Search

The increasing shortage of nursing staff and the acute risk of falls in nursing homes pose significant challenges for the healthcare system. This study presents the development of an automated fall detection system integrated into care beds, aimed at enhancing patient safety without compromising privacy through wearables or video monitoring. Mechanical vibrations transmitted through the bed frame are processed using a short-time Fourier transform, enabling robust classification of distinct human fall patterns with a convolutional neural network. Challenges pertaining to the quantity and diversity of the data are addressed, proposing the generation of additional data with a specific emphasis on enhancing variation. While the model shows promising results in distinguishing fall events from noise using lab data, further testing in real-world environments is recommended for validation and improvement. Despite limited available data, the proposed system shows the potential for an accurate and rapid response to falls, mitigating health implications, and addressing the needs of an aging population. This case study was performed as part of the ZIM Project. Further research on sensors enhanced by artificial intelligence will be continued in the ShapeFuture Project.

Gallenene is a promising low-dimensional material with a structure down to the thickness of a single atom, similar to graphene. However, van der Waals stacking of two-dimensional (2D) gallenene under confinement remain poorly understood. In this study, we present evidence of the formation of parallel-stacked hexagonal gallenene (a100) structures in liquid gallium. The present study demonstrates the AB stacking of 2D gallenene a100 crystals in liquid gallium sandwiched between two graphene layers, as observed through transmission electron microscopy. A nonlinear optical response of the confined hexagonal gallenene was investigated through second harmonic generation (SHG) microscopy. The SHG signal exhibits periodic peak intensity shifts upon angular rotation up to 90 degrees and intensity dampening at elevated temperatures. These findings offer insights on device applications of 2D gallenene., Comment: 14 pages and 5 figures

We study a system of three bosons interacting with short-range potentials which can move along three different lines. Two of these lines are parallel to each other within one plane. The third line is constrained to a plane perpendicular to the first one. Recently it was predicted in physics literature that such a system exhibits the so-called confinement induced Efimov effect. We prove that this prediction is not correct by showing that this system has at most finitely many bound-states.

Scientists and engineers use simulators to model empirically observed phenomena. However, tuning the parameters of a simulator to ensure its outputs match observed data presents a significant challenge. Simulation-based inference (SBI) addresses this by enabling Bayesian inference for simulators, identifying parameters that match observed data and align with prior knowledge. Unlike traditional Bayesian inference, SBI only needs access to simulations from the model and does not require evaluations of the likelihood-function. In addition, SBI algorithms do not require gradients through the simulator, allow for massive parallelization of simulations, and can perform inference for different observations without further simulations or training, thereby amortizing inference. Over the past years, we have developed, maintained, and extended $\texttt{sbi}$, a PyTorch-based package that implements Bayesian SBI algorithms based on neural networks. The $\texttt{sbi}$ toolkit implements a wide range of inference methods, neural network architectures, sampling methods, and diagnostic tools. In addition, it provides well-tested default settings but also offers flexibility to fully customize every step of the simulation-based inference workflow. Taken together, the $\texttt{sbi}$ toolkit enables scientists and engineers to apply state-of-the-art SBI methods to black-box simulators, opening up new possibilities for aligning simulations with empirically observed data.

Ordered binary decision diagrams (OBDDs) are a fundamental data structure for the manipulation of Boolean functions, with strong applications to finite-state symbolic model checking. OBDDs allow for efficient algorithms using top-down dynamic programming. From an automata-theoretic perspective, OBDDs essentially are minimal deterministic finite automata recognizing languages whose words have a fixed length (the arity of the Boolean function). We introduce weakly acyclic diagrams (WADs), a generalization of OBDDs that maintains their algorithmic advantages, but can also represent infinite languages. We develop the theory of WADs and show that they can be used for symbolic model checking of various models of infinite-state systems.

Acoustic emission signals have been shown to accompany avalanche-like events in materials, such as dislocation avalanches in crystalline solids, collapse of voids in porous matter or domain wall movement in ferroics. The data provided by acoustic emission measurements is tremendously rich, but it is rather challenging to precisely connect it to the characteristics of the triggering avalanche. In our work we propose a machine learning based method with which one can infer microscopic details of dislocation avalanches in micropillar compression tests from merely acoustic emission data. As it is demonstrated in the paper, this approach is suitable for the prediction of the force-time response as it can provide outstanding prediction for the temporal location of avalanches and can also predict the magnitude of individual deformation events. Various descriptors (including frequency dependent and independent ones) are utilised in our machine learning approach and their importance in the prediction is analysed. The transferability of the method to other specimen sizes is also demonstrated and the possible application in more generic settings is discussed.

