Search

Diagnosing dementia, particularly for Alzheimer's Disease (AD) and frontotemporal dementia (FTD), is complex due to overlapping symptoms. While magnetic resonance imaging (MRI) and positron emission tomography (PET) data are critical for the diagnosis, integrating these modalities in deep learning faces challenges, often resulting in suboptimal performance compared to using single modalities. Moreover, the potential of multi-modal approaches in differential diagnosis, which holds significant clinical importance, remains largely unexplored. We propose a novel framework, DiaMond, to address these issues with vision Transformers to effectively integrate MRI and PET. DiaMond is equipped with self-attention and a novel bi-attention mechanism that synergistically combine MRI and PET, alongside a multi-modal normalization to reduce redundant dependency, thereby boosting the performance. DiaMond significantly outperforms existing multi-modal methods across various datasets, achieving a balanced accuracy of 92.4% in AD diagnosis, 65.2% for AD-MCI-CN classification, and 76.5% in differential diagnosis of AD and FTD. We also validated the robustness of DiaMond in a comprehensive ablation study. The code is available at https://github.com/ai-med/DiaMond., Comment: Accepted by IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025

Gradient-based dimension reduction decreases the cost of Bayesian inference and probabilistic modeling by identifying maximally informative (and informed) low-dimensional projections of the data and parameters, allowing high-dimensional problems to be reformulated as cheaper low-dimensional problems. A broad family of such techniques identify these projections and provide error bounds on the resulting posterior approximations, via eigendecompositions of certain diagnostic matrices. Yet these matrices require gradients or even Hessians of the log-likelihood, excluding the purely data-driven setting and many problems of simulation-based inference. We propose a framework, derived from score-matching, to extend gradient-based dimension reduction to problems where gradients are unavailable. Specifically, we formulate an objective function to directly learn the score ratio function needed to compute the diagnostic matrices, propose a tailored parameterization for the score ratio network, and introduce regularization methods that capitalize on the hypothesized low-dimensional structure. We also introduce a novel algorithm to iteratively identify the low-dimensional reduced basis vectors more accurately with limited data based on eigenvalue deflation methods. We show that our approach outperforms standard score-matching for problems with low-dimensional structure, and demonstrate its effectiveness for PDE-constrained Bayesian inverse problems and conditional generative modeling., Comment: 23 pages, 9 figures, 1 table

In this paper, we investigate the existence and uniqueness of solutions for the following model problem, involving singularities and inhomogeneous Robin boundary conditions \begin{equation*} \left\{ \begin{array}{ll} -\Delta_{p}u_{p}=\frac{f}{u_{p}^{\gamma}}& \hbox{in $\Omega,$} \frac{\partial u_{p}}{\partial \sigma}+\lambda\vert u_{p}\vert^{p-2} u_{p}+\vert u_{p}\vert^{s-1}u_{p}=\frac{g}{u_{p}^{\eta}} & \hbox{on $\partial\Omega,$} \end{array} \right. \end{equation*} where $\Omega \subset \mathbb{R}^{m}$ represents an open bounded domain, with smooth boundary, $m \geq 2$, the symbol $\sigma $ stands for the unit outward normal vector, $ \Delta_{p}u:=\mbox{div}(\vert\nabla u\vert^{p-2}\nabla u) $ is the $p-$Laplacian operator $(1\leq p0$ and $s\geq 1.$ The function $ f\in L^{\frac{m}{p}}(\Omega)$ is a nonnegative additionally $ \lambda$ and $ g$ are nonnegative functions in $L^{\infty}(\partial \Omega).$

Pre-trained Language Models (PLMs) encode various facts about the world at their pre-training phase as they are trained to predict the next or missing word in a sentence. There has a been an interest in quantifying and improving the amount of facts that can be extracted from PLMs, as they have been envisioned to act as soft knowledge bases, which can be queried in natural language. Different approaches exist to enhance fact retrieval from PLM. Recent work shows that the hidden states of PLMs can be leveraged to determine the truthfulness of the PLMs' inputs. Leveraging this finding to improve factual knowledge retrieval remains unexplored. In this work, we investigate the use of a helper model to improve fact retrieval. The helper model assesses the truthfulness of an input based on the corresponding hidden states representations from the PLMs. We evaluate this approach on several masked PLMs and show that it enhances fact retrieval by up to 33\%. Our findings highlight the potential of hidden states representations from PLMs in improving their factual knowledge retrieval.

In-context knowledge editing (IKE) enables efficient modification of large language model (LLM) outputs without parameter changes and at zero-cost. However, it can be misused to manipulate responses opaquely, e.g., insert misinformation or offensive content. Such malicious interventions could be incorporated into high-level wrapped APIs where the final input prompt is not shown to end-users. To address this issue, we investigate the detection and reversal of IKE-edits. First, we demonstrate that IKE-edits can be detected with high accuracy (F1 > 80\%) using only the top-10 output probabilities of the next token, even in a black-box setting, e.g. proprietary LLMs with limited output information. Further, we introduce the novel task of reversing IKE-edits using specially tuned reversal tokens. We explore using both continuous and discrete reversal tokens, achieving over 80\% accuracy in recovering original, unedited outputs across multiple LLMs. Our continuous reversal tokens prove particularly effective, with minimal impact on unedited prompts. Through analysis of output distributions, attention patterns, and token rankings, we provide insights into IKE's effects on LLMs and how reversal tokens mitigate them. This work represents a significant step towards enhancing LLM resilience against potential misuse of in-context editing, improving their transparency and trustworthiness.

The emerging zero-shot capabilities of Large Language Models (LLMs) have led to their applications in areas extending well beyond natural language processing tasks. In reinforcement learning, while LLMs have been extensively used in text-based environments, their integration with continuous state spaces remains understudied. In this paper, we investigate how pre-trained LLMs can be leveraged to predict in context the dynamics of continuous Markov decision processes. We identify handling multivariate data and incorporating the control signal as key challenges that limit the potential of LLMs' deployment in this setup and propose Disentangled In-Context Learning (DICL) to address them. We present proof-of-concept applications in two reinforcement learning settings: model-based policy evaluation and data-augmented off-policy reinforcement learning, supported by theoretical analysis of the proposed methods. Our experiments further demonstrate that our approach produces well-calibrated uncertainty estimates. We release the code at https://github.com/abenechehab/dicl.

