Papers

Electromagnetic resonances play a central role in nanophotonics by enabling efficient confinement of electromagnetic energy and enhanced light-matter interaction. Traditionally, resonant phenomena have been described using platform-specific concepts developed within distinct research communities, including photonic crystals, plasmonics, and dielectric metasurfaces. In this Perspective, we propose a unified framework that distinguishes electromagnetic resonances as eigenmodes of open systems from their experimentally observed manifestations as scattering features. We show how resonances evolve from isolated particles to coupled oligomers and periodic structures, highlighting the roles of geometry, material response, and dimensionality. Particular attention is given to interference-driven phenomena such as bound states in the continuum, lattice resonances, anapoles, and superscattering, some of which cannot always be associated with a single eigenmode. By clarifying the relationship between eigenmodes, scattering channels, and interference effects, this Perspective provides a coherent language for interpreting resonant phenomena and identifies key challenges and opportunities for designing robust resonant photonic systems.

High-quality proton beams generated by laser-plasma interactions are of significant interest for applications ranging from tumor therapy to fast ignition in inertial confinement fusion. However, simultaneously achieving high energy coupling efficiency and beam collimation remains a challenge. In this work, we investigate the enhancement of proton acceleration via geometric confinement in Near-Critical Density (NCD) plasma-filled micro-structured targets using two-dimensional particle-in-cell (PIC) simulations. To optimize laser-to-particle energy transfer, we systematically compared various target configurations, such as rectangular tubes, hybrid funnels, and straight cones. Our results reveals that increasing geometric complexity does not necessarily translate to superior acceleration performance. Instead, the relatively simple NCD-filled straight-cone target outperforms more complex hybrid geometries, achieving a maximum proton cutoff energy of 181.7 MeV and a reduced divergence of approximately $12^{\circ}$ at a laser intensity of $5.5 \times 10^{20}$ W/cm$^2$. This enhancement is attributed to the synergistic effect of relativistic laser self-focusing within the NCD channel and the strong spatial confinement of hot electrons by the conical walls. Furthermore, we identify a unique double-peak structure in the temporal evolution of the electron energy, which serves as a signature of sustained electron refluxing. This refluxing mechanism maintains a robust sheath field over an extended duration, driving the superior acceleration. The proposed target design offers a robust pathway for generating high-flux, high-energy proton beams suitable for next-generation high-repetition-rate laser facilities.

Rydberg-atom electric field sensing has shown great potential from near-DC to THz with state-of-the-art measurement metrics realized in sensitivity, phase extraction, multi-band receptivity, etc. While Rydberg-atom sensors have shown exceptional performance in the GHz regime, low-frequency operation has remained challenging because of electric-field-screening in conventional vapor cells, which suppresses externally applied fields. We overcome this limitation by combining auxiliary modulation and lock-in detection with a paraffin-coated vapor cell, and demonstrate an electrode-free, wideband method for sensing frequencies, ranging from 0.5 Hz to 10 kHz. Our work extends Rydberg-atom sensor range to VLF, ULF, SLF, ELF and sub-ELF frequency bands. In our method, high state-of-the-art sensitivities have been achieved - 819 $\mu$V/cm/$\sqrt{\text{Hz}}$ for 1 Hz, 33 $\mu$V/cm/$\sqrt{\text{Hz}}$ for 10 Hz, 10 $\mu$V/cm/$\sqrt{\text{Hz}}$ for 100 Hz and 2 $\mu$V/cm/$\sqrt{\text{Hz}}$ for 1 kHz.

