Search

We present a benchmarking protocol that combines the characterization of boron nitride (BN) crystals and films with the evaluation of the electronic properties of graphene on these substrates. Our study includes hBN crystals grown under different conditions and scalable BN films deposited by either chemical or physical vapor deposition (CVD or PVD). We explore the complete process from boron nitride growth, over its optical characterization by time-resolved cathodoluminescence (TRCL), to the optical and electronic characterization of graphene by Raman spectroscopy after encapsulation and Hall bar processing. Within our benchmarking protocol we achieve a homogeneous electronic performance within each Hall bar device through a fast and reproducible processing routine. We find that a free exciton lifetime of 1 ns measured on as-grown hBN crystals by TRCL is sufficient to achieve high graphene room temperature charge carrier mobilities of 80,000 cm$^2$/(Vs) at a carrier density of |n| = 10$^{12}$ cm$^{-2}$, while respective exciton lifetimes around 100 ps yield mobilities up to 30,000 cm$^2$/(Vs). For scalable PVD-grown BN films, we measure carrier mobilities exceeding 10,000 cm$^2$/(Vs) which correlates with a graphene Raman 2D peak linewidth of 22 cm$^{-1}$. Our work highlights the importance of the Raman 2D linewidth of graphene as a critical metric that effectively assesses the interface quality (i.e. surface roughness) to the BN substrate, which directly affects the charge carrier mobility of graphene. Graphene 2D linewidth analysis is suitable for all BN substrates and is particularly advantageous when TRCL or BN Raman spectroscopy cannot be applied to specific BN materials such as amorphous or thin films. This underlines the superior role of spatially-resolved spectroscopy in the evaluation of BN crystals and films for the use of high-mobility graphene devices., Comment: 18 pages, 11 figures

The Euclid mission will measure cosmological parameters with unprecedented precision. To distinguish between cosmological models, it is essential to generate realistic mock observables from cosmological simulations that were run in both the standard $\Lambda$-cold-dark-matter ($\Lambda$CDM) paradigm and in many non-standard models beyond $\Lambda$CDM. We present the scientific results from a suite of cosmological N-body simulations using non-standard models including dynamical dark energy, k-essence, interacting dark energy, modified gravity, massive neutrinos, and primordial non-Gaussianities. We investigate how these models affect the large-scale-structure formation and evolution in addition to providing synthetic observables that can be used to test and constrain these models with Euclid data. We developed a custom pipeline based on the Rockstar halo finder and the nbodykit large-scale structure toolkit to analyse the particle output of non-standard simulations and generate mock observables such as halo and void catalogues, mass density fields, and power spectra in a consistent way. We compare these observables with those from the standard $\Lambda$CDM model and quantify the deviations. We find that non-standard cosmological models can leave significant imprints on the synthetic observables that we have generated. Our results demonstrate that non-standard cosmological N-body simulations provide valuable insights into the physics of dark energy and dark matter, which is essential to maximising the scientific return of Euclid., Comment: 22 pages, 7 figures

To constrain models beyond $\Lambda$CDM, the development of the Euclid analysis pipeline requires simulations that capture the nonlinear phenomenology of such models. We present an overview of numerical methods and $N$-body simulation codes developed to study the nonlinear regime of structure formation in alternative dark energy and modified gravity theories. We review a variety of numerical techniques and approximations employed in cosmological $N$-body simulations to model the complex phenomenology of scenarios beyond $\Lambda$CDM. This includes discussions on solving nonlinear field equations, accounting for fifth forces, and implementing screening mechanisms. Furthermore, we conduct a code comparison exercise to assess the reliability and convergence of different simulation codes across a range of models. Our analysis demonstrates a high degree of agreement among the outputs of different simulation codes, providing confidence in current numerical methods for modelling cosmic structure formation beyond $\Lambda$CDM. We highlight recent advances made in simulating the nonlinear scales of structure formation, which are essential for leveraging the full scientific potential of the forthcoming observational data from the Euclid mission., Comment: 20 pages, 7 figures, 1 appendix; submitted on behalf of the Euclid Collaboration

Both real and virtual photons can be involved in light-matter interactions. A famous example of the observable implications of virtual photons -- vacuum fluctuations of the quantum electromagnetic field -- is the Casimir effect. Since quantum vacuum effects are weak, various mechanisms have been proposed to enhance and engineer them, ranging from static, e.g., strong optical resonances, to dynamic, e.g., systems with moving boundaries or time-varying optical properties, or a combination of them. In this Letter, we discuss the role of material nonlocality (spatial dispersion) in dynamical Casimir effects in time-varying frequency-dispersive nanophotonic systems. We first show that local models may lead to nonphysical predictions, such as diverging emission rates of entangled polariton pairs. We then theoretically demonstrate that nonlocality regularizes this behavior by correcting the asymptotic response of the system for large wavevectors and reveals physical effects missed by local models, including a significant broadening of the emission rate distribution, which are relevant for future experimental observations. Our work sheds light on the importance of nonlocal effects in this new frontier of nanophotonics.