Understanding protein motion within the cell is crucial for predicting reaction rates and macromolecular transport in the cytoplasm. A key question is how crowded environments affect protein dynamics through hydrodynamic and direct interactions at molecular length scales. Using megahertz X-ray Photon Correlation Spectroscopy (MHz-XPCS) at the European X-ray Free Electron Laser (EuXFEL), we investigate ferritin diffusion at microsecond time scales. Our results reveal anomalous diffusion, indicated by the non-exponential decay of the intensity autocorrelation function $g_2(q,t)$ at high concentrations. This behavior is consistent with the presence of cage-trapping in between the short- and long-time protein diffusion regimes. Modeling with the $\delta\gamma$-theory of hydrodynamically interacting colloidal spheres successfully reproduces the experimental data by including a scaling factor linked to the protein direct interactions. These findings offer new insights into the complex molecular motion in crowded protein solutions, with potential applications for optimizing ferritin-based drug delivery, where protein diffusion is the rate-limiting step.

We introduce a novel method for extracting a fragmentation model directly from experimental data without requiring an explicit parametric form, called Histories and Observables for Monte-Carlo Event Reweighting (HOMER), consisting of three steps: the training of a classifier between simulation and data, the inference of single fragmentation weights, and the calculation of the weight for the full hadronization chain. We illustrate the use of HOMER on a simplified hadronization problem, a $q\bar{q}$ string fragmenting into pions, and extract a modified Lund string fragmentation function $f(z)$. We then demonstrate the use of HOMER on three types of experimental data: (i) binned distributions of high level observables, (ii) unbinned event-by-event distributions of these observables, and (iii) full particle cloud information. After demonstrating that $f(z)$ can be extracted from data (the inverse of hadronization), we also show that, at least in this limited setup, the fidelity of the extracted $f(z)$ suffers only limited loss when moving from (i) to (ii) to (iii). Public code is available at https://gitlab.com/uchep/mlhad., Comment: 41 pages, 21 figures. Updated version prepared for submission. Public code available

Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language model) or fine-tuning the LLM using self-generated data to influence the outcome. In this paper, we show that LLMs have the capability of self-detoxification without the use of an additional reward model or re-training. We propose \textit{Self-disciplined Autoregressive Sampling (SASA)}, a lightweight controlled decoding algorithm for toxicity reduction of LLMs. SASA leverages the contextual representations from an LLM to learn linear subspaces characterizing toxic v.s. non-toxic output in analytical forms. When auto-completing a response token-by-token, SASA dynamically tracks the margin of the current output to steer the generation away from the toxic subspace, by adjusting the autoregressive sampling strategy. Evaluated on LLMs of different scale and nature, namely Llama-3.1-Instruct (8B), Llama-2 (7B), and GPT2-L models with the RealToxicityPrompts, BOLD, and AttaQ benchmarks, SASA markedly enhances the quality of the generated sentences relative to the original models and attains comparable performance to state-of-the-art detoxification techniques, significantly reducing the toxicity level by only using the LLM's internal representations., Comment: 20 pages

Monte Carlo Exploring Starts (MCES), which aims to learn the optimal policy using only sample returns, is a simple and natural algorithm in reinforcement learning which has been shown to converge under various conditions. However, the convergence rate analysis for MCES-style algorithms in the form of sample complexity has received very little attention. In this paper we develop a finite sample bound for a modified MCES algorithm which solves the stochastic shortest path problem. To this end, we prove a novel result on the convergence rate of the policy iteration algorithm. This result implies that with probability at least $1-\delta$, the algorithm returns an optimal policy after $\tilde{O}(SAK^3\log^3\frac{1}{\delta})$ sampled episodes, where $S$ and $A$ denote the number of states and actions respectively, $K$ is a proxy for episode length, and $\tilde{O}$ hides logarithmic factors and constants depending on the rewards of the environment that are assumed to be known., Comment: 13 pages

Indoor localization has become increasingly important due to its wide-ranging applications in indoor navigation, emergency services, the Internet of Things (IoT), and accessibility for individuals with special needs. Traditional localization systems often require extensive calibration to achieve high accuracy. We introduce UbiLoc, an innovative, calibration-free indoor localization system that leverages Apple AirTags in a novel way to localize users instead of tracking objects. By utilizing the ubiquitous presence of AirTags and their Ultra-Wideband (UWB) technology, UbiLoc achieves centimeter-level accuracy, surpassing traditional WiFi and Bluetooth Low Energy (BLE) systems. UbiLoc addresses key challenges, including ranging errors caused by multipath and noise, through a novel AirTag selection technique. The system operates without the need for manual calibration, ensuring robustness and self-maintenance. Deployed on various Apple devices and tested in real-world environments, UbiLoc achieved median localization errors as low as 26 cm in a campus building and 31.5 cm in an apartment setting. These results demonstrate that UbiLoc is the first system to offer reliable, cm-level accuracy using widely available technology without requiring calibration, making it a promising solution for next-generation indoor localization systems., Comment: Accepted for publication in 2nd ACM SIGSPATIAL International Workshop on Geo-Privacy and Data Utility for Smart Societies: 7 pages, 9 figures

We explore a scaled spectral preconditioner for the efficient solution of sequences of symmetric and positive-definite linear systems. We design the scaled preconditioner not only as an approximation of the inverse of the linear system but also with consideration of its use within the conjugate gradient (CG) method. We propose three different strategies for selecting a scaling parameter, which aims to position the eigenvalues of the preconditioned matrix in a way that reduces the energy norm of the error, the quantity that CG monotonically decreases at each iteration. Our focus is on accelerating convergence especially in the early iterations, which is particularly important when CG is truncated due to computational cost constraints. Numerical experiments provide in data assimilation confirm that the scaled spectral preconditioner can significantly improve early CG convergence with negligible computational cost.

Penalty methods are a well known class of algorithms for constrained optimization. They transform a constrained problem into a sequence of unconstrained penalized problems in the hope that approximate solutions of the latter converge to a solution of the former. If Lagrange multipliers exist, exact penalty methods ensure that the penalty parameter only need increase a finite number of times, but are typically scorned in smooth optimization for the penalized problems are not smooth. This led researchers to consider the implementation of exact penalty methods inconvenient. Recently, advances in proximal methods have led to increasingly efficient solvers for nonsmooth optimization. We show that the exact $\ell_2$-penalty method for equality-constrained optimization can in fact be implemented efficiently by solving the penalized problem with a proximal-type algorithm. We study the convergence of our algorithm and establish a worst-case complexity bound of $O(\epsilon^{-2})$ to bring a stationarity measure below $\epsilon > 0$ under the Mangarasian-Fromowitz constraint qualification and Lipschitz continuity of the objective gradient and constraint Jacobian. In a degenerate scenario where the penalty parameter grows unbounded, the complexity becomes $O(\epsilon^{-8})$, which is worse than another bound found in the literature. We justify the difference by arguing that our feasibility measure is properly scaled. Finally, we report numerical experience on small-scale problems from a standard collection and compare our solver with an augmented-Lagrangian and an SQP method. Our preliminary implementation is on par with the augmented Lagrangian in terms of robustness and efficiency. It is on par with the SQP method in terms of robustness, though the former remains ahead in terms of number of problem function evaluations.