Collective optical excitations, such as localized surface plasmons in metallic nanoparticles and Mie resonances in high-index dielectrics, play a central role in nanoscale light–matter interactions. When such optical modes interact with electronic transitions in matter under suitable conditions, they can couple strongly, analogous to two coupled harmonic oscillators, forming hybrid light–matter states. In this work, we probe this coupling in core–shell nanoparticles using fast electrons in electron energy-loss (EEL) and cathodoluminescence (CL) spectroscopy. Owing to their highly localized fields, fast electrons can excite modes inaccessible with light-based spectroscopies, including higher-order nonradiative modes, which offer greater field confinement and potentially stronger coupling. Here, we develop an analytical framework to calculate the EEL and CL probabilities for spherical core–shell nanoparticles under aloof and penetrating electron trajectories. This formalism is applied to two representative systems: an excitonic core with a metallic shell, and a silicon core with an excitonic shell. Our main focus is to examine how the electron beam position and velocity affect our ability to probe this coupling. Depending on the electron beam parameters, we find that the spectral signature of strong coupling remains robust in plasmonic nanospheres. In contrast, it can be significantly suppressed or even completely obscured in dielectric nanospheres. Our developed formalism enables a deeper understanding of the coupling mechanisms in electron–light–matter interactions, thereby accelerating progress in single-nanoparticle-based polaritonic studies.

Extreme-event predictability in turbulence is strongly state dependent, yet event-by-event predictability horizons are difficult to quantify without access to governing equations or costly perturbation ensembles. Here we train an autoregressive conditional diffusion model on direct numerical simulations of the two-dimensional Kolmogorov flow and use a CRPS-based skill score to define an event-wise predictability horizon. Enstrophy extremes exhibit a pronounced hierarchy: forecast skill persists from $\approx 1$ to $> 4$ Lyapunov times across events. Spectral filtering shows that these horizons are controlled predominantly by large-scale structures. Extremes are preceded by intense strain cores organizing quadrupolar vortex packets, whose lifetime sharply separates long- from short-horizon events. These results identify coherent-structure persistence as a governing mechanism for the predictability of turbulence extremes and provide a data-driven route to diagnose predictability limits from observations.

Recently proposed analog solvers based on dynamical systems, such as Ising machines, are promising platforms for large-scale combinatorial optimization. Yet, given the heuristic nature of the field, there is very limited insight on optimality guarantees of the solvers, as well as how parameter schedules shape dynamics and outcomes. Here, we develop a dynamical mean-field framework to analyze Ising-machine dynamics for finding the ground state energy of the Sherrington-Kirkpatrick(SK) model of spin glasses and identify mechanisms that enable rapid convergence to provenly near-optimal energies. For a fixed target energy density Ec, we show that solutions are typically reached within O(1) matrix vector multiplications, indicating constant time complexity. We further delineate theoretical limitations arising from different parameter-scheduling trajectories and demonstrate a pronounced benefit of temperature-only annealing for the Coherent Ising Machine. Building on these insights, we propose a general framework for designing optimized parameter schedules, thereby improving the practical effectiveness of Ising machines for complex optimization tasks. The superior performance of the dynamical solvers is illustrated by the attainment of the ground state energy of the SK model.

Symbolic regression is a powerful tool for knowledge discovery, enabling the extraction of interpretable mathematical expressions directly from data. However, conventional symbolic discovery typically follows an end-to-end, "one-step" process, which often generates lengthy and physically meaningless expressions when dealing with real physical systems, leading to poor model generalization. This limitation fundamentally stems from its deviation from the basic path of scientific discovery: physical laws do not exist in a single form but follow a hierarchical and progressive pattern from simplicity to complexity. Motivated by this principle, we propose Chain of Symbolic Regression (CoSR), a novel framework that models the discovery of physical laws as a chain of symbolic knowledge. This knowledge chain is formed by progressively combining multiple knowledge units with clear physical meanings along a specific logic, ultimately enabling the precise discovery of the underlying physical laws from data. CoSR fully recapitulates the progressive discovery path from Kepler's third law to the law of universal gravitation in classical mechanics, and is applied to three types of problems: turbulent Rayleigh-Benard convection, viscous flows in a circular pipe, and laser-metal interaction, demonstrating its ability to improve classical scaling theories. Finally, CoSR showcases its capability to discover new knowledge in the complex engineering problem of aerodynamic coefficients scaling for different aircraft.