Many languages have vast amounts of handwritten texts, such as ancient scripts about folktale stories and historical narratives or contemporary documents and letters. Digitization of those texts has various applications, such as daily tasks, cultural studies, and historical research. Syriac is an ancient, endangered, and low-resourced language that has not received the attention it requires and deserves. This paper reports on a research project aimed at developing a optical character recognition (OCR) model based on the handwritten Syriac texts as a starting point to build more digital services for this endangered language. A dataset was created, KHAMIS (inspired by the East Syriac poet, Khamis bar Qardahe), which consists of handwritten sentences in the East Syriac script. We used it to fine-tune the Tesseract-OCR engine's pretrained Syriac model on handwritten data. The data was collected from volunteers capable of reading and writing in the language to create KHAMIS. KHAMIS currently consists of 624 handwritten Syriac sentences collected from 31 university students and one professor, and it will be partially available online and the whole dataset available in the near future for development and research purposes. As a result, the handwritten OCR model was able to achieve a character error rate of 1.097-1.610% and 8.963-10.490% on both training and evaluation sets, respectively, and both a character error rate of 18.89-19.71% and a word error rate of 62.83-65.42% when evaluated on the test set, which is twice as better than the default Syriac model of Tesseract., Comment: 15 pages, 12 figures, 5 tables

This thesis presents and evaluates the Dilated Convolution with Learnable Spacings (DCLS) method. Through various supervised learning experiments in the fields of computer vision, audio, and speech processing, the DCLS method proves to outperform both standard and advanced convolution techniques. The research is organized into several steps, starting with an analysis of the literature and existing convolution techniques that preceded the development of the DCLS method. We were particularly interested in the methods that are closely related to our own and that remain essential to capture the nuances and uniqueness of our approach. The cornerstone of our study is the introduction and application of the DCLS method to convolutional neural networks (CNNs), as well as to hybrid architectures that rely on both convolutional and visual attention approaches. DCLS is shown to be particularly effective in tasks such as classification, semantic segmentation, and object detection. Initially using bilinear interpolation, the study also explores other interpolation methods, finding that Gaussian interpolation slightly improves performance. The DCLS method is further applied to spiking neural networks (SNNs) to enable synaptic delay learning within a neural network that could eventually be transferred to so-called neuromorphic chips. The results show that the DCLS method stands out as a new state-of-the-art technique in SNN audio classification for certain benchmark tasks in this field. These tasks involve datasets with a high temporal component. In addition, we show that DCLS can significantly improve the accuracy of artificial neural networks for the multi-label audio classification task. We conclude with a discussion of the chosen experimental setup, its limitations, the limitations of our method, and our results., Comment: PhD Thesis

Dilated Convolution with Learnable Spacing (DCLS) is a recent advanced convolution method that allows enlarging the receptive fields (RF) without increasing the number of parameters, like the dilated convolution, yet without imposing a regular grid. DCLS has been shown to outperform the standard and dilated convolutions on several computer vision benchmarks. Here, we show that, in addition, DCLS increases the models' interpretability, defined as the alignment with human visual strategies. To quantify it, we use the Spearman correlation between the models' GradCAM heatmaps and the ClickMe dataset heatmaps, which reflect human visual attention. We took eight reference models - ResNet50, ConvNeXt (T, S and B), CAFormer, ConvFormer, and FastViT (sa 24 and 36) - and drop-in replaced the standard convolution layers with DCLS ones. This improved the interpretability score in seven of them. Moreover, we observed that Grad-CAM generated random heatmaps for two models in our study: CAFormer and ConvFormer models, leading to low interpretability scores. We addressed this issue by introducing Threshold-Grad-CAM, a modification built on top of Grad-CAM that enhanced interpretability across nearly all models. The code and checkpoints to reproduce this study are available at: https://github.com/rabihchamas/DCLS-GradCAM-Eval., Comment: Accepted at The Trustworthy AI Workshop, IJCAI 2024

We treat privacy in a network of quantum sensors where accessible information is limited to specific functions of the network parameters, and all other information remains private. We develop an analysis of privacy in terms of a manipulation of the quantum Fisher information matrix, and find the optimal state achieving maximum privacy in the estimation of linear combination of the unknown parameters in a network of quantum sensors. We also discuss the effect of uncorrelated noise on the privacy of the network. Moreover, we illustrate our results with an example where the goal is to estimate the average value of the unknown parameters in the network. In this example, we also introduce the notion of quasi-privacy ($\epsilon$-privacy), quantifying how close the state is to being private., Comment: 10 pages, 1 figures

Distributed quantum sensing enables the estimation of multiple parameters encoded in spatially separated probes. While traditional quantum sensing is often focused on estimating a single parameter with maximum precision, distributed quantum sensing seeks to estimate some function of multiple parameters that are only locally accessible for each party involved. In such settings it is natural to not want to give away more information than is necessary. To address this, we use the concept of privacy with respect to a function, ensuring that only information about the target function is available to all the parties, and no other information. We define a measure of privacy (essentially how close we are to this condition being satisfied), and show it satisfies a set of naturally desirable properties of such a measure. Using this privacy measure, we identify and construct entangled resources states that ensure privacy for a given function under different resource distributions and encoding dynamics, characterized by Hamiltonian evolution. For separable and parallel Hamiltonians, we prove that the GHZ state is the only private state for certain linear functions, with the minimum amount of required resources, up to SLOCC. Recognizing the vulnerability of this state to particle loss, we create families of private states, that remain robust even against loss of qubits, by incorporating additional resources. We then extend our findings to different resource distribution scenarios and Hamiltonians, resulting in a comprehensive set of private and robust states for distributed quantum estimation. These results advance the understanding of privacy and robustness in multi-parameter quantum sensing., Comment: Keywords: Quantum Sensing, GHZ states, Private Sensing, Quantum Information