Federated learning (FL) is an appealing paradigm that allows a group of machines (a.k.a. clients) to learn collectively while keeping their data local. However, due to the heterogeneity between the clients' data distributions, the model obtained through the use of FL algorithms may perform poorly on some client's data. Personalization addresses this issue by enabling each client to have a different model tailored to their own data while simultaneously benefiting from the other clients' data. We consider an FL setting where some clients can be adversarial, and we derive conditions under which full collaboration fails. Specifically, we analyze the generalization performance of an interpolated personalized FL framework in the presence of adversarial clients, and we precisely characterize situations when full collaboration performs strictly worse than fine-tuned personalization. Our analysis determines how much we should scale down the level of collaboration, according to data heterogeneity and the tolerable fraction of adversarial clients. We support our findings with empirical results on mean estimation and binary classification problems, considering synthetic and benchmark image classification datasets.

Brain-related research topics in artificial intelligence have recently gained popularity, particularly due to the expansion of what multimodal architectures can do from computer vision to natural language processing. Our main goal in this work is to explore the possibilities and limitations of these architectures in spoken text decoding from non-invasive fMRI recordings. Contrary to vision and textual data, fMRI data represent a complex modality due to the variety of brain scanners, which implies (i) the variety of the recorded signal formats, (ii) the low resolution and noise of the raw signals, and (iii) the scarcity of pretrained models that can be leveraged as foundation models for generative learning. These points make the problem of the non-invasive decoding of text from fMRI recordings very challenging. In this paper, we propose and end-to-end multimodal LLM for decoding spoken text from fMRI signals. The proposed architecture is founded on (i) an encoder derived from a specific transformer incorporating an augmented embedding layer for the encoder and a better-adjusted attention mechanism than that present in the state of the art, and (ii) a frozen large language model adapted to align the embedding of the input text and the encoded embedding of brain activity to decode the output text. A benchmark in performed on a corpus consisting of a set of interactions human-human and human-robot interactions where fMRI and conversational signals are recorded synchronously. The obtained results are very promising, as our proposal outperforms the evaluated models, and is able to generate text capturing more accurate semantics present in the ground truth. The implementation code is provided in https://github.com/Hmamouche/brain_decode., Comment: 15 pages, 4 figures

This paper tackles the challenge of running multiple ML inference jobs (models) under time-varying workloads, on a constrained on-premises production cluster. Our system Faro takes in latency Service Level Objectives (SLOs) for each job, auto-distills them into utility functions, "sloppifies" these utility functions to make them amenable to mathematical optimization, automatically predicts workload via probabilistic prediction, and dynamically makes implicit cross-job resource allocations, in order to satisfy cluster-wide objectives, e.g., total utility, fairness, and other hybrid variants. A major challenge Faro tackles is that using precise utilities and high-fidelity predictors, can be too slow (and in a sense too precise!) for the fast adaptation we require. Faro's solution is to "sloppify" (relax) its multiple design components to achieve fast adaptation without overly degrading solution quality. Faro is implemented in a stack consisting of Ray Serve running atop a Kubernetes cluster. Trace-driven cluster deployments show that Faro achieves 2.3$\times$-23$\times$ lower SLO violations compared to state-of-the-art systems., Comment: 13 pages, 16 figures, To appear in Eurosys 2025

We develop R2N, a modified quasi-Newton method for minimizing the sum of a $\mathcal{C}^1$ function $f$ and a lower semi-continuous prox-bounded $h$. Both $f$ and $h$ may be nonconvex. At each iteration, our method computes a step by minimizing the sum of a quadratic model of $f$, a model of $h$, and an adaptive quadratic regularization term. A step may be computed by a variant of the proximal-gradient method. An advantage of R2N over trust-region (TR) methods is that proximal operators do not involve an extra TR indicator. We also develop the variant R2DH, in which the model Hessian is diagonal, which allows us to compute a step without relying on a subproblem solver when $h$ is separable. R2DH can be used as standalone solver, but also as subproblem solver inside R2N. We describe non-monotone variants of both R2N and R2DH. Global convergence of a first-order stationarity measure to zero holds without relying on local Lipschitz continuity of $\nabla f$, while allowing model Hessians to grow unbounded, an assumption particularly relevant to quasi-Newton models. Under Lipschitz-continuity of $\nabla f$, we establish a tight worst-case complexity bound of $O(1 / \epsilon^{2/(1 - p)})$ to bring said measure below $\epsilon > 0$, where $0 \leq p < 1$ controls the growth of model Hessians. The latter must not diverge faster than $|\mathcal{S}_k|^p$, where $\mathcal{S}_k$ is the set of successful iterations up to iteration $k$. When $p = 1$, we establish the tight exponential complexity bound $O(\exp(c \epsilon^{-2}))$ where $c > 0$ is a constant. We describe our Julia implementation and report numerical experience on a basis-pursuit problem, image denoising, minimum-rank matrix completion, and a nonlinear support vector machine. In particular, the minimum-rank problem cannot be solved directly at this time by a TR approach as corresponding proximal operators are not known analytically.