Scaling solid-state architectures to the millions of qubits required for utility-scale quantum computing could benefit from the integration of control electronics in the immediate vicinity of the quantum layer. However, lithographically fabricated solid-state qubits perform best at temperatures well below 1 K, where available cooling power is limited, whereas the control electronics dissipate substantial power and therefore require the higher cooling power available at elevated temperatures. To address this challenge, we propose a cryopackaging concept that uses broadband phononic Distributed Bragg Reflectors (DBRs) as a thermal barrier between cryoelectronics and the qubit chip. As an experimental realization of this concept, we fabricate and characterize Ta/SiO$_2$ DBR structures. In this architecture, the DBR is intended to provide mechanical support for superconducting vias while offering substantially better thermal insulation than typical bulk materials. For a 600-nm-thick DBR consisting of 10 Ta/SiO$_2$ bilayers, we obtain a thermal conduction below 1 mW/cm$^2$ from 1.5 K to 100 mK. In a centimeter-scale architecture, this level of isolation is compatible with Watt-level cooling power for nearby electronics while maintaining a qubit temperature around 100 mK in commercially available dilution refrigerators.

Large-scale land enclosure for speculative mega-development constitutes a non-equilibrium spatial process whose velocity, topology, and irreversibility remain poorly quantified. We study the Pantai Indah Kapuk 2 (PIK2) coastal mega-development north of Jakarta, Indonesia, using eight years (2017–2024) of Sentinel-2 land-use/land-cover (LULC) data at 10-meter resolution. The landscape is projected onto a Marxian probability simplex partitioning terrestrial pixels into Commons, Agrarian, and Capital fractions. Fisher-Rao (FR) geodesic distances on this simplex identify a transformation pulse of $0.405$~rad/yr during 2019–2020, coinciding with major construction activity. Absorbing Markov chain analysis yields expected absorption times into the built environment of $46.0$~years for cropland and $38.1$~years for tree cover, with a pooled built-area self-retention rate of $96.4\%$. Percolation analysis reveals that a giant connected component containing $89$–$95\%$ of all built pixels persists at occupation probabilities $p \in [0.096, 0.162]$, far below the random percolation threshold $p_c \approx 0.593$, indicating planned rather than stochastic spatial growth. The box-counting fractal dimension of the urban boundary increases from $d_f = 1.316$ to $1.397$, consistent with increasingly irregular frontier expansion. These results suggest that information-geometric and statistical-mechanical tools can characterize the kinematic and topological signatures of capitalist spatial accumulation with quantitative precision.

Hydroxide ion transport in anion-exchange membranes fundamentally limits the efficiency of alkaline water electrolysis for green hydrogen production, yet the atomic-scale transport mechanisms remain poorly understood due to the computational challenges associated with modeling ion dynamics. Given that anion-exchange membranes enable alkaline electrolysis with abundant catalysts while avoiding perfluoroalkyl and polyfluoroalkyl materials, a deeper mechanistic understanding of hydroxide transport in these systems is essential for advancing sustainable hydrogen production. Here, we show that large-scale molecular dynamics simulations with fine-tuned machine-learned interatomic potentials provide atomistic insight into hydroxide mobility in a commercial membrane over tens of nanoseconds and over ten nanometer. We find that increasing water content transforms isolated water clusters into a connected hydrogen-bond network that enables long-range proton transfer. Under dry conditions hydroxide ions are trapped near positively charged groups and transport is strongly hindered, whereas well-hydrated membranes exhibit extended proton migration and diffusion coefficients approaching those of dilute aqueous solutions. The simulations reproduce experimental trends in diffusion and activation energies. Our results establish a direct link between nano-scale structure and macroscopic transport. Beyond mechanistic insight, the presented simulation framework enables predictive, simulation-guided optimization of membrane chemistry and architecture, opening a pathway toward the rational design of more efficient anion-exchange membranes for green hydrogen technologies.