The success of embolisation, a minimally invasive treatment of liver cancer, could be evaluated in the operational room with cone-beam CT by acquiring a dynamic perfusion scan. The reconstruction algorithm must address the issues of low temporal sampling and higher noise levels inherent in cone-beam CT systems, compared to conventional CT. Therefore, a model-based perfusion reconstruction based on the time separation technique (TST) was applied. TST uses basis functions to model time attenuation curves. These functions are either analytical or based on prior knowledge, extracted using singular value decomposition from CT perfusion data. To explore how well the prior knowledge can model perfusion dynamics and what the potential limitations are, the dynamic CBCT perfusion scan was simulated under different noise levels. The TST method was compared to static reconstruction. It was demonstrated that a set consisting of only four basis functions results in perfusion maps that preserve relevant information, denoises the data, and outperforms static reconstruction under higher noise levels. TST with prior knowledge would not only outperform static reconstruction, but also the TST with analytical basis functions. Furthermore, it has been shown that only eight CBCT rotations, unlike previously assumed ten, are sufficient to obtain the perfusion maps comparable to the reference CT perfusion maps. This contributes to saving dose and reconstruction time. The real dynamic CBCT perfusion scan, reconstructed under the same conditions as the simulated scan, shows potential for maintaining the accuracy of the perfusion maps. By visual inspection, the embolised region was matching to that in corresponding CT perfusion maps. Further analysis of a larger cohort of patient data is needed to draw final conclusions regarding the expected advantages of the time separation technique., Comment: 28 pages, 11 figures

It is known that in an unbounded fluid, the inline configuration of a freely rising bubble pair is often unstable with respect to lateral disturbances. This work numerically examines the stability of this configuration in the presence of a nearby vertical wall. The focus is on moderately inertial regimes, where two bubbles rising initially in line typically separate laterally from each other under unbounded conditions. In the presence of the wall, our results indicate that while the path of the bubble pair predominantly separates laterally, the plane of separation largely depends on the wall bubble interaction. This interaction involves a competition between two distinct effects, with the dominance determined by the ratios of buoyancy to viscous and buoyancy to capillary forces, which define the Galilei (Ga) and Bond (Bo) numbers, respectively. When Bo is below a critical Ga-dependent threshold, irrotational effects dominate, initially stabilizing both bubbles near the wall until horizontal separation among them occurs in the wall parallel plane. Conversely, at higher Bo, vortical effects dominate such that both bubbles migrate away from the wall. During the departure, asymmetric interactions cause the wall normal velocities of the two bubbles to differ, leading to horizontal separation in the wall-normal plane. These two separation motions, both newly identified in the present study, are found to result from two distinct mechanisms: one associated with the shear flow generated in the gap separating the wall and the leading bubble, which attracts the trailing bubble toward the wall, and the other linked to vortex shedding from the leading bubble, which promotes the trailing bubble's faster escape from the wall.

We propose an information-theoretic framework to measure narratives, providing a formalism to understand pivotal moments, cliffhangers, and plot twists. This approach offers creatives and AI researchers tools to analyse and benchmark human- and AI-created stories. We illustrate our method in TV shows, showing its ability to quantify narrative complexity and emotional dynamics across genres. We discuss applications in media and in human-in-the-loop generative AI storytelling., Comment: To be published in NeurIPS 2024 Workshop on Creativity & Generative AI. 7 pages, 3 figures

Neutral atoms have emerged as a promising technology for implementing quantum computers due to their scalability and long coherence times. However, the execution frequency of neutral atom quantum computers is constrained by image processing procedures, particularly the assembly of defect-free atom arrays, which is a crucial step in preparing qubits (atoms) for execution. To optimize this assembly process, we propose a novel quadrant-based rearrangement algorithm that employs a divide-and-conquer strategy and also enables the simultaneous movement of multiple atoms, even across different columns and rows. We implement the algorithm on FPGA to handle each quadrant independently (hardware-level optimization) while maximizing parallelization. To the best of our knowledge, this is the first hardware acceleration work for atom rearrangement, and it significantly reduces the processing time. This achievement also contributes to the ongoing efforts of tightly integrating quantum accelerators into High-Performance Computing (HPC) systems. Tested on a Zynq RFSoC FPGA at 250 MHz, our hardware implementation is able to complete the rearrangement process of a 30$\times$30 compact target array, derived from a 50$\times$50 initial loaded array, in approximately 1.0 $\mu s$. Compared to a comparable CPU implementation and to state-of-the-art FPGA work, we achieved about 54$\times$ and 300$\times$ speedups in the rearrangement analysis time, respectively. Additionally, the FPGA-based acceleration demonstrates good scalability, allowing for seamless adaptation to varying sizes of the atom array, which makes this algorithm a promising solution for large-scale quantum systems., Comment: The paper is accepted by Design, Automation and Test in Europe Conference (DATE), 2025

