller approximation, we show for a three-orbital Hubbard model that a variational space learned on a Bethe lattice is transferable to square and cubic lattices without additional training, while substantially reducing the cost of the EH step. We further validate the approach on plutonium, where a single variational space reproduces the energetics of all six crystalline phases while reducing the cost of the EH solution by orders of magnitude. This provides a practical route to overcome the main computational bottleneck of QE frameworks, paving the way for high-throughput ab initio simulations of strongly correlated materials at a near-DFT cost.

We present the vision, scope, and editorial philosophy of PRX Intelligence, a selective, fully open access journal at the intersection of artificial intelligence, machine learning, and the physical sciences. We reflect on the transformational role of artificial intelligence as an emerging paradigm of science, examine its implications for scientific understanding and practice, and outline editorial standards that will guide this venue as a home for rigorous and impactful research.