A high-resolution Eulerian method for simulating high-speed polydisperse granular multiphase flows has been developed. The governing equations include a compressible gas that is coupled to mass-based moment equations for a polydisperse granular flow derived from the generalized population balance equation. The model includes effects from particle collisions, drag, convective heat transfer, particle-fluid-particle pressure, and finite-size particle force terms. The mass moment integrals are closed using the generalized quadrature method of moments to allow for continuous size distributions. The governing equations are solved by using high-resolution reconstruction schemes and results from decoupled Riemann problems for the gas and particles as each quadrature node. Success of the technique is demonstrated through a variety of numerical experiments including polydisperse multiphase Riemann shock-tube problems, shock–particle-curtain interactions, dust layer dispersal, dust layer dispersal by shock waves, and dispersal of spherical particle shells by high-pressure gas.

Quantum systems inside high-Q cavities offer an excellent testbed for the control of emergent symmetries induced by light and their interplay with quantum matter. Recently several developments in cavity experiments with neutral atoms and other quantum objects such as ions motivate the study of their quantum correlated properties and their entanglement to tailor and control the behavior of the system. Using the enhanced coupling between light and interacting matter we explore the properties of emergent superradiant modes using our newly developed Light-Matter DMRG algorithm with strongly interacting spin chains. We explore a experimentally viable generalization of the transverse Ising chain coupled to the cavity light where it is possible to induce multimode structures tailored by the light pumped into the system. We find a plethora of scenarios can be explored with clear and accesible measurable signatures. This allows to study the physics of emergent orders and strong quantum correlations with quantum spins where the local and long range coupling can be efficiently simulated. We find that quantum spin nematic states with long range order and magnon pairs emerge as the transitions to superradiant phases take place. Notably, we show the cavity field allows the optimization of entanglement between spins for different light induced modes which can be used for quantum state engineering of quantum correlated states. Our methods can be used to model other hybrid quantum systems efficiently.

Murray's cubic branching law ($\alpha=3$) predicts a universal diameter scaling exponent for all hierarchical transport networks, yet arterial trees yield $\alpha \sim 2.7-2.9$. We show that this discrepancy has a structural origin: Murray's universality is an artifact of cost homogeneity, not a biological property. Incorporating the empirical vessel-wall thickness law $h(r)=c_0 r^p$ ($p \approx 0.77$) introduces a third metabolic cost term $\propto r^{1+p}$ that renders the cost function inhomogeneous with incommensurate scaling exponents. By Cauchy's functional equation, homogeneity is necessary and sufficient for a universal branching exponent to exist; its absence implies non-universality, and Murray's law is identified as a singular degeneracy of the cost-function family rather than a general principle. We prove that the resulting scale-dependent exponent satisfies the strict bounds $(5+p)/2 < \alpha^*(Q) < 3$ independently of flow asymmetry (Theorem 4, Corollary 5). The static wall-tissue mechanism bounds the symmetric bifurcation exponent to $\alpha_t \in [2.90, 2.94]$ from measured parameters, marking a first-order symmetry breaking from Murray's law that narrows the empirical gap by one-third. The remaining discrepancy with the cardiovascular mean ($\alpha_{exp} \approx 2.70$) is not a model failure but a mathematical necessity that signals the independent contribution of pulsatile wave dynamics. Additionally, the wall cost breaks Murray's topological degeneracy, bounding the optimal branching number to small finite integers; binary bifurcation emerges as the physiologically selected minimum under steric constraints.

In this work, we propose an unsupervised domain adaptation (UDA) framework for 3D volumetric lesion detection that adapts a detector trained on labeled FDG PET/CT to unlabeled PSMA PET/CT. Beyond covariate shift, cross tracer adaptation also exhibits label shift in both lesion size composition and the number of lesions per subject. We introduce self-training with two mechanisms that explicitly model and compensate for this label shift. First, we adaptively adjust the detection anchor shapes by re-estimating target domain box scales from selected pseudo labels and updating anchors with an exponential moving average. This increases positive anchor coverage for small PSMA lesions and stabilizes box regression. Second, instead of a fixed confidence threshold for pseudo-label selection, we allocate size bin-wise quotas according to the estimated target domain histogram over lesion volumes. The self-training alternates between supervised learning with prior-guided pseudo labeling on PSMA and supervised learning on labeled FDG. On AutoPET 2024, adapting from 501 labeled FDG studies to 369 $^{18}$F-PSMA studies, the proposed method improves both AP and FROC over the source-only baseline and conventional self-training without label-shift mitigation, indicating that modeling target lesion prevalence and size composition is an effective path to robust cross-tracer detection.