We investigated the temporal and spectral features of $\gamma$ Cassiopeiae's X-ray emission within the context of the white dwarf accretion hypothesis. We find that the variabilities present in the X-ray data show two different signals, one primarily due to absorption and the other due to flickering like in non-magnetic cataclysmic variables. We then use this two-component insight to investigate previously un-reported simultaneous XMM and NuSTAR data. The model fitting results find white dwarf properties consistent with optical studies alongside a significant secondary, thermal source. We propose a secondary shock between the Be decretion disk and white dwarf accretion disk as the source. Finally, we analyzed a unique, low-count rate event of the XMM light curve as potential evidence for the white dwarf encountering Be decretion disk structures., Comment: Accepted for publication in ApJ

In both the random hopping model and at topological phase transitions in one-dimensional chiral systems, the Lyapunov exponent vanishes at zero energy, but is here shown to have an inverse logarithmic increase with a coefficient that is computed explicitly. This is the counterpart of the Dyson spike in the density of states. The argument also transposes to the free energy density of the random field Ising model, and more generally to many so-called balanced hyperbolic critical points. It is based on the fact that the Furstenberg measure in rescaled logarithmic Dyson-Schmidt variables can be well-approximated by an absolutely continuous measure with trapezoidal density.

Cosmic dust plays a crucial role in the evolution of galaxies, significantly influencing star formation and the interstellar medium. However, in active galactic nuclei (AGN), the role and origin of dust remain poorly understood. High-resolution X-ray spectroscopy is a powerful tool for probing the properties of dust in AGN. NGC 6860, an X-ray bright type-1 quasar, is an ideal target for investigating the connection between dust and winds in AGN. It exhibits reddening and X-ray absorption by both dust and winds. By modeling high-resolution X-ray spectra from XMM-Newton and Chandra observations, we determine the properties of dust and outflows in this AGN. Our analysis finds four photoionized components, outflowing with velocities of 50-300 km/s. The first two are relatively highly ionized with logxi = 3.4 and logxi = 2.9. The results of our photoionization modeling suggest that these two components are thermally unstable. The third component is ionized, with logxi = 2.3 and is located further away from the central black hole. The fourth component is less ionized, and is possibly located in the host galaxy. The application of dust models enables us to probe the abundance and location of the dust in NGC 6860. Our findings suggest that dust absorption and reddening originates from the extended narrow-line region and its host galaxy., Comment: Submitted to Astrophysical Journal (ApJ)

Active metamaterials are engineered structures that possess novel properties that can be changed after the point of manufacture. Their novel properties arise predominantly from their physical structure, as opposed to their chemical composition and can be changed through means such as direct energy addition into wave paths, or physically changing/morphing the structure in response to both a user or environmental input. Active metamaterials are currently of wide interest to the physics community and encompass a range of sub-domains in applied physics (e.g. photonic, microwave, acoustic, mechanical, etc.). They possess the potential to provide solutions that are more suitable to specific applications, or which allow novel properties to be produced which cannot be achieved with passive metamaterials, such as time-varying or gain enhancement effects. They have the potential to help solve some of the important current and future problems faced by the advancement of modern society, such as achieving net-zero, sustainability, healthcare and equality goals. Despite their huge potential, the added complexity of their design and operation, compared to passive metamaterials creates challenges to the advancement of the field, particularly beyond theoretical and lab-based experiments. This roadmap brings together experts in all types of active metamaterials and across a wide range of areas of applied physics. The objective is to provide an overview of the current state of the art and the associated current/future challenges, with the hope that the required advances identified create a roadmap for the future advancement and application of this field.

Humans excel at learning abstract patterns across different sequences, filtering out irrelevant details, and transferring these generalized concepts to new sequences. In contrast, many sequence learning models lack the ability to abstract, which leads to memory inefficiency and poor transfer. We introduce a non-parametric hierarchical variable learning model (HVM) that learns chunks from sequences and abstracts contextually similar chunks as variables. HVM efficiently organizes memory while uncovering abstractions, leading to compact sequence representations. When learning on language datasets such as babyLM, HVM learns a more efficient dictionary than standard compression algorithms such as Lempel-Ziv. In a sequence recall task requiring the acquisition and transfer of variables embedded in sequences, we demonstrate HVM's sequence likelihood correlates with human recall times. In contrast, large language models (LLMs) struggle to transfer abstract variables as effectively as humans. From HVM's adjustable layer of abstraction, we demonstrate that the model realizes a precise trade-off between compression and generalization. Our work offers a cognitive model that captures the learning and transfer of abstract representations in human cognition and differentiates itself from the behavior of large language models.