A fundamental challenge in federated learning lies in mixing heterogeneous datasets and classification tasks while minimizing the high communication cost caused by clients as well as the exchange of weight updates with the server over a fixed number of rounds. This results in divergent model convergence rates and performance, which may hinder their deployment in precision medicine. In real-world scenarios, client data is collected from different hospitals with extremely varying components (e.g., imaging modality, organ type, etc). Previous studies often overlooked the convoluted heterogeneity during the training stage where the target learning tasks vary across clients as well as the dataset type and their distributions. To address such limitations, we unprecedentedly introduce UniFed, a universal federated learning paradigm that aims to classify any disease from any imaging modality. UniFed also handles the issue of varying convergence times in the client-specific optimization based on the complexity of their learning tasks. Specifically, by dynamically adjusting both local and global models, UniFed considers the varying task complexities of clients and the server, enhancing its adaptability to real-world scenarios, thereby mitigating issues related to overtraining and excessive communication. Furthermore, our framework incorporates a sequential model transfer mechanism that takes into account the diverse tasks among hospitals and a dynamic task-complexity based ordering. We demonstrate the superiority of our framework in terms of accuracy, communication cost, and convergence time over relevant benchmarks in diagnosing retina, histopathology, and liver tumour diseases under federated learning. Our UniFed code is available at https://github.com/basiralab/UniFed., Comment: MLMI@MICCAI 2024

Watermarking is a technique used to embed a hidden signal in the probability distribution of text generated by large language models (LLMs), enabling attribution of the text to the originating model. We introduce smoothing attacks and show that existing watermarking methods are not robust against minor modifications of text. An adversary can use weaker language models to smooth out the distribution perturbations caused by watermarks without significantly compromising the quality of the generated text. The modified text resulting from the smoothing attack remains close to the distribution of text that the original model (without watermark) would have produced. Our attack reveals a fundamental limitation of a wide range of watermarking techniques.

Conditional validity and length efficiency are two crucial aspects of conformal prediction (CP). Achieving conditional validity ensures accurate uncertainty quantification for data subpopulations, while proper length efficiency ensures that the prediction sets remain informative and non-trivial. Despite significant efforts to address each of these issues individually, a principled framework that reconciles these two objectives has been missing in the CP literature. In this paper, we develop Conformal Prediction with Length-Optimization (CPL) - a novel framework that constructs prediction sets with (near-) optimal length while ensuring conditional validity under various classes of covariate shifts, including the key cases of marginal and group-conditional coverage. In the infinite sample regime, we provide strong duality results which indicate that CPL achieves conditional validity and length optimality. In the finite sample regime, we show that CPL constructs conditionally valid prediction sets. Our extensive empirical evaluations demonstrate the superior prediction set size performance of CPL compared to state-of-the-art methods across diverse real-world and synthetic datasets in classification, regression, and text-related settings.

Testing gravity and the concordance model of cosmology, $\Lambda$CDM, at large scales is a key goal of this decade's largest galaxy surveys. Here we present a comparative study of dark matter power spectrum predictions from different numerical codes in the context of three popular theories of gravity that induce scale-independent modifications to the linear growth of structure: nDGP, Cubic Galileon and K-mouflage. In particular, we compare the predictions from full $N$-body simulations, two $N$-body codes with approximate time integration schemes, a parametrised modified $N$-body implementation and the analytic halo model reaction approach. We find the modification to the $\Lambda$CDM spectrum is in $2\%$ agreement for $z\leq1$ and $k\leq 1~h/{\rm Mpc}$ over all gravitational models and codes, in accordance with many previous studies, indicating these modelling approaches are robust enough to be used in forthcoming survey analyses under appropriate scale cuts. We further make public the new code implementations presented, specifically the halo model reaction K-mouflage implementation and the relativistic Cubic Galileon implementation., Comment: 20 pages, 4 figures, 4 tables

Large Language Models (LLMs) are rapidly evolving and impacting various fields, necessitating the development of effective methods to evaluate and compare their performance. Most current approaches for performance evaluation are either based on fixed, domain-specific questions that lack the flexibility required in many real-world applications where tasks are not always from a single domain, or rely on human input, making them unscalable. We propose an automated benchmarking framework based on debates between LLMs, judged by another LLM. This method assesses not only domain knowledge, but also skills such as problem definition and inconsistency recognition. We evaluate the performance of various state-of-the-art LLMs using the debate framework and achieve rankings that align closely with popular rankings based on human input, eliminating the need for costly human crowdsourcing.