We explore the capabilities of Large Language Models (LLMs) by comparing the way they gather data with the way humans build knowledge. Here we examine how scientific knowledge is made and compare it with LLMs. The argument is structured by reference to two figures, one representing scientific knowledge and the other LLMs. In a 2014 study, scientists explain how they choose to ignore a 'fringe science' paper in the domain of gravitational wave physics: the decisions are made largely as a result of tacit knowledge built up in social discourse, most spoken discourse, within closed groups of experts. It is argued that LLMs cannot or do not currently access such discourse, but it is typical of the early formation of scientific knowledge. LLMs 'understanding' builds on written literatures and is therefore insecure in the case of the initial stages of knowledge building. We refer to Colin Fraser's 'Dumb Monty Hall problem' where in 2023 ChatGPT failed though a year later or so later LLMs were succeeding. We argue that this is not a matter of improvement in LLMs ability to reason but in the change in the body of human written discourse on which they can draw (or changes being put in by humans 'by hand'). We then invent a new Monty Hall prompt and compare the responses of a panel of LLMs and a panel of humans: they are starkly different but we explain that the previous mechanisms will soon allow the LLMs to align themselves to humans once more. Finally, we look at 'overshadowing' where a settled body of discourse becomes so dominant that LLMs fail to respond to small variations in prompts which render the old answers nonsensical. The 'intelligence' we argue is in the humans not the LLMs

A dichroic dual-angle refractor based on a 2D Huygens' metasurface model is treated by means of resonant-circuit approximations of multiple cells. The whole parameter space of refraction angles is tested for the analytic approximations involved, whereas the realised refraction guides the choice of optimal such angles. Our results indicate the possibility of sythesising a rectangular array of a number of cells which eventually depends on the low-frequency band diffraction limit. Aberrations from the ideal performance are also examined and attributed to certain approximation caveats.

I present a reanalysis of temperature data from a publicly available certified laboratory report that documented the self-discharging behavior of an energy-storage device during 10 days. Graphs of temperature variations of both the tested device itself and the test chamber (fume hood) were given mainly for monitoring without further analysis, and variations in the ambient temperature signal were attributed to "other cells being cycled simultaneously in the same fume hood". I show that the ambient temperature signal alone – together with some quite mild and reasonable assumptions – allow to extract previously unpublished information on the simultaneously run test on the other cells: 1) the number of charge/discharge cycles 2) the cycle period, 3) the charge/discharge half-cycle asymmetry, and – most significantly – evidence that 4) the mentioned "other device" completed 338 full charge/discharge cycles at 3C rate at room temperature without any detectable thermal degradation signature.

Certain radiation detectors are 'paralyzed' with high input count rates. When applied to count rates close to the event discriminator working rate the one-parameter dead time model fails. Here we present a corrected paralyzable detector model accounting for the event discriminator's finite response time. This two-parameter analytical model, when compared to the experimental data from a commercial x-ray detector, gives an improved description of the input and output count rate relations. Furthermore, it can independently determine the discriminator response time and the pulse shaper dead time, critical parameters for understanding a detector's performance. Finally, this model also provides a post-acquisition pile-up correction that greatly reduces artifacts in high-throughput spectra. In some situations, applying this model to optimize the acquisition and post-acquisition correction allows a user to acquire data an order of magnitude faster without compromising accuracy.

We propose a joint TDC and multi-time-gated imaging single-photon avalanche diode LiDAR sensor featuring a maximum detection range of 108m with a minimum depth resolution (least significant bit) of 2.93mm, fabricated in 110nm CMOS technology. The sensor is implemented 320x240 pixels with a pitch of 23{\mu}m, achieving a maximum fill factor of 10% and a total size of 8.2mmx6.3mm. The power consumption of the pixel array is 167.4mW. Under a repetition rate of 3.125MHz, a laser power of 11.3mW, and a wavelength of 780nm, the sensor is designed to operate at up to 100klx background illumination with a centimetric depth precision. It can be further improved to 130klx by reducing image resolution to 160x120 pixels. In addition, the sensor can reconfigure the idle TSPCs integrated in the cluster into counters for histogramming, thereby reducing the size of the data processing module.