The advancement of artificial intelligence algorithms has expanded their application to several fields such as the biomedical domain. Artificial intelligence systems, including Large Language Models (LLMs), can be particularly advantageous in drug discovery, which is a very long and expensive process. However, LLMs by themselves lack in-depth knowledge about specific domains and can generate factually incorrect information. Moreover, they are not able to perform more complex actions that imply the usage of external tools. Our work is focused on these two issues. Firstly, we show how the implementation of an advanced RAG system can help the LLM to generate more accurate answers to drug-discovery-related questions. The results show that the answers generated by the LLM with the RAG system surpass in quality the answers produced by the model without RAG. Secondly, we show how to create an automatic target dossier using LLMs and incorporating them with external tools that they can use to execute more intricate tasks to gather data such as accessing databases and executing code. The result is a production-ready target dossier containing the acquired information summarized into a PDF and a PowerPoint presentation., Comment: 10 pages, 7 figures, 2 tables

In this paper, we present a novel visual servoing (VS) approach based on latent Denoising Diffusion Probabilistic Models (DDPMs). Opposite to classical VS methods, the proposed approach allows reaching the desired target view, even when the target is initially not visible. This is possible thanks to the learning of a latent representation that the DDPM uses for planning and a dataset of trajectories encompassing target-invisible initial views. The latent representation is learned using a Cross-Modal Variational Autoencoder, and used to estimate the return for conditioning the trajectory generation of the DDPM. Given the current image, the DDPM generates trajectories in the latent space driving the robotic platform to the desired visual target. The approach is applicable to any velocity-based controlled platform. We test our method with simulated and real-world experiments using generic multi-rotor Uncrewed Aerial Vehicles (UAVs). A video of our experiments can be found at https://youtu.be/yu-aTxqceOA.

This work focuses on developing and motivating a stochastic version of a wellknown inverse problem methodology. Specifically, we consider the iteratively regularized Gauss-Newton method, originally proposed by Bakushinskii for infinite-dimensional problems. Recent work have extended this method to handle sequential observations, rather than a single instance of the data, demonstrating notable improvements in reconstruction accuracy. In this paper, we further extend these methods to a stochastic framework through mini-batching, introducing a new algorithm, the stochastic iteratively regularized Gauss-Newton method (SIRGNM). Our algorithm is designed through the use randomized sketching. We provide an analysis for the SIRGNM, which includes a preliminary error decomposition and a convergence analysis, related to the residuals. We provide numerical experiments on a 2D elliptic PDE example. This illustrates the effectiveness of the SIRGNM, through maintaining a similar level of accuracy while reducing on the computational time., Comment: 23 pages

Accurate recognition of human emotions is a crucial challenge in affective computing and human-robot interaction (HRI). Emotional states play a vital role in shaping behaviors, decisions, and social interactions. However, emotional expressions can be influenced by contextual factors, leading to misinterpretations if context is not considered. Multimodal fusion, combining modalities like facial expressions, speech, and physiological signals, has shown promise in improving affect recognition. This paper proposes a transformer-based multimodal fusion approach that leverages facial thermal data, facial action units, and textual context information for context-aware emotion recognition. We explore modality-specific encoders to learn tailored representations, which are then fused using additive fusion and processed by a shared transformer encoder to capture temporal dependencies and interactions. The proposed method is evaluated on a dataset collected from participants engaged in a tangible tabletop Pacman game designed to induce various affective states. Our results demonstrate the effectiveness of incorporating contextual information and multimodal fusion for affective state recognition.

In state-of-the-art optical lattice clocks, beyond-electric-dipole polarizability terms lead to a break-down of magic wavelength trapping. In this Letter, we report a novel approach to evaluate lattice light shifts, specifically addressing recent discrepancies in the atomic multipolarizability term between experimental techniques and theoretical calculations. We combine imaging and multi-ensemble techniques to evaluate lattice light shift atomic coefficients, leveraging comparisons in a dual-ensemble lattice clock to rapidly evaluate differential frequency shifts. Further, we demonstrate application of a running wave field to probe both the multipolarizability and hyperpolarizability coefficients, establishing a new technique for future lattice light shift evaluations., Comment: 17 pages, 6 figures

Addressing the Out-of-Distribution (OoD) segmentation task is a prerequisite for perception systems operating in an open-world environment. Large foundational models are frequently used in downstream tasks, however, their potential for OoD remains mostly unexplored. We seek to leverage a large foundational model to achieve robust representation. Outlier supervision is a widely used strategy for improving OoD detection of the existing segmentation networks. However, current approaches for outlier supervision involve retraining parts of the original network, which is typically disruptive to the model's learned feature representation. Furthermore, retraining becomes infeasible in the case of large foundational models. Our goal is to retrain for outlier segmentation without compromising the strong representation space of the foundational model. To this end, we propose an adaptive, lightweight unknown estimation module (UEM) for outlier supervision that significantly enhances the OoD segmentation performance without affecting the learned feature representation of the original network. UEM learns a distribution for outliers and a generic distribution for known classes. Using the learned distributions, we propose a likelihood-ratio-based outlier scoring function that fuses the confidence of UEM with that of the pixel-wise segmentation inlier network to detect unknown objects. We also propose an objective to optimize this score directly. Our approach achieves a new state-of-the-art across multiple datasets, outperforming the previous best method by 5.74% average precision points while having a lower false-positive rate. Importantly, strong inlier performance remains unaffected., Comment: 13 pages, 2 figures, and 4 tables

The current paradigm for motion planning generates solutions from scratch for every new problem, which consumes significant amounts of time and computational resources. For complex, cluttered scenes, motion planning approaches can often take minutes to produce a solution, while humans are able to accurately and safely reach any goal in seconds by leveraging their prior experience. We seek to do the same by applying data-driven learning at scale to the problem of motion planning. Our approach builds a large number of complex scenes in simulation, collects expert data from a motion planner, then distills it into a reactive generalist policy. We then combine this with lightweight optimization to obtain a safe path for real world deployment. We perform a thorough evaluation of our method on 64 motion planning tasks across four diverse environments with randomized poses, scenes and obstacles, in the real world, demonstrating an improvement of 23%, 17% and 79% motion planning success rate over state of the art sampling, optimization and learning based planning methods. Video results available at mihdalal.github.io/neuralmotionplanner, Comment: Website at mihdalal.github.io/neuralmotionplanner. Main paper: 7 pages, 4 figures, 2 tables. Appendix: 9 pages, 5 figures, 6 tables

In many industrial settings, users wish to ask questions whose answers may be found in structured data sources such as a spreadsheets, databases, APIs, or combinations thereof. Often, the user doesn't know how to identify or access the right data source. This problem is compounded even further if multiple (and potentially siloed) data sources must be assembled to derive the answer. Recently, various Text-to-SQL applications that leverage Large Language Models (LLMs) have addressed some of these problems by enabling users to ask questions in natural language. However, these applications remain impractical in realistic industrial settings because they fail to cope with the data source heterogeneity that typifies such environments. In this paper, we address heterogeneity by introducing the siwarex platform, which enables seamless natural language access to both databases and APIs. To demonstrate the effectiveness of siwarex, we extend the popular Spider dataset and benchmark by replacing some of its tables by data retrieval APIs. We find that siwarex does a good job of coping with data source heterogeneity. Our modified Spider benchmark will soon be available to the research community