Recent progress in large language models enables the creation of realistic machine-generated content. Watermarking is a promising approach to distinguish machine-generated text from human text, embedding statistical signals in the output that are ideally undetectable to humans. We propose a watermarking framework that encodes such signals through an error correcting code. Our method, termed robust binary code (RBC) watermark, introduces no distortion compared to the original probability distribution, and no noticeable degradation in quality. We evaluate our watermark on base and instruction fine-tuned models and find our watermark is robust to edits, deletions, and translations. We provide an information-theoretic perspective on watermarking, a powerful statistical test for detection and for generating p-values, and theoretical guarantees. Our empirical findings suggest our watermark is fast, powerful, and robust, comparing favorably to the state-of-the-art.

In today's world, the Internet is recognized as one of the essentials of human life, playing a significant role in communications, business, and lifestyle. The quality of internet services can have widespread negative impacts on individual and social levels. Consequently, Quality of Service (QoS) has become a fundamental necessity for service providers in a competitive market aiming to offer superior services. The success and survival of these providers depend on their ability to maintain high service quality and ensure satisfaction.Alongside QoS, the concept of Quality of Experience (QoE) has emerged with the development of telephony networks. QoE focuses on the user's satisfaction with the service, helping operators adjust their services to meet user expectations. Recent research shows a trend towards utilizing machine learning and deep learning techniques to predict QoE. Researchers aim to develop accurate models by leveraging large volumes of data from network and user interactions, considering various real-world scenarios. Despite the complexity of network environments, this research provides a practical framework for improving and evaluating QoE. This study presents a comprehensive framework for evaluating QoE in multimedia services, adhering to the ITU-T P.1203 standard which includes automated data collection processes and uses machine learning algorithms to predict user satisfaction based on key network parameters. By collecting over 20,000 data records from different network conditions and users, the Random Forest model achieved a prediction accuracy of 95.8% for user satisfaction. This approach allows operators to dynamically allocate network resources in real-time, maintaining high levels of customer satisfaction with minimal costs., Comment: 11 pages, 5 figures

Despite the success of Transformers on language understanding, code generation, and logical reasoning, they still fail to generalize over length on basic arithmetic tasks such as addition and multiplication. A major reason behind this failure is the vast difference in structure between numbers and text; For example, the numbers are typically parsed from right to left, and there is a correspondence between digits at the same position across different numbers. In contrast, for text, such symmetries are quite unnatural. In this work, we propose to encode these semantics explicitly into the model via modified number formatting and custom positional encodings. Empirically, our method allows a Transformer trained on numbers with at most 5-digits for addition and multiplication to generalize up to 50-digit numbers, without using additional data for longer sequences. We further demonstrate that traditional absolute positional encodings (APE) fail to generalize to longer sequences, even when trained with augmented data that captures task symmetries. To elucidate the importance of explicitly encoding structure, we prove that explicit incorporation of structure via positional encodings is necessary for out-of-distribution generalization. Finally, we pinpoint other challenges inherent to length generalization beyond capturing symmetries, in particular complexity of the underlying task, and propose changes in the training distribution to address them., Comment: 32 pages, 16 figures

The growing safety concerns surrounding Large Language Models (LLMs) raise an urgent need to align them with diverse human preferences to simultaneously enhance their helpfulness and safety. A promising approach is to enforce safety constraints through Reinforcement Learning from Human Feedback (RLHF). For such constrained RLHF, common Lagrangian-based primal-dual policy optimization methods are computationally expensive and often unstable. This paper presents a dualization perspective that reduces constrained alignment to an equivalent unconstrained alignment problem. We do so by pre-optimizing a smooth and convex dual function that has a closed form. This shortcut eliminates the need for cumbersome primal-dual policy iterations, thus greatly reducing the computational burden and improving training stability. Our strategy leads to two practical algorithms in model-based and preference-based scenarios (MoCAN and PeCAN, respectively). A broad range of experiments demonstrate the effectiveness of our methods.

In this paper, we study a nonlinear spiked random matrix model where a nonlinear function is applied element-wise to a noise matrix perturbed by a rank-one signal. We establish a signal-plus-noise decomposition for this model and identify precise phase transitions in the structure of the signal components at critical thresholds of signal strength. To demonstrate the applicability of this decomposition, we then utilize it to study new phenomena in the problems of signed signal recovery in nonlinear models and community detection in transformed stochastic block models. Finally, we validate our results through a series of numerical simulations.

The current standard model of cosmology successfully describes a variety of measurements, but the nature of its main ingredients, dark matter and dark energy, remains unknown. Euclid is a medium-class mission in the Cosmic Vision 2015-2025 programme of the European Space Agency (ESA) that will provide high-resolution optical imaging, as well as near-infrared imaging and spectroscopy, over about 14,000 deg^2 of extragalactic sky. In addition to accurate weak lensing and clustering measurements that probe structure formation over half of the age of the Universe, its primary probes for cosmology, these exquisite data will enable a wide range of science. This paper provides a high-level overview of the mission, summarising the survey characteristics, the various data-processing steps, and data products. We also highlight the main science objectives and expected performance., Comment: Paper submitted as part of the A&A special issue`Euclid on Sky'