Density functional theory (DFT) is a cornerstone of computational chemistry and materials science, but its computational cost limits its use in large-scale and high-throughput applications. While machine learning has accelerated energy prediction for specific molecular classes, transferable prediction of electron density across diverse chemical spaces remains challenging. Here, we present a universal framework based on Fourier Neural Operators (FNOs) that directly learns the mapping from external potentials to electron density distributions. Unlike conventional approaches that rely on explicit atomic orbitals, basis sets, or handcrafted descriptors, the proposed method captures global electronic interactions and long-range correlations through operator learning in the spatial-frequency domain. Trained on datasets spanning multiple elements and molecular geometries, the model achieves zero-shot generalization to entirely unseen molecular systems and accurately predicts their electron densities without retraining. This transferability arises from the intrinsic ability of FNOs to represent global structure in continuous fields. Our work establishes neural operator learning as a promising route for fast, accurate, and transferable electronic structure prediction, with potential applications in high-throughput screening and chemical space exploration.

Flow instabilities such as Haines jumps in porous media are common phenomena that occur on sub-second timescales. X-rays are particularly suitable for investigating these processes because they provide non-destructive three-dimensional insight into the network structure and the liquid distribution within porous media. Studying imbibition events in four dimensions (three spatial dimensions plus time) is inherently challenging with conventional tomography because the required rapid sample rotation imposes significant centrifugal forces that alter the flow. Here, we demonstrate synchrotron X-ray multi-projection imaging (XMPI) to capture four-dimensional flow in an additively manufactured, homogeneous spherical pore network at 1.3 $\mu$m effective pixel size and 50 Hz temporal resolution without the need for high rotational speeds. This enables in situ visualization of non-repeatable pore-scale events in both space and time, a capability unachievable with classical X-ray tomographic approaches. We compare the results to Shan-Chen multiphase Lattice Boltzmann simulations performed on the same geometry, finding both qualitative agreements and systematic differences in filling sequences and timescales. These discrepancies expose key limitations of current simulation methods in representing contact-line dynamics and realistic boundary conditions limitations that XMPI can directly overcome. By enabling high-resolution, real-time imaging of flow instabilities in opaque porous media, synchrotron XMPI provides a unique platform that bridges the gap between pore-scale experiments and simulations.

Reduced graphene oxide (rGO) exhibits strong anisotropic light absorption and high compatibility with photonic integrated chips, making it a promising material for implementing high performance onchip polarization selective devices. The performance of rGO integrated waveguide polarizers is highly dependent on the waveguide geometry, and achieving optimal performance requires exploring a large parameter space, making conventional mode simulation methods computationally demanding. Here, we propose and demonstrate a machine learning framework based on fully connected neural networks (FCNNs) to map the dependence of the polarizer figure of merit (FOM) on the waveguide geometry. Once trained by using a small dataset of low resolution mode simulation results, the FCNN framework can rapidly and accurately predict FOM values across a large structural parameter space with high resolution. Results show that this method can reduce overall computing time by more than 4 orders of magnitude as compared to the mode simulation methods, and achieve high prediction accuracy with an average deviation (AD) below 0.05. These results highlight the FCNN based machine learning framework as an efficient tool for the design and optimization of rGO integrated waveguide polarizers.