Line Current Differential Relays (LCDRs) are high-speed relays progressively used to protect critical transmission lines. However, LCDRs are vulnerable to cyberattacks. Fault-Masking Attacks (FMAs) are stealthy cyberattacks performed by manipulating the remote measurements of the targeted LCDR to disguise faults on the protected line. Hence, they remain undetected by this LCDR. In this paper, we propose a two-module framework to detect FMAs. The first module is a Mismatch Index (MI) developed from the protected transmission line's equivalent physical model. The MI is triggered only if there is a significant mismatch in the LCDR's local and remote measurements while the LCDR itself is untriggered, which indicates an FMA. After the MI is triggered, the second module, a neural network-based classifier, promptly confirms that the triggering event is a physical fault that lies on the line protected by the LCDR before declaring the occurrence of an FMA. The proposed framework is tested using the IEEE 39-bus benchmark system. Our simulation results confirm that the proposed framework can accurately detect FMAs on LCDRs and is not affected by normal system disturbances, variations, or measurement noise. Our experimental results using OPAL-RT's real-time simulator confirm the proposed solution's real-time performance capability., Comment: Accepted to IEEE Transactions on Systems, Man, and Cybernetics: Systems. \c{opyright} 2024 IEEE

Accurate floor localization in a multi-story environment is an important but challenging task. Among the current floor localization techniques, fingerprinting is the mainstream technology due to its accuracy in noisy environments. To achieve accurate floor localization in a building with many floors, we have to collect sufficient data on each floor, which needs significant storage and running time; preventing fingerprinting techniques from scaling to support large multi-story buildings, especially on a worldwide scale. In this paper, we propose a quantum algorithm for accurate multi-story localization. The proposed algorithm leverages quantum computing concepts to provide an exponential enhancement in both space and running time compared to the classical counterparts. In addition, it builds on an efficient binary-neuron implementation that can be implemented using fewer qubits compared to the typical non-binary neurons, allowing for easier deployment with near-term quantum devices. We implement the proposed algorithm on a real IBM quantum machine and evaluate it on three real indoor testbeds. Results confirm the exponential saving in both time and space for the proposed quantum algorithm, while keeping the same localization accuracy compared to the traditional classical techniques, and using half the number of qubits required for other quantum localization algorithms.

Deep Neural Networks (DNNs) have become central for the perception functions of autonomous vehicles, substantially enhancing their ability to understand and interpret the environment. However, these systems exhibit inherent limitations such as brittleness, opacity, and unpredictable behavior in out-of-distribution scenarios. The European Union (EU) Artificial Intelligence (AI) Act, as a pioneering legislative framework, aims to address these challenges by establishing stringent norms and standards for AI systems, including those used in autonomous driving (AD), which are categorized as high-risk AI. In this work, we explore how the newly available generative AI models can potentially support addressing upcoming regulatory requirements in AD perception, particularly with respect to safety. This short review paper summarizes the requirements arising from the EU AI Act regarding DNN-based perception systems and systematically categorizes existing generative AI applications in AD. While generative AI models show promise in addressing some of the EU AI Acts requirements, such as transparency and robustness, this review examines their potential benefits and discusses how developers could leverage these methods to enhance compliance with the Act. The paper also highlights areas where further research is needed to ensure reliable and safe integration of these technologies.

We demonstrate the non-reciprocity of electrically and thermally-generated incoherent magnon transport using the magnetization direction of a Py wire placed on top of an ultrathin YIG film. We show that the transport properties of thermally-generated magnons under a Py wire depends on the relative orientation between the temperature gradient and the Py-magnetization direction. The symmetries of this non-reciprocal magnon transport match with those predicted by the remote dipolar interaction between YIG and Py magnons, controlled by the chirality of the YIG magnon dipolar stray fields. We also show that the directional magnon generation by the spin Seebeck effect from the Py wire displays the symmetries expected from the chiral spin Seebeck effect.

Approximation using Fourier features is a popular technique for scaling kernel methods to large-scale problems, with myriad applications in machine learning and statistics. This method replaces the integral representation of a shift-invariant kernel with a sum using a quadrature rule. The design of the latter is meant to reduce the number of features required for high-precision approximation. Specifically, for the squared exponential kernel, one must design a quadrature rule that approximates the Gaussian measure on $\mathbb{R}^d$. Previous efforts in this line of research have faced difficulties in higher dimensions. We introduce a new family of quadrature rules that accurately approximate the Gaussian measure in higher dimensions by exploiting its isotropy. These rules are constructed as a tensor product of a radial quadrature rule and a spherical quadrature rule. Compared to previous work, our approach leverages a thorough analysis of the approximation error, which suggests natural choices for both the radial and spherical components. We demonstrate that this family of Fourier features yields improved approximation bounds.

\texttt{ml\_edm} is a Python 3 library, designed for early decision making of any learning tasks involving temporal/sequential data. The package is also modular, providing researchers an easy way to implement their own triggering strategy for classification, regression or any machine learning task. As of now, many Early Classification of Time Series (ECTS) state-of-the-art algorithms, are efficiently implemented in the library leveraging parallel computation. The syntax follows the one introduce in \texttt{scikit-learn}, making estimators and pipelines compatible with \texttt{ml\_edm}. This software is distributed over the BSD-3-Clause license, source code can be found at \url{https://github.com/ML-EDM/ml_edm}.

Reinforcement Learning (RL) algorithms suffer from the dependency on accurately engineered reward functions to properly guide the learning agents to do the required tasks. Preference-based reinforcement learning (PbRL) addresses that by utilizing human preferences as feedback from the experts instead of numeric rewards. Due to its promising advantage over traditional RL, PbRL has gained more focus in recent years with many significant advances. In this survey, we present a unified PbRL framework to include the newly emerging approaches that improve the scalability and efficiency of PbRL. In addition, we give a detailed overview of the theoretical guarantees and benchmarking work done in the field, while presenting its recent applications in complex real-world tasks. Lastly, we go over the limitations of the current approaches and the proposed future research directions.