The Super-Kamiokande and T2K collaborations present a joint measurement of neutrino oscillation parameters from their atmospheric and beam neutrino data. It uses a common interaction model for events overlapping in neutrino energy and correlated detector systematic uncertainties between the two datasets, which are found to be compatible. Using 3244.4 days of atmospheric data and a beam exposure of $19.7(16.3) \times 10^{20}$ protons on target in (anti)neutrino mode, the analysis finds a 1.9$\sigma$ exclusion of CP-conservation (defined as $J_{CP}=0$) and a preference for the normal mass ordering., Comment: 10 pages, 3 figures

We build an emulator based on the polynomial chaos expansion (PCE) technique to efficiently model the non-linear effects associated with the clustering of the $k$-essence dark energy in the effective field theory (EFT) framework. These effects can be described through a modification of Poisson's equation, denoted by the function $\mu(k,z)$, which in general depends on wavenumber $k$ and redshift $z$. To emulate this function, we perform $200$ high-resolution $N$-body simulations sampled from a seven-dimensional parameter space with the Latin hypercube method. These simulations are executed using the $\texttt{k-evolution}$ code on a fixed mesh, containing $1200^3$ dark matter particles within a box size of $400~\text{Mpc}/ h$. The emulation process has been carried out within $\texttt{UQLab}$, a $\texttt{MATLAB}$-based software specifically dedicated to emulation and uncertainty quantification tasks. Apart from its role in emulation, the PCE method also facilitates the measurement of Sobol indices, enabling us to assess the relative impact of each cosmological parameter on the $\mu$ function. Our results show that the PCE-based emulator efficiently and accurately reflects the behavior of the $k$-essence dark energy for the cosmological parameter space defined by $w_0 c_s^2 \text{CDM} +\sum m_{\nu}$. Compared against actual simulations, the emulator achieves sub-percent accuracy up to the wavenumber $k \approx 9.4 ~h \text{Mpc}^{-1} $ for redshifts $z \leq 3$. Our emulator provides an efficient and reliable tool for Markov chain Monte Carlo (MCMC) analysis, and its capability to closely mimic the properties of the $k$-essence dark energy makes it a crucial component in Bayesian parameter estimations. The code is publicly available at https://github.com/anourizo/k-emulator ., Comment: 21 pages, 16 figures, 4 tables

A new degravitation mechanism within the framework of scalar tensor gravity is proposed. The mechanism eliminates all constant contributions from the potential to the Friedmann equation, leaving only the kinematic and the dynamic terms of the potential to drive cosmic acceleration. We explore a scenario involving a density-triggered phase transition in the late-time universe, and argue that the resulting effective energy density and equation of state parameter can explain late-time cosmology when extrapolated to a region of the parameter space., Comment: 5 pages, 2 figures

This research explores the application of Large Language Models (LLMs) for automating the extraction of requirement-related legal content in the food safety domain and checking legal compliance of regulatory artifacts. With Industry 4.0 revolutionizing the food industry and with the General Data Protection Regulation (GDPR) reshaping privacy policies and data processing agreements, there is a growing gap between regulatory analysis and recent technological advancements. This study aims to bridge this gap by leveraging LLMs, namely BERT and GPT models, to accurately classify legal provisions and automate compliance checks. Our findings demonstrate promising results, indicating LLMs' significant potential to enhance legal compliance and regulatory analysis efficiency, notably by reducing manual workload and improving accuracy within reasonable time and financial constraints., Comment: to be published in 32nd IEEE International Requirements Engineering 2024 Conference (RE'24) - Doctoral Symposium. arXiv admin note: text overlap with arXiv:2404.14356

In this paper, we focus on the problem of conformal prediction with conditional guarantees. Prior work has shown that it is impossible to construct nontrivial prediction sets with full conditional coverage guarantees. A wealth of research has considered relaxations of full conditional guarantees, relying on some predefined uncertainty structures. Departing from this line of thinking, we propose Partition Learning Conformal Prediction (PLCP), a framework to improve conditional validity of prediction sets through learning uncertainty-guided features from the calibration data. We implement PLCP efficiently with alternating gradient descent, utilizing off-the-shelf machine learning models. We further analyze PLCP theoretically and provide conditional guarantees for infinite and finite sample sizes. Finally, our experimental results over four real-world and synthetic datasets show the superior performance of PLCP compared to state-of-the-art methods in terms of coverage and length in both classification and regression scenarios.

Widely available measurement equipment in electrical distribution grids, such as power-quality measurement devices, substation meters, or customer smart meters do not provide phasor measurements due to the lack of high resolution time synchronisation. Instead such measurement devices allow to obtain magnitudes of voltages and currents and the local phase angle between those. In addition, these measurements are subject to measurement errors of up to few percent of the measurand. In order to utilize such measurements for grid monitoring, this paper presents and assesses a stochastic grid calculation approach that allows to derive confidence regions for the resulting current and voltage phasors. Two different metering models are introduced: a PMU model, which is used to validate theoretical properties of the estimator, and an Electric Meter model for which a Gaussian approximation is introduced. The estimator results are compared for the two meter models and case study results for a real Danish distribution grid are presented.