Establishing a unified theory of cognition has been a major goal of psychology. While there have been previous attempts to instantiate such theories by building computational models, we currently do not have one model that captures the human mind in its entirety. Here we introduce Centaur, a computational model that can predict and simulate human behavior in any experiment expressible in natural language. We derived Centaur by finetuning a state-of-the-art language model on a novel, large-scale data set called Psych-101. Psych-101 reaches an unprecedented scale, covering trial-by-trial data from over 60,000 participants performing over 10,000,000 choices in 160 experiments. Centaur not only captures the behavior of held-out participants better than existing cognitive models, but also generalizes to new cover stories, structural task modifications, and entirely new domains. Furthermore, we find that the model's internal representations become more aligned with human neural activity after finetuning. Taken together, Centaur is the first real candidate for a unified model of human cognition. We anticipate that it will have a disruptive impact on the cognitive sciences, challenging the existing paradigm for developing computational models.

Scattering-type scanning near-field optical microscopy (s-SNOM) allows for the observation of the optical response of material surfaces with a resolution far below the diffraction limit. A spatial resolution of 10-100 nm is routinely achieved in s-SNOM based on amplitude-modulation atomic force microscopy (AM-AFM) with tapping amplitudes of tens of nanometers. However, optical imaging and spectroscopy of structures that are localized to the atomic scale remain a significant challenge. This can be overcome by combining the field enhancement localized at the atomic-scale structure of the tip apex, namely a plasmonic picocavity, with frequency-modulationAFM (FM-AFM), namely non-contact AFM, in a stable cryogenic ultrahigh vacuum environment. Here, we developed picocavityenhanced SNOM (PE-SNOM) under visible laser illumination based on the integration of a quartz tuning fork sensor with small-amplitude oscillations of 1 nm or less. In addition, the use of a focused ion beam-polished silver tip mounted on the sensor leads to strong field enhancement in the picocavity and ensures minimal background scattering from the tip shaft. PE-SNOM allows us to obtain a material-contrast image of silicon islands on a silver surface with 1-nm lateral resolution, which surpasses the conventional limits of s-SNOM. PE-SNOM paves the way for the acquisition of optical information from atomic-scale targets, such as single photo-active defects and molecules.

Since groundbreaking works in the 1980s it is well-known that simple deterministic dynamical systems can display intermittent dynamics and weak chaos leading to anomalous diffusion. A paradigmatic example is the Pomeau-Manneville (PM) map which, suitably lifted onto the whole real line, was shown to generate superdiffusion that can be reproduced by stochastic Levy walks (LWs). Here we report that this matching only holds for parameter values of the PM map that are of Lebesgue measure zero in its two-dimensional parameter space. This is due to a bifurcation scenario that the map exhibits under variation of one parameter. Constraining this parameter to specific singular values at which the map generates superdiffusion by varying the second one, as has been done in previous literature, we find quantitative deviations between deterministic diffusion and diffusion generated by stochastic LWs in a particular range of parameter values, which cannot be cured by simple LW modifcations. We also explore the effect of aging on superdiffusion in the PM map and show that this yields a profound change of the diffusive properties under variation of the aging time, which should be important for experiments. Our findings demonstrate that even in this simplest well-studied setting, a matching of deterministic and stochastic diffusive properties is non-trivial., Comment: 19 pages, 10 figures. arXiv admin note: text overlap with arXiv:2208.09458

On a compact Riemann surface $\Sigma$ of genus $g>1$, equipped with a complex vector bundle $E$ of rank $2$ and degree zero let $M_H$ be the moduli space of Higgs bundles. $M_H$ admits a $\mathbb C^{\star}$-action and to each stable $\mathbb C^{\star}$-fixed point $[(\bar\partial_0,\Phi_0)]$ is associated a holomorphic Lagrangian submanifold $W^1(\bar\partial_0,\Phi_0)$ inside the de Rham moduli space $M_{dR}$ of complex flat connections. In this note we prove a conjecture of Simpson stating that $W^1(\bar\partial_0,\Phi_0)$ is closed inside $M_{dR}$.

OpenCUBE aims to develop an open-source full software stack for Cloud computing blueprint deployed on EPI hardware, adaptable to emerging workloads across the computing continuum. OpenCUBE prioritizes energy awareness and utilizes open APIs, Open Source components, advanced SiPearl Rhea processors, and RISC-V accelerator. The project leverages representative workloads, such as cloud-native workloads and workflows of weather forecast data management, molecular docking, and space weather, for evaluation and validation.

The increasing demand for highly customized products, as well as flexible production lines, can be seen as trigger for the "fourth industrial revolution", referred to as "Industrie 4.0". Current systems usually rely on wire-line technologies to connect sensors and actuators. To enable a higher flexibility such as moving robots or drones, these connections need to be replaced by wireless technologies in the future. Furthermore, this facilitates the renewal of brownfield deployments to address Industrie 4.0 requirements. This paper proposes representative use cases, which have been examined in the German Tactile Internet 4.0 (TACNET 4.0) research project. In order to analyze these use cases, this paper identifies the main challenges and requirements of communication networks in Industrie 4.0 and discusses the applicability of 5th generation wireless communication systems (5G).