Locating the persons moving through an environment without the necessity of them being equipped with special devices has become vital for many applications including security, IoT, healthcare, etc. Existing device-free indoor localization systems commonly rely on the utilization of Received Signal Strength Indicator (RSSI) and WiFi Channel State Information (CSI) techniques. However, the accuracy of RSSI is adversely affected by environmental factors like multi-path interference and fading. Additionally, the lack of standardization in CSI necessitates the use of specialized hardware and software. In this paper, we present TimeSense, a deep learning-based multi-person device-free indoor localization system that addresses these challenges. TimeSense leverages Time of Flight information acquired by the fine-time measurement protocol of IEEE 802.11-2016 standard. Specifically, the measured round trip time between the transmitter and receiver is influenced by the dynamic changes in the environment induced by human presence. TimeSense effectively detects this anomalous behavior using a stacked denoising auto-encoder model, thereby estimating the user's location. The system incorporates a probabilistic approach on top of the deep learning model to ensure seamless tracking of the users. The evaluation of TimeSene in two realistic environments demonstrates its efficacy, achieving a median localization accuracy of 1.57 and 2.65 meters. This surpasses the performance of state-of-the-art techniques by 49% and 103% in the two testbeds.

With the rapid integration of electronically interfaced renewable energy resources and loads into smart grids, there is increasing interest in power quality disturbances (PQD) classification to enhance the security and efficiency of these grids. This paper introduces a new approach to PQD classification based on the Vision Transformer (ViT) model. When a PQD occurs, the proposed approach first converts the power quality signal into an image and then utilizes a pre-trained ViT to accurately determine the class of the PQD. Unlike most previous works, which were limited to a few disturbance classes or small datasets, the proposed method is trained and tested on a large dataset with 17 disturbance classes. Our experimental results show that the proposed ViT-based approach achieves PQD classification precision and recall of 98.28% and 97.98%, respectively, outperforming recently proposed techniques applied to the same dataset., Comment: IECON 2024-50th Annual Conference of the IEEE Industrial Electronics Society, Chicago, U.S.A, 2024, pp. 1-6

In this paper, we present new generalized wormhole (WH) solutions within the context of $f(R)$ gravity. Specifically, we focus on $f(R)$ gravitational theories formulated in the metric formalism, with our investigation centered on a power-law form represented by $f(R) = \epsilon R^{\chi}$. Here, $\epsilon$ is an arbitrary constant, and $\chi$ is a real number. Notably, this form possesses the advantageous property of reducing to Einstein gravity when $\epsilon=1$ and $\chi=1$. To obtain these novel WH solutions, we establish the general field equations for any $f(R)$ theory within the framework of Morris-Thorne spacetime, assuming metric coefficients that are independent of time. By utilizing an anisotropic matter source and a specific type of energy density associated with solitonic quantum wave (SQW) and cold dark matter (CDM) halos, we calculate two distinct WH solutions. We thoroughly investigate the properties of the exotic matter (ExoM) residing within the WH geometry and analyze the matter contents through energy conditions (ECs). Both analytical and graphical methods are employed in this analysis to examine the validity of different regions. Notably, the calculated shape functions for the WH geometry satisfy the necessary conditions in both scenarios, emphasizing their reliability. This ExoM is characterized by an energy-momentum tensor that violates the null energy condition (NEC) and, consequently, the weak energy condition as well, in the vicinity of the WH throats. Furthermore, we investigated the repulsive effect of gravity and discovered that its presence results in a negative deflection angle for photons following null geodesics. Importantly, we observed that the deflection angle consistently exhibits negative values across all $r_0$ values in both scenarios, indicating the manifestation of the repulsive gravity effect., Comment: Accepted for publication in the European Physical Journal C, 15 pages, 18 figures

We extend traditional complexity analyses of trust-region methods for unconstrained, possibly nonconvex, optimization. Whereas most complexity analyses assume uniform boundedness of the model Hessians, we work with potentially unbounded model Hessians. Boundedness is not guaranteed in practical implementations, in particular ones based on quasi-Newton updates such as PSB, BFGS and SR1. Our analysis is conducted for a family of trust-region methods that includes most known methods as special cases. We examine two regimes of Hessian growth: one bounded by a power of the number of successful iterations, and one bounded by a power of the number of iterations. This allows us to formalize and confirm the profound intuition of Powell [IMA J. Numer. Ana. 30(1):289-301,2010], who studied convergence under a special case of our assumptions, but whose proof contained complexity arguments. Specifically, for \(0 \leq p < 1\), we establish sharp \(O(\epsilon^{-2/(1-p)})\) evaluation complexity to find an \(\epsilon\)-stationary point when model Hessians are \(O(k^p)\), where \(k\) is the iteration counter. For \(p = 1\), which is the case studied by Powell, we establish a sharp \(O(\exp(c\epsilon^{-2}))\) evaluation complexity for a certain constant \(c > 0\). This is as Powell suspected and is far worse than other bounds surmised elsewhere in the literature. We establish similar bounds when model Hessians are \(O(|\mathcal{S}_k|^p)\), where \(|\mathcal{S}_k|\) is the number of iterations where the step was accepted, up to iteration \(k\). To the best of our knowledge, ours is the first work to provide complexity bounds when model Hessians grow linearly with \(|\mathcal{S}_k|\) or at most linearly with \(k\), which covers multiple quasi-Newton approximations.

Background. Fully automatic analysis of myocardial perfusion MRI datasets enables rapid and objective reporting of stress/rest studies in patients with suspected ischemic heart disease. Developing deep learning techniques that can analyze multi-center datasets despite limited training data and variations in software and hardware is an ongoing challenge. Methods. Datasets from 3 medical centers acquired at 3T (n = 150 subjects) were included: an internal dataset (inD; n = 95) and two external datasets (exDs; n = 55) used for evaluating the robustness of the trained deep neural network (DNN) models against differences in pulse sequence (exD-1) and scanner vendor (exD-2). A subset of inD (n = 85) was used for training/validation of a pool of DNNs for segmentation, all using the same spatiotemporal U-Net architecture and hyperparameters but with different parameter initializations. We employed a space-time sliding-patch analysis approach that automatically yields a pixel-wise "uncertainty map" as a byproduct of the segmentation process. In our approach, a given test case is segmented by all members of the DNN pool and the resulting uncertainty maps are leveraged to automatically select the "best" one among the pool of solutions. Results. The proposed DAUGS analysis approach performed similarly to the established approach on the internal dataset (p = n.s.) whereas it significantly outperformed on the external datasets (p < 0.005 for exD-1 and exD-2). Moreover, the number of image series with "failed" segmentation was significantly lower for the proposed vs. the established approach (4.3% vs. 17.1%, p < 0.0005). Conclusions. The proposed DAUGS analysis approach has the potential to improve the robustness of deep learning methods for segmentation of multi-center stress perfusion datasets with variations in the choice of pulse sequence, site location or scanner vendor., Comment: Accepted for publication in JCMR, 2024