As software-intensive systems face growing pressure to comply with laws and regulations, providing automated support for compliance analysis has become paramount. Despite advances in the Requirements Engineering (RE) community on legal compliance analysis, important obstacles remain in developing accurate and generalizable compliance automation solutions. This paper highlights some observed limitations of current approaches and examines how adopting new automation strategies that leverage Large Language Models (LLMs) can help address these shortcomings and open up fresh opportunities. Specifically, we argue that the examination of (textual) legal artifacts should, first, employ a broader context than sentences, which have widely been used as the units of analysis in past research. Second, the mode of analysis with legal artifacts needs to shift from classification and information extraction to more end-to-end strategies that are not only accurate but also capable of providing explanation and justification. We present a compliance analysis approach designed to address these limitations. We further outline our evaluation plan for the approach and provide preliminary evaluation results based on data processing agreements (DPAs) that must comply with the General Data Protection Regulation (GDPR). Our initial findings suggest that our approach yields substantial accuracy improvements and, at the same time, provides justification for compliance decisions., Comment: Accepted for publication at the RE@Next! track of RE 2024

We report on adiabatic state preparation in the one-dimensional quantum Ising model using ultracold bosons in a tilted optical lattice. We prepare many-body ground states of controllable system sizes and observe enhanced fluctuations around the transition between paramagnetic and antiferromagnetic states, marking the precursor of quantum critical behavior. Furthermore, we find evidence for superpositions of domain walls and study their effect on the many-body ground state by measuring the populations of each spin configuration across the transition. These results shed new light on the effect of boundary conditions in finite-size quantum systems., Comment: 5+5 pages, 4+8 figures

Kurdish libraries have many historical publications that were printed back in the early days when printing devices were brought to Kurdistan. Having a good Optical Character Recognition (OCR) to help process these publications and contribute to the Kurdish languages resources which is crucial as Kurdish is considered a low-resource language. Current OCR systems are unable to extract text from historical documents as they have many issues, including being damaged, very fragile, having many marks left on them, and often written in non-standard fonts and more. This is a massive obstacle in processing these documents as currently processing them requires manual typing which is very time-consuming. In this study, we adopt an open-source OCR framework by Google, Tesseract version 5.0, that has been used to extract text for various languages. Currently, there is no public dataset, and we developed our own by collecting historical documents from Zheen Center for Documentation and Research, which were printed before 1950 and resulted in a dataset of 1233 images of lines with transcription of each. Then we used the Arabic model as our base model and trained the model using the dataset. We used different methods to evaluate our model, Tesseracts built-in evaluator lstmeval indicated a Character Error Rate (CER) of 0.755%. Additionally, Ocreval demonstrated an average character accuracy of 84.02%. Finally, we developed a web application to provide an easy- to-use interface for end-users, allowing them to interact with the model by inputting an image of a page and extracting the text. Having an extensive dataset is crucial to develop OCR systems with reasonable accuracy, as currently, no public datasets are available for historical Kurdish documents; this posed a significant challenge in our work. Additionally, the unaligned spaces between characters and words proved another challenge with our work., Comment: 30 pages, 21 figures, 2 tables

Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs. In addition to verbalized confidence elicited via prompting, many uncertainty measures ($e.g.$, semantic entropy and affinity-graph-based measures) have been proposed. However, these measures can differ greatly, and it is unclear how to compare them, partly because they take values over different ranges ($e.g.$, $[0,\infty)$ or $[0,1]$). In this work, we address this issue by developing a novel and practical framework, termed $Rank$-$Calibration$, to assess uncertainty and confidence measures for LMs. Our key tenet is that higher uncertainty (or lower confidence) should imply lower generation quality, on average. Rank-calibration quantifies deviations from this ideal relationship in a principled manner, without requiring ad hoc binary thresholding of the correctness score ($e.g.$, ROUGE or METEOR). The broad applicability and the granular interpretability of our methods are demonstrated empirically.

Classifying Sorani Kurdish subdialects poses a challenge due to the need for publicly available datasets or reliable resources like social media or websites for data collection. We conducted field visits to various cities and villages to address this issue, connecting with native speakers from different age groups, genders, academic backgrounds, and professions. We recorded their voices while engaging in conversations covering diverse topics such as lifestyle, background history, hobbies, interests, vacations, and life lessons. The target area of the research was the Kurdistan Region of Iraq. As a result, we accumulated 29 hours, 16 minutes, and 40 seconds of audio recordings from 107 interviews, constituting an unbalanced dataset encompassing six subdialects. Subsequently, we adapted three deep learning models: ANN, CNN, and RNN-LSTM. We explored various configurations, including different track durations, dataset splitting, and imbalanced dataset handling techniques such as oversampling and undersampling. Two hundred and twenty-five(225) experiments were conducted, and the outcomes were evaluated. The results indicated that the RNN-LSTM outperforms the other methods by achieving an accuracy of 96%. CNN achieved an accuracy of 93%, and ANN 75%. All three models demonstrated improved performance when applied to balanced datasets, primarily when we followed the oversampling approach. Future studies can explore additional future research directions to include other Kurdish dialects., Comment: 30 pages, 25 figures, 6 tables