Efficient physics simulations are essential for numerous applications, ranging from realistic cloth animations or smoke effects in video games, to analyzing pollutant dispersion in environmental sciences, to calculating vehicle drag coefficients in engineering applications. Unfortunately, analytical solutions to the underlying physical equations are rarely available, and numerical solutions require high computational resources. Latest developments in the field of physics-based Deep Learning have led to promising efficiency improvements but still suffer from limited generalization capabilities and low accuracy compared to numerical solvers. In this work, we introduce Metamizer, a novel neural optimizer that iteratively solves a wide range of physical systems with high accuracy by minimizing a physics-based loss function. To this end, our approach leverages a scale-invariant architecture that enhances gradient descent updates to accelerate convergence. Since the neural network itself acts as an optimizer, training this neural optimizer falls into the category of meta-optimization approaches. We demonstrate that Metamizer achieves unprecedented accuracy for deep learning based approaches - sometimes approaching machine precision - across multiple PDEs after training on the Laplace, advection-diffusion and incompressible Navier-Stokes equation as well as on cloth simulations. Remarkably, the model also generalizes to PDEs that were not covered during training such as the Poisson, wave and Burgers equation. Our results suggest that Metamizer could have a profound impact on future numerical solvers, paving the way for fast and accurate neural physics simulations without the need for retraining.

Processing large-scale graphs, containing billions of entities, is critical across fields like bioinformatics, high-performance computing, navigation and route planning, among others. Efficient graph partitioning, which divides a graph into sub-graphs while minimizing inter-block edges, is essential to graph processing, as it optimizes parallel computing and enhances data locality. Traditional in-memory partitioners, such as METIS and KaHIP, offer high-quality partitions but are often infeasible for enormous graphs due to their substantial memory overhead. Streaming partitioners reduce memory usage to O(n), where 'n' is the number of nodes of the graph, by loading nodes sequentially and assigning them to blocks on-the-fly. This paper introduces StreamCPI, a novel framework that further reduces the memory overhead of streaming partitioners through run-length compression of block assignments. Notably, StreamCPI enables the partitioning of trillion-edge graphs on edge devices. Additionally, within this framework, we propose a modification to the LA-vector bit vector for append support, which can be used for online run-length compression in other streaming applications. Empirical results show that StreamCPI reduces memory usage while maintaining or improving partition quality. For instance, using StreamCPI, the Fennel partitioner effectively partitions a graph with 17 billion nodes and 1.03 trillion edges on a Raspberry Pi, achieving significantly better solution quality than Hashing, the only other feasible algorithm on edge devices. StreamCPI thus advances graph processing by enabling high-quality partitioning on low-cost machines.

We prove that strictly mean convex toroids contain infinitely many (geometrically distinct) embedded free boundary minimal M\"obius bands as well as infinitely many embedded free boundary minimal annuli. The surfaces in both families are constructed by means of equivariant variational methods and their areas grow linearly with the order of their symmetry groups., Comment: 19 pages, 8 figures

Gravitational redshift and Doppler effects give rise to an antisymmetric component of the galaxy correlation function when cross-correlating two galaxy populations or two different tracers. In this paper, we assess the detectability of these effects in the Euclid spectroscopic galaxy survey. We model the impact of gravitational redshift on the observed redshift of galaxies in the Flagship mock catalogue using a Navarro-Frenk-White profile for the host haloes. We isolate these relativistic effects, largely subdominant in the standard analysis, by splitting the galaxy catalogue into two populations of faint and bright objects and estimating the dipole of their cross-correlation in four redshift bins. In the simulated catalogue, we detect the dipole signal on scales below $30\,h^{-1}{\rm Mpc}$, with detection significances of $4\,\sigma$ and $3\,\sigma$ in the two lowest redshift bins, respectively. At higher redshifts, the detection significance drops below $2\,\sigma$. Overall, we estimate the total detection significance in the Euclid spectroscopic sample to be approximately $6\,\sigma$. We find that on small scales, the major contribution to the signal comes from the nonlinear gravitational potential. Our study on the Flagship mock catalogue shows that this observable can be detected in Euclid Data Release 2 and beyond., Comment: 21 pages, 11 figures, 1 appendix; submitted on behalf of the Euclid Collaboration

Compositional representations are thought to enable humans to generalize across combinatorially vast state spaces. Models with learnable object slots, which encode information about objects in separate latent codes, have shown promise for this type of generalization but rely on strong architectural priors. Models with distributed representations, on the other hand, use overlapping, potentially entangled neural codes, and their ability to support compositional generalization remains underexplored. In this paper we examine whether distributed models can develop linearly separable representations of objects, like slotted models, through unsupervised training on videos of object interactions. We show that, surprisingly, models with distributed representations often match or outperform models with object slots in downstream prediction tasks. Furthermore, we find that linearly separable object representations can emerge without object-centric priors, with auxiliary objectives like next-state prediction playing a key role. Finally, we observe that distributed models' object representations are never fully disentangled, even if they are linearly separable: Multiple objects can be encoded through partially overlapping neural populations while still being highly separable with a linear classifier. We hypothesize that maintaining partially shared codes enables distributed models to better compress object dynamics, potentially enhancing generalization.