In this article, we study the stochastic aggregation-diffusion equation with a singular drift represented by a monotone radial kernel. We demonstrate the existence and uniqueness of a diffusion process that acts as a weak solution to our equation. This process can be described as a distorted Brownian motion originating from a delocalized point. Utilizing Dirichlet form theory, we prove the existence of a weak solution for a quasi-everywhere point in a state space. However uniqueness is not assured for solutions commencing from points outside polar sets, and explicitly characterizing these sets poses a significant challenge. To address this, we employ the H_2-condition introduced by Albeverio et al.(2003). This condition provides a more thorough understanding of the uniqueness issue within the framework of Dirichlet forms. Consequently the H_2-condition is pivotal in enhancing the analysis of weak solutions, ensuring a more detailed comprehension of the problem. An explicit expression for the generalized Schr\"odinger operator associated with certain kernels is also provided.

Phase transitions in many-body systems are often associated with the emergence of spatial inhomogeneities. Such features may develop at microscopic lengthscales and are not necessarily evident in measurements of macroscopic quantities. In this work, we address the topic of distribution of current paths in superconducting films. Typical lengthscales associated with superconductivity are in the range of nanometres. Accordingly, measurements of electrical resistance over much larger distances are supposed to be insensitive to details of spatial inhomogeneities of electronic properties. We observe that, contrary to expectations, current paths adopt a highly non-uniform distribution at the onset of the superconducting transition which is manifested in the development of a finite transverse resistance. The anisotropic distribution of current density is unrelated to the structural properties of the superconducting films, and indicates the emergence of electronic inhomogeneities perceivable over macroscopic distances. Our experiments reveal the ubiquitous nature of this phenomenon in conventional superconductors.

Questions of `how best to acquire data' are essential to modeling and prediction in the natural and social sciences, engineering applications, and beyond. Optimal experimental design (OED) formalizes these questions and creates computational methods to answer them. This article presents a systematic survey of modern OED, from its foundations in classical design theory to current research involving OED for complex models. We begin by reviewing criteria used to formulate an OED problem and thus to encode the goal of performing an experiment. We emphasize the flexibility of the Bayesian and decision-theoretic approach, which encompasses information-based criteria that are well-suited to nonlinear and non-Gaussian statistical models. We then discuss methods for estimating or bounding the values of these design criteria; this endeavor can be quite challenging due to strong nonlinearities, high parameter dimension, large per-sample costs, or settings where the model is implicit. A complementary set of computational issues involves optimization methods used to find a design; we discuss such methods in the discrete (combinatorial) setting of observation selection and in settings where an exact design can be continuously parameterized. Finally we present emerging methods for sequential OED that build non-myopic design policies, rather than explicit designs; these methods naturally adapt to the outcomes of past experiments in proposing new experiments, while seeking coordination among all experiments to be performed. Throughout, we highlight important open questions and challenges., Comment: Appears in Acta Numerica 2024. This version contains an evolving set of post-publication additions and corrections

Although outdoor localization is already available to the general public and businesses through the wide spread use of the GPS, it is not supported by low-end phones, requires a direct line of sight to satellites and can drain phone battery quickly. The current fingerprinting solutions can provide high-accuracy localization but are based on the client side. This limits their ubiquitous deployment and accuracy. In this paper, we introduce DeepCell: a provider-side fingerprinting localization system that can provide high accuracy localization for any cell phone. To build its fingerprint, DeepCell leverages the unlabeled cellular measurements recorded by the cellular provider while opportunistically synchronizing with selected client devices to get location labels. The fingerprint is then used to train a deep neural network model that is harnessed for localization. To achieve this goal, DeepCell need to address a number of challenges including using unlabeled data from the provider side, handling noise and sparsity, scaling the data to large areas, and finally providing enough data that is required for training deep models without overhead. Evaluation of DeepCell in a typical realistic environment shows that it can achieve a consistent median accuracy of 29m. This accuracy outperforms the state-of-the-art client-based cellular-based systems by more than 75.4%. In addition, the same accuracy is extended to low-end phones., Comment: arXiv admin note: substantial text overlap with arXiv:2106.13632

Deep learning-based fingerprinting is one of the current promising technologies for outdoor localization in cellular networks. However, deploying such localization systems for heterogeneous phones affects their accuracy as the cellular received signal strength (RSS) readings vary for different types of phones. In this paper, we introduce a number of techniques for addressing the phones heterogeneity problem in the deep-learning based localization systems. The basic idea is either to approximate a function that maps the cellular RSS measurements between different devices or to transfer the knowledge across them. Evaluation of the proposed techniques using different Android phones on four independent testbeds shows that our techniques can improve the localization accuracy by more than 220% for the four testbeds as compared to the state-of-the-art systems. This highlights the promise of the proposed device heterogeneity handling techniques for enabling a wide deployment of deep learning-based localization systems over different devices.

Fingerprinting techniques are widely used for localization because of their accuracy, especially in the presence of wireless channel noise. However, the fingerprinting techniques require significant storage and running time, which is a concern when implementing such systems on a global worldwide scale. In this paper, we propose an efficient quantum Euclidean similarity algorithm for wireless localization systems. The proposed quantum algorithm offers exponentially improved complexity compared to its classical counterpart and even the state-of-the-art quantum localization systems, in terms of both storage space and running time. The basic idea is to entangle the test received signal strength (RSS) vector with the fingerprint vectors at different locations and perform the similarity calculation in parallel to all fingerprint locations. We give the details of how to construct the quantum fingerprint, how to encode the RSS measurements in quantum particles, and finally; present the quantum algorithm for calculating the Euclidean similarity between the online RSS measurements and the fingerprint ones. Implementation and evaluation of our algorithm in a real testbed using a real IBM quantum machine as well as a simulation for a larger testbed confirm its ability to correctly obtain the estimated location with an exponential enhancement in both time and space compared to the traditional classical fingerprinting techniques and the state-of-the-art quantum localization techniques.