Jailbreak attacks cause large language models (LLMs) to generate harmful, unethical, or otherwise objectionable content. Evaluating these attacks presents a number of challenges, which the current collection of benchmarks and evaluation techniques do not adequately address. First, there is no clear standard of practice regarding jailbreaking evaluation. Second, existing works compute costs and success rates in incomparable ways. And third, numerous works are not reproducible, as they withhold adversarial prompts, involve closed-source code, or rely on evolving proprietary APIs. To address these challenges, we introduce JailbreakBench, an open-sourced benchmark with the following components: (1) an evolving repository of state-of-the-art adversarial prompts, which we refer to as jailbreak artifacts; (2) a jailbreaking dataset comprising 100 behaviors -- both original and sourced from prior work (Zou et al., 2023; Mazeika et al., 2023, 2024) -- which align with OpenAI's usage policies; (3) a standardized evaluation framework at https://github.com/JailbreakBench/jailbreakbench that includes a clearly defined threat model, system prompts, chat templates, and scoring functions; and (4) a leaderboard at https://jailbreakbench.github.io/ that tracks the performance of attacks and defenses for various LLMs. We have carefully considered the potential ethical implications of releasing this benchmark, and believe that it will be a net positive for the community., Comment: JailbreakBench v1.0: more attack artifacts, more test-time defenses, a more accurate jailbreak judge (Llama-3-70B with a custom prompt), a larger dataset of human preferences for selecting a jailbreak judge (300 examples), an over-refusal evaluation dataset (100 benign/borderline behaviors), a semantic refusal judge based on Llama-3-8B

Prompt engineering is effective for controlling the output of text-to-image (T2I) generative models, but it is also laborious due to the need for manually crafted prompts. This challenge has spurred the development of algorithms for automated prompt generation. However, these methods often struggle with transferability across T2I models, require white-box access to the underlying model, and produce non-intuitive prompts. In this work, we introduce PRISM, an algorithm that automatically identifies human-interpretable and transferable prompts that can effectively generate desired concepts given only black-box access to T2I models. Inspired by large language model (LLM) jailbreaking, PRISM leverages the in-context learning ability of LLMs to iteratively refine the candidate prompts distribution for given reference images. Our experiments demonstrate the versatility and effectiveness of PRISM in generating accurate prompts for objects, styles and images across multiple T2I models, including Stable Diffusion, DALL-E, and Midjourney.

Gate-tunable transmons (gatemons) employing semiconductor Josephson junctions have recently emerged as building blocks for hybrid quantum circuits. In this study, we present a gatemon fabricated in planar Germanium. We induce superconductivity in a two-dimensional hole gas by evaporating aluminum atop a thin spacer, which separates the superconductor from the Ge quantum well. The Josephson junction is then integrated into an Xmon circuit and capacitively coupled to a transmission line resonator. We showcase the qubit tunability in a broad frequency range with resonator and two-tone spectroscopy. Time-domain characterizations reveal energy relaxation and coherence times up to 75 ns. Our results, combined with the recent advances in the spin qubit field, pave the way towards novel hybrid and protected qubits in a group IV, CMOS-compatible material.

This paper introduces and defines a novel concept in sustainable investing, termed crosswashing, and explore its impact on ESG (Environmental, Social, and Governance) ratings through quantitative analysis using a Multi-Criteria Decision Making (MCDM) model. The study emphasises that this specific form of greenwashing is not currently considered in existing ESG assessments, potentially leading to an inflated perception of corporate ethical practices. Unlike traditional greenwashing, crosswashing involves companies strategically investing in sustainable activities to boost Environmental, Social, and Governance (ESG) scores while preserving nonsustainable core operations. By unveiling the nuances of crosswashing, the research contributes to a more nuanced understanding of sustainable investing, offering insights for improved evaluation and regulation of corporate environmental and ethical responsibilities.

Neural compression has brought tremendous progress in designing lossy compressors with good rate-distortion (RD) performance at low complexity. Thus far, neural compression design involves transforming the source to a latent vector, which is then rounded to integers and entropy coded. While this approach has been shown to be optimal in a one-shot sense on certain sources, we show that it is highly sub-optimal on i.i.d. sequences, and in fact always recovers scalar quantization of the original source sequence. We demonstrate that the sub-optimality is due to the choice of quantization scheme in the latent space, and not the transform design. By employing lattice quantization instead of scalar quantization in the latent space, we demonstrate that Lattice Transform Coding (LTC) is able to recover optimal vector quantization at various dimensions and approach the asymptotically-achievable rate-distortion function at reasonable complexity. On general vector sources, LTC improves upon standard neural compressors in one-shot coding performance. LTC also enables neural compressors that perform block coding on i.i.d. vector sources, which yields coding gain over optimal one-shot coding.