Cloaking has important applications but entails sophisticated control of signal propagation and scattering characteristics. Here, we show that invisibility for magnon signals is achievable in a non-reciprocal and electrically controlled way by engineering the magnonic channels such that they exhibit PT-symmetry. This is accomplished by attaching current-carrying heavy metal contacts to the magnon waveguides and exerting fields from an attached bias layer. Tuning the current density in the metal layer, the magnons in this setup experience electrically controlled, compensated gain and loss due to spin-orbit torque which renders the setup PT-symmetric. The magnon dynamics is then shown to be pseudo-Hermitian with exceptional points (EPs) determined actively by an external electric field. We analyze the magnon scattering from single and periodic PT-symmetric regions and identify the conditions necessary for the formation of unidirectional invisibility which can be steered by specific combinations of bias layers and current amplitudes in the heavy metal as to reach the EP. The unidirectional invisibility at EP is found to be extended for a periodic PT-symmetric region. Intrinsic damping on PT-symmetric unidirectional invisibility is shown to be marginal confirming the experimental feasibility. It is shown how the unidirectional magnons can be utilized to amplify and generate magnonic orbital angular momentum states in coupled magnetic rings demonstrating a new path for manipulating magnon propagation and processing., Comment: 25 pages, 6 figures

In-context learning, the ability to adapt based on a few examples in the input prompt, is a ubiquitous feature of large language models (LLMs). However, as LLMs' in-context learning abilities continue to improve, understanding this phenomenon mechanistically becomes increasingly important. In particular, it is not well-understood how LLMs learn to solve specific classes of problems, such as reinforcement learning (RL) problems, in-context. Through three different tasks, we first show that Llama $3$ $70$B can solve simple RL problems in-context. We then analyze the residual stream of Llama using Sparse Autoencoders (SAEs) and find representations that closely match temporal difference (TD) errors. Notably, these representations emerge despite the model only being trained to predict the next token. We verify that these representations are indeed causally involved in the computation of TD errors and $Q$-values by performing carefully designed interventions on them. Taken together, our work establishes a methodology for studying and manipulating in-context learning with SAEs, paving the way for a more mechanistic understanding.

The IEA's International Civic and Citizenship Education Study (ICCS) investigates the ways in which young people around the world are prepared to undertake their roles as citizens. This report presents the European results from the third cycle of the study (ICCS 2022). Eighteen countries and two benchmarking participants (the German states of North Rhine-Westphalia and Schleswig-Holstein) administered the European student questionnaire to target grade students in this study cycle. ICCS 2022 studied contexts for and learning outcomes of civic and citizenship education in a wide range of national contexts at the beginning of the third decade of the 21st Century. The general purpose of the European student questionnaire is to explore specific European-related civic and citizenship issues derived from the overarching ICCS 2022 assessment framework, supplementing the data obtained from the international survey with a specific European perspective. The ICCS 2022 European student questionnaire included 12 questions aimed at examining students' interest and their opinions regarding European-related civic and citizenship issues such as students' sense of European identity; students' opportunities for learning about Europe provided by schools; and students' attitudes toward free movement of European citizens within Europe, toward the European Union, and toward cooperation among European countries. It also encompasses questions on students' perceptions of discrimination in their country, of the future of Europe, and of their life in the future, as well as on students' sustainable behaviors and those related to political and ethical consumerism. Over the past 50 years, the IEA has conducted comparative research studies in a range of domains focusing on educational policies, practices, and outcomes in many countries around the world. Prior to ICCS 2022, the IEA had conducted four international comparative studies of civic and citizenship education, with a first survey implemented in 1971, a second in 1999, a third in 2009 and a fourth in 2016. ICCS 2022 data will allow education systems to evaluate the strengths of educational policies, both internationally and in the European regional context, and to measure progress in achieving critical social objectives of their educational policy. [This report was jointly prepared by Libera Università Maria Santissima Assunta (LUMSA Università -- Rome, Italy).]