Convolutional Neural Networks are particularly suited for image analysis tasks, such as Image Classification, Object Recognition or Image Segmentation. Like all Artificial Neural Networks, however, they are "black box" models, and suffer from poor explainability. This work is concerned with the specific downstream task of Emotion Recognition from images, and proposes a framework that combines CAM-based techniques with Object Detection on a corpus level to better understand on which image cues a particular model, in our case EmoNet, relies to assign a specific emotion to an image. We demonstrate that the model mostly focuses on human characteristics, but also explore the pronounced effect of specific image modifications., Comment: 10 pages, 7 figures

The Wasserstein space of probability measures is known for its intricate Riemannian structure, which underpins the Wasserstein geometry and enables gradient flow algorithms. However, the Wasserstein geometry may not be suitable for certain tasks or data modalities. Motivated by scenarios where the global structure of the data needs to be preserved, this work initiates the study of gradient flows and Riemannian structure in the Gromov-Wasserstein (GW) geometry, which is particularly suited for such purposes. We focus on the inner product GW (IGW) distance between distributions on $\mathbb{R}^d$. Given a functional $\mathsf{F}:\mathcal{P}_2(\mathbb{R}^d)\to\mathbb{R}$ to optimize, we present an implicit IGW minimizing movement scheme that generates a sequence of distributions $\{\rho_i\}_{i=0}^n$, which are close in IGW and aligned in the 2-Wasserstein sense. Taking the time step to zero, we prove that the discrete solution converges to an IGW generalized minimizing movement (GMM) $(\rho_t)_t$ that follows the continuity equation with a velocity field $v_t\in L^2(\rho_t;\mathbb{R}^d)$, specified by a global transformation of the Wasserstein gradient of $\mathsf{F}$. The transformation is given by a mobility operator that modifies the Wasserstein gradient to encode not only local information, but also global structure. Our gradient flow analysis leads us to identify the Riemannian structure that gives rise to the intrinsic IGW geometry, using which we establish a Benamou-Brenier-like formula for IGW. We conclude with a formal derivation, akin to the Otto calculus, of the IGW gradient as the inverse mobility acting on the Wasserstein gradient. Numerical experiments validating our theory and demonstrating the global nature of IGW interpolations are provided., Comment: 73 pages

Despite the significant advancements in computer vision models, their ability to generalize to novel object-attribute compositions remains limited. Existing methods for Compositional Zero-Shot Learning (CZSL) mainly focus on image classification. This paper aims to enhance CZSL in object detection without forgetting prior learned knowledge. We use Grounding DINO and incorporate Compositional Soft Prompting (CSP) into it and extend it with Compositional Anticipation. We achieve a 70.5% improvement over CSP on the harmonic mean (HM) between seen and unseen compositions on the CLEVR dataset. Furthermore, we introduce Contrastive Prompt Tuning to incrementally address model confusion between similar compositions. We demonstrate the effectiveness of this method and achieve an increase of 14.5% in HM across the pretrain, increment, and unseen sets. Collectively, these methods provide a framework for learning various compositions with limited data, as well as improving the performance of underperforming compositions when additional data becomes available.

The rhythmic pumping motion of the heart stands as a cornerstone in life, as it circulates blood to the entire human body through a series of carefully timed contractions of the individual chambers. Changes in the size, shape and movement of the chambers can be important markers for cardiac disease and modeling this in relation to clinical demography or disease is therefore of interest. Existing methods for spatio-temporal modeling of the human heart require shape correspondence over time or suffer from large memory requirements, making it difficult to use for complex anatomies. We introduce a novel conditional generative model, where the shape and movement is modeled implicitly in the form of a spatio-temporal neural distance field and conditioned on clinical demography. The model is based on an auto-decoder architecture and aims to disentangle the individual variations from that related to the clinical demography. It is tested on the left atrium (including the left atrial appendage), where it outperforms current state-of-the-art methods for anatomical sequence completion and generates synthetic sequences that realistically mimics the shape and motion of the real left atrium. In practice, this means we can infer functional measurements from a static image, generate synthetic populations with specified demography or disease and investigate how non-imaging clinical data effect the shape and motion of cardiac anatomies., Comment: Accepted for MICCAI2024

Foundation models (FMs) currently dominate news headlines. They employ advanced deep learning architectures to extract structural information autonomously from vast datasets through self-supervision. The resulting rich representations of complex systems and dynamics can be applied to many downstream applications. Therefore, FMs can find uses in electric power grids, challenged by the energy transition and climate change. In this paper, we call for the development of, and state why we believe in, the potential of FMs for electric grids. We highlight their strengths and weaknesses amidst the challenges of a changing grid. We argue that an FM learning from diverse grid data and topologies could unlock transformative capabilities, pioneering a new approach in leveraging AI to redefine how we manage complexity and uncertainty in the electric grid. Finally, we discuss a power grid FM concept, namely GridFM, based on graph neural networks and show how different downstream tasks benefit., Comment: Lead contact: H.F.H.; Major equal contributors: H.F.H., T.B., B.G., L.S.A.M., A.P., A.V., J.W.; Significant equal contributors: J.B., A.B.M., S.C., I.F., B.H., R.J., K.K., V.M., F.M., M.D.M., O.R., H.S., L.X., E.S.Y., A.Z.; Other equal contributors: A.J.B., R.J.B., B.P.B., J.S., S.S

Effective access points (APs) selection is a crucial step in localization systems. It directly affects both localization accuracy and computational efficiency. Classical APs selection algorithms are usually computationally expensive, hindering the deployment of localization systems in a large worldwide scale. In this paper, we introduce a quantum APs selection algorithm for large-scale localization systems. The proposed algorithm leverages quantum annealing to eliminate redundant and noisy APs. We explain how to formulate the APs selection problem as a quadratic unconstrained binary optimization (QUBO) problem, suitable for quantum annealing, and how to select the minimum number of APs that maintain the same overall localization system accuracy as the complete APs set. Based on this, we further propose a logarithmic-complexity algorithm to select the optimal number of APs. We implement our quantum algorithm on a real D-Wave Systems quantum machine and assess its performance in a real test environment for a floor localization problem. Our findings reveal that by selecting fewer than 14% of the available APs in the environment, our quantum algorithm achieves the same floor localization accuracy as utilizing the entire set of APs and a superior accuracy over utilizing the reduced dataset by classical APs selection counterparts. Moreover, the proposed quantum algorithm achieves more than an order of magnitude speedup over the corresponding classical APs selection algorithms, emphasizing the efficiency of the proposed quantum algorithm for large-scale localization systems.