We introduce the Seismic Waveforms dataset for Automatic Neural-network processing (SWAN), a comprehensive and standardized benchmark designed to advance data-driven seismic signal processing. SWAN aggregates diverse synthetic and real seismic waveforms spanning a wide range of geological structures, noise conditions, propagation environments, and acquisition geometries, providing a unified foundation for training highly generalizable models. Leveraging this dataset, we develop and evaluate a conditionally constrained residual diffusion model for core seismic processing tasks, focusing on missing-trace reconstruction. Extensive experiments demonstrate that diffusion models trained on SWAN achieve state-of-the-art performance across heterogeneous testing scenarios, outperforming leading deep-learning and physics-based baselines on both synthetic benchmarks and field data examples. The results highlight SWAN's value as both a scalable training corpus and a rigorous evaluation framework, and illustrate the strong potential of diffusion-based architectures for robust, generalizable seismic data processing.

Paleo-detectors are a proposed experimental technique for direct detection (DD) of dark matter (DM) via the read-out of DM-induced nuclear recoil tracks in natural minerals. The large detector mass required for the sensitivity of conventional DD experiments to rare events is replaced by the exposure of paleo-detectors to DM-induced nuclear recoils over geological timescales. In this paper, we extend previous theoretical predictions for canonical spin-independent coherent and spin-dependent scattering (proportional to $A^2$ and the spin of the nucleus, respectively). We estimate the sensitivity of paleo-detectors to interactions between weakly interacting massive particle (WIMP) DM and nuclei within the framework of a Non-Relativistic Effective Field Theory (NREFT), considering isoscalar couplings to nucleons for both elastic and inelastic scattering. Taking into account cosmogenic, astrophysical and radiogenic backgrounds, we project the 90% confidence-level (CL) upper limits on the isoscalar NREFT coupling constants for both scattering types. We consider representative read-out scenarios and examine several target minerals. The projected sensitivities of paleo-detectors are compared with the 90% CL limits from the XENON100, LUX-ZEPLIN, and PandaX-II experiments, as well as with the 95% Bayesian credible region of the 2D marginalized posterior distribution from SuperCDMS. For DM masses from 1 GeV-10 GeV, paleo-detectors are projected to have sensitivity superior to that of conventional experiments for WIMP-nucleus interactions via all NREFT operators, largely independent of read-out scenario or target mineral. For DM masses from 10 GeV-5 TeV, we find that the sensitivity of paleo-detectors is projected to be comparable to or better than that of conventional experiments for WIMP-nucleus interactions via several NREFT operators, depending on the read-out scenario and target mineral.

This paper presents novel refinement sensors for the application to adaptive mesh and algorithm refinement (AMAR) with kinetic models, such as discrete velocity and lattice Boltzmann methods. While refinement criteria for AMAR based on macroscopic variables can be replicated in a purely local, and therefore more scalable, way, the main advantage that can be leveraged when working with discrete velocity and lattice Boltzmann methods is the accessibility of information from the one-particle distribution function. With this accessibility, a novel palette of refinement sensors is introduced, allowing for a set of neatly tailored refinement criteria applicable to resolve characteristic flows features in many relevant domains of fluid mechanics, for instance, those emerging in compressible, turbulent, and non-equilibrium flows or non-ideal fluids. After detailed validation, novel refinement sensors are showcased for the application of adaptive mesh refinement (AMR) to a discrete velocity Boltzmann solver for compressible, viscous, and non-equilibrium flows, demonstrating promising results. The proposed sensors establish an accurate, efficient and scalable approach to kinetic simulations with AMAR, offering a valuable tool for studying complex problems in fluid dynamics and paving the way for future extensions to more specific flow problems.

Alzheimer's disease involves progressive tau accumulation and spread, leading to regional brain atrophy and disruption of large-scale functional networks. While tau propagation and tissue degeneration have been widely modeled, how atrophy dynamics translate into functional connectivity (FC) degradation remains unclear. Here, we develop a multiphysics framework integrating anisotropic tau reaction-diffusion, finite-deformation biomechanics, and network modeling to link tau-driven atrophy with FC changes. Model fidelity is evaluated by quantitatively comparing simulated atrophy patterns with imaging-derived measurements. Using longitudinal structural and functional MRI, we identify an approximately linear relationship between regional atrophy rates and FC change. We then construct an atrophy-informed structural network degradation matrix from model-predicted region-specific atrophy rates and embed it into a neural oscillation model to predict FC disruption. Our results show that (i) the coupled reaction-diffusion-biomechanical model reproduces observed regional atrophy, (ii) regional atrophy rates parsimoniously predict longitudinal FC changes, and (iii) the atrophy-informed degradation matrix captures the direction and relative magnitude of regional FC disruption. By converting tau-driven atrophy into predictive FC trajectories, the proposed framework offers a clinically interpretable avenue for forecasting disease progression and informing trial design.