When assessing the quality of prediction models in machine learning, confidence intervals (CIs) for the generalization error, which measures predictive performance, are a crucial tool. Luckily, there exist many methods for computing such CIs and new promising approaches are continuously being proposed. Typically, these methods combine various resampling procedures, most popular among them cross-validation and bootstrapping, with different variance estimation techniques. Unfortunately, however, there is currently no consensus on when any of these combinations may be most reliably employed and how they generally compare. In this work, we conduct the first large-scale study comparing CIs for the generalization error - empirically evaluating 13 different methods on a total of 18 tabular regression and classification problems, using four different inducers and a total of eight loss functions. We give an overview of the methodological foundations and inherent challenges of constructing CIs for the generalization error and provide a concise review of all 13 methods in a unified framework. Finally, the CI methods are evaluated in terms of their relative coverage frequency, width, and runtime. Based on these findings, we are able to identify a subset of methods that we would recommend. We also publish the datasets as a benchmarking suite on OpenML and our code on GitHub to serve as a basis for further studies.

We investigate charged-hadron production in relativistic heavy-ion collisions of asymmetric systems within a nonequilibrium-statistical framework. Calculated centrality-dependent pseudorapidity distributions for p-Pb collisions at sqrt(s_NN)=5.02 and 8.16 TeV are compared with data from the Large Hadron Collider (LHC). Our approach combines a relativistic diffusion model with formulations based on quantum chromodynamics while utilizing numerical solutions of a Fokker-Planck equation to account for the shift and broadening of the fragmentation sources for particle-production with respect to the stopping (net-baryon) rapidity distributions. To represent the centrality dependence of charged-hadron production in asymmetric systems over a broad region of pseudorapidities, the consideration and precise modelling of the fragmentation sources - along with the central gluon-gluon source - is found to be essential. Specifically, this results in an inversion of the particle-production amplitude from backward- to forward-dominance when transitioning from central to peripheral collisions, in agreement with recent ATLAS and ALICE p-Pb data at sqrt(s_NN)=5.02 TeV., Comment: 14 pages, 6 figures, 3 new references and added text, as accepted for Phys. Rev. C

Introduction: Medication prescriptions are often in free text and include a mix of two languages, local brand names, and a wide range of idiosyncratic formats and abbreviations. Large language models (LLMs) have shown promising ability to generate text in response to input prompts. We use ChatGPT 3.5 to automatically structure and expand medication statements in discharge summaries and thus make them easier to interpret for people and machines. Methods: Named-entity Recognition (NER) and Text Expansion (EX) are used in a zero- and few-shot setting with different prompt strategies. 100 medication statements were manually annotated and curated. NER performance was measured by using strict and partial matching. For the task EX, two experts interpreted the results by assessing semantic equivalence between original and expanded statements. The model performance was measured by precision, recall, and F1 score. Results: For NER, the best-performing prompt reached an average F1 score of 0.94 in the test set. For EX, the few-shot prompt showed superior performance among other prompts, with an average F1 score of 0.87. Conclusion: Our study demonstrates good performance for NER and EX tasks in free-text medication statements using ChatGPT. Compared to a zero-shot baseline, a few-shot approach prevented the system from hallucinating, which would be unacceptable when processing safety-relevant medication data.

In neutral atom quantum computers, readout and preparation of the atomic qubits are usually based on fluorescence imaging and subsequent analysis of the acquired image. For each atom site, the brightness or some comparable metric is estimated and used to predict the presence or absence of an atom. Across different setups, we can see a vast number of different approaches used to analyze these images. Often, the choice of detection algorithm is either not mentioned at all or it is not justified. We investigate several different algorithms and compare their performance in terms of both precision and execution run time. To do so, we rely on a set of synthetic images across different simulated exposure times with known occupancy states. Since the use of simulation provides us with the ground truth of atom site occupancy, we can easily state precise error rates and variances of the reconstructed property. To also rule out the possibility of better algorithms existing, we calculated the Cram\'er-Rao bound in order to establish an upper limit that even a perfect estimator cannot outperform. As the metric of choice, we used the number of photonelectrons that can be contributed to a specific atom site. Since the bound depends on the occupancy of neighboring sites, we provide the best and worst cases, as well as a half filled one. Our comparison shows that of our tested algorithms, a global non-linear least-squares solver that uses the optical system's PSF to return a each sites' number of photoelectrons performed the best, on average crossing the worst-case bound for longer exposure times. Its main drawback is its huge computational complexity and, thus, required calculation time. We manage to somewhat reduce this problem, suggesting that its use may be viable. However, our study also shows that for cases where utmost speed is required, simple algorithms may be preferable., Comment: 10 pages, 11 figures

Research in Explainable Artificial Intelligence (XAI) is increasing, aiming to make deep learning models more transparent. Most XAI methods focus on justifying the decisions made by Artificial Intelligence (AI) systems in security-relevant applications. However, relatively little attention has been given to using these methods to improve the performance and robustness of deep learning algorithms. Additionally, much of the existing XAI work primarily addresses classification problems. In this study, we investigate the potential of feature attribution methods to filter out uninformative features in input data for regression problems, thereby improving the accuracy and stability of predictions. We introduce a feature selection pipeline that combines Integrated Gradients with k-means clustering to select an optimal set of variables from the initial data space. To validate the effectiveness of this approach, we apply it to a real-world industrial problem - blade vibration analysis in the development process of turbo machinery.