Neighborhood attention reduces the cost of self attention by restricting each token's attention span to its nearest neighbors. This restriction, parameterized by a window size and dilation factor, draws a spectrum of possible attention patterns between linear projection and self attention. Neighborhood attention, and more generally sliding window attention patterns, have long been bounded by infrastructure, particularly in higher-rank spaces (2-D and 3-D), calling for the development of custom kernels, which have been limited in either functionality, or performance, if not both. In this work, we first show that neighborhood attention can be represented as a batched GEMM problem, similar to standard attention, and implement it for 1-D and 2-D neighborhood attention. These kernels on average provide 895% and 272% improvement in full precision latency compared to existing naive kernels for 1-D and 2-D neighborhood attention respectively. We find certain inherent inefficiencies in all unfused neighborhood attention kernels that bound their performance and lower-precision scalability. We also developed fused neighborhood attention; an adaptation of fused dot-product attention kernels that allow fine-grained control over attention across different spatial axes. Known for reducing the quadratic time complexity of self attention to a linear complexity, neighborhood attention can now enjoy a reduced and constant memory footprint, and record-breaking half precision latency. We observe that our fused kernels successfully circumvent some of the unavoidable inefficiencies in unfused implementations. While our unfused GEMM-based kernels only improve half precision performance compared to naive kernels by an average of 496% and 113% in 1-D and 2-D problems respectively, our fused kernels improve naive kernels by an average of 1607% and 581% in 1-D and 2-D problems respectively., Comment: Project page: https://github.com/SHI-Labs/NATTEN

Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While initial defenses show promise against token-based threat models, there do not exist defenses that provide robustness against semantic attacks and avoid unfavorable trade-offs between robustness and nominal performance. To meet this need, we propose SEMANTICSMOOTH, a smoothing-based defense that aggregates the predictions of multiple semantically transformed copies of a given input prompt. Experimental results demonstrate that SEMANTICSMOOTH achieves state-of-the-art robustness against GCG, PAIR, and AutoDAN attacks while maintaining strong nominal performance on instruction following benchmarks such as InstructionFollowing and AlpacaEval. The codes will be publicly available at https://github.com/UCSB-NLP-Chang/SemanticSmooth., Comment: 37 pages

Motivated by applications in large-scale and multi-agent reinforcement learning, we study the non-asymptotic performance of stochastic approximation (SA) schemes with delayed updates under Markovian sampling. While the effect of delays has been extensively studied for optimization, the manner in which they interact with the underlying Markov process to shape the finite-time performance of SA remains poorly understood. In this context, our first main contribution is to show that under time-varying bounded delays, the delayed SA update rule guarantees exponentially fast convergence of the \emph{last iterate} to a ball around the SA operator's fixed point. Notably, our bound is \emph{tight} in its dependence on both the maximum delay $\tau_{max}$, and the mixing time $\tau_{mix}$. To achieve this tight bound, we develop a novel inductive proof technique that, unlike various existing delayed-optimization analyses, relies on establishing uniform boundedness of the iterates. As such, our proof may be of independent interest. Next, to mitigate the impact of the maximum delay on the convergence rate, we provide the first finite-time analysis of a delay-adaptive SA scheme under Markovian sampling. In particular, we show that the exponent of convergence of this scheme gets scaled down by $\tau_{avg}$, as opposed to $\tau_{max}$ for the vanilla delayed SA rule; here, $\tau_{avg}$ denotes the average delay across all iterations. Moreover, the adaptive scheme requires no prior knowledge of the delay sequence for step-size tuning. Our theoretical findings shed light on the finite-time effects of delays for a broad class of algorithms, including TD learning, Q-learning, and stochastic gradient descent under Markovian sampling., Comment: Accepted to the 27th International Conference on Artificial Intelligence and Statistics (AISTATS) 2024!

Autoencoders are a prominent model in many empirical branches of machine learning and lossy data compression. However, basic theoretical questions remain unanswered even in a shallow two-layer setting. In particular, to what degree does a shallow autoencoder capture the structure of the underlying data distribution? For the prototypical case of the 1-bit compression of sparse Gaussian data, we prove that gradient descent converges to a solution that completely disregards the sparse structure of the input. Namely, the performance of the algorithm is the same as if it was compressing a Gaussian source - with no sparsity. For general data distributions, we give evidence of a phase transition phenomenon in the shape of the gradient descent minimizer, as a function of the data sparsity: below the critical sparsity level, the minimizer is a rotation taken uniformly at random (just like in the compression of non-sparse data); above the critical sparsity, the minimizer is the identity (up to a permutation). Finally, by exploiting a connection with approximate message passing algorithms, we show how to improve upon Gaussian performance for the compression of sparse data: adding a denoising function to a shallow architecture already reduces the loss provably, and a suitable multi-layer decoder leads to a further improvement. We validate our findings on image datasets, such as CIFAR-10 and MNIST.

We have widely observed that neural networks are vulnerable to small additive perturbations to the input causing misclassification. In this paper, we focus on the $\ell_0$-bounded adversarial attacks, and aim to theoretically characterize the performance of adversarial training for an important class of truncated classifiers. Such classifiers are shown to have strong performance empirically, as well as theoretically in the Gaussian mixture model, in the $\ell_0$-adversarial setting. The main contribution of this paper is to prove a novel generalization bound for the binary classification setting with $\ell_0$-bounded adversarial perturbation that is distribution-independent. Deriving a generalization bound in this setting has two main challenges: (i) the truncated inner product which is highly non-linear; and (ii) maximization over the $\ell_0$ ball due to adversarial training is non-convex and highly non-smooth. To tackle these challenges, we develop new coding techniques for bounding the combinatorial dimension of the truncated hypothesis class.

The exquisite angular resolution and sensitivity of JWST is opening a new window for our understanding of the Universe. In nearby galaxies, JWST observations are revolutionizing our understanding of the first phases of star formation and the dusty interstellar medium. Nineteen