Spin-orbit beams, in which the orbital angular momentum degree of freedom is coupled to a two-level system such as polarization of light or spin in electrons and neutrons, have gained significant interest for their unique propagation properties and potential applications in imaging, material characterization, optical trapping, and quantum information processing. In this work we introduce a method for generating and engineering two-dimensional lattices of such spin-orbit beams based on coherent averaging in k-space. By programming the angle, amplitude, and polarization of a set of input beams we obtain precise control over lattice geometry and period, as well as the orbital and radial degrees of freedom inside each unit cell. We explore both electromagnetic and matter wave implementations, and we experimentally demonstrate the generation and characterization of a micron-scale optical hexagonal lattice with well defined orbital and radial numbers in each unit cell. The described methods provide a robust and general method of generating and controlling structured waves such as optical skyrmions and matter wave implementations of orbit and spin-orbit beams.

A key challenge for molecular dynamics simulations is efficient exploration of free energy landscapes over relevant collective variables (CV). Common methods for enhancing sampling become prohibitively inefficient beyond only a few CVs; in the case of the widely-used metadynamics method, the computational cost of evaluating and storing the bias potential grows exponentially with the number of dimensions. Here, we introduce TT-Metadynamics, in which the accumulated sum of Gaussian functions in the original metadynamics method is periodically compressed into a low-rank tensor train (TT) representation. The TT enables efficient memory use and prevents the computational cost of evaluating the bias potential from increasing with simulation time. We present a "sketching" algorithm that allows us to construct the TT with linear scaling in the number of CVs. Applied to benchmark systems with up to 14 CVs, the accuracy of TT-Metadynamics matches or exceeds that of standard metadynamics in long simulations, particularly in systems with high barriers. These results establish TT-Metadynamics as a scalable and effective method for computing free energies that are functions of several CVs.

Internal waves, or waves that propagate within a stratified fluid, may break and cause mixing. While each individual mixing event may be small, collectively, internal wave breaking drive processes in the ocean that are critical to understanding the maritime climate and biosphere. In this paper we show how to set up an experiment, suitable for an undergraduate-level lab, that illustrates a common generation and breaking mechanism in the ocean. In particular, we show how the process changes in response to a non dimensional parameter, the buoyancy Reynolds number, that can be easily varied. This parameter highlights the role of viscous vs. inertial/buoyancy forces. We outline our methods of creating a linear stratification, injecting energy with a forced topography, and analyzing the resulting dynamics with Background Oriented Schlieren and energy spectra from a conductivity probe. By altering our forcing to accommodate three values of the buoyancy Reynolds, three distinct internal wave regimes can be observed: no turbulence, slight turbulence, and extreme turbulence. Our methods aim to increase the accessibility to studying these internal waves in future experimental work, ocean modeling, and math and physics undergraduate learning.

Computationally expensive, high-accuracy detector simulations are a major bottleneck for many particle physics experiments such as those at the Large Hadron Collider (LHC) as well as those planned for future colliders. This challenge has motivated the development of fast generative machine learning based surrogates. We present a hardware-aware variational autoencoder model for fast calorimeter simulation that is designed specifically for field programmable gate array (FPGA) deployment, offering faster and lower power inference capability. Quantization aware training and other compression techniques are applied to respect the resource constraints of a single FPGA. The synthesized implementation of the VAE decoder achieves sub-millisecond latency, resulting in a substantial speed up compared to a traditional GPU implementation with only a small performance drop. This feasibility study demonstrates the potential of utilizing existing FPGA architecture at the LHC and other facilities for efficient offline computing using online resources.