We introduce a novel mesh-free and direct method for computing the shape derivative in PDE-constrained shape optimization problems. Our approach is based on a probabilistic representation of the shape derivative and is applicable for second-order semilinear elliptic PDEs with Dirichlet boundary conditions and a general class of target functions. The probabilistic representation derives from an extension of a boundary sensitivity result for diffusion processes due to Costantini, Gobet and El Karoui [14]. Moreover, we present a simulation methodology based on our results that does not necessarily require a mesh of the relevant domain, and provide Taylor tests to verify its numerical accuracy

Cen X-3 is a compact, high-mass X-ray binary (HMXRB), likely powered by Roche lobe overflow. We present a phase-resolved X-ray spectral and timing analysis of a target of opportunity \textit{Chandra} observation made during a low-flux to high-flux transition. The high-resolution spectra allow us to delve into the events that occurred during this episode. The spectrum is described by a single black body absorbed by a local column density of the order of $10^{23-24}$ cm$^{-2}$, which is one to two orders of magnitude higher than found for previous analyses of data taken at similar orbital phases. Such a large column produces a Compton shoulder in the Fe K$\alpha$ line. The transition appears to be caused by the onset of efficient cooling, which cools the plasma by 10 million degrees in just 10 ks, allowing matter to enter the magnetosphere. This happens after a major disturbance, probably the arrival of a train of wind clumps with individual masses in the range $10^{19-20}$ g. This train moves ballistically in an eccentric orbit around the NS, producing a distinctive Doppler modulation in the \ion{Fe}{xxv} line.

We use variational methods to construct a free boundary minimal surface in the three-dimensional unit ball with genus one, two boundary components and prismatic symmetry. Key ingredients are an extension of the equivariant min-max theory to include orientation-reversing isometries and the discovery of a nontrivial two-parameter sweepout.

Online adaptation of exoskeleton control based on muscle activity sensing is a promising way to personalize exoskeletons based on the user's biosignals. While several electromyography (EMG) based methods have been shown to improve joint torque estimation, EMG sensors require direct skin contact and complex post-processing. In contrast, force myography (FMG) measures normal forces from changes in muscle volume due to muscle activity. We propose an FMG-based method to estimate knee and ankle joint torques by combining joint angles and velocities with muscle activity information. We learn a model for joint torque estimation using Gaussian process regression (GPR). The effectiveness of the proposed FMG-based method is validated on isokinetic motions performed by two subjects. The model is compared to a baseline model using only joint angle and velocity, as well as a model augmented by EMG data. The results show that integrating FMG into exoskeleton control improves the joint torque estimation for the ankle and knee and is therefore a promising way to improve adaptability to different exoskeleton users., Comment: This work has been submitted to the IEEE for possible publication

In contrast with the diversity of materials found in nature, most robots are designed with some combination of aluminum, stainless steel, and 3D-printed filament. Additionally, robotic systems are typically assumed to follow basic rigid-body dynamics. However, several examples in nature illustrate how changes in physical material properties yield functional advantages. In this paper, we explore how physical materials (non-rigid bodies) affect the functional performance of a hopping robot. In doing so, we address the practical question of how to model and simulate material properties. Through these simulations we demonstrate that material gradients in the limb system of a single-limb hopper provide functional advantages compared to homogeneous designs. For example, when considering incline ramp hopping, a material gradient with increasing density provides a 35\% reduction in tracking error and a 23\% reduction in power consumption compared to isotropic stainless steel. By providing bio-inspiration to the rigid limbs in a robotic system, we seek to show that future fabrication of robots should look to leverage the material anisotropies of moduli and density found in nature. This would allow for reduced vibrations in the system and would provide offsets of joint torques and vibrations while protecting their structural integrity against reduced fatigue and wear. This simulation system could inspire future intelligent material gradients of custom-fabricated robotic locomotive devices.

Soliton automata are mathematical models of soliton switching in chemical molecules. Several concepts of determinism for soliton automata have been defined. The concept of strong determinism has been investigated for the case in which only a single soliton can be present in a molecule. In the present paper, several different concepts of determinism are explored for the multi-soliton case. It is shown that the degree of non-determinism is a connected measure of descriptional complexity for multi-soliton automata. A characterization of the class of strongly deterministic multi-soliton automata is presented. Finally, the concept of perfect determinism, forming a natural extension of strong determinism, is introduced and considered for multi-soliton automata., Comment: In Proceedings NCMA 2024, arXiv:2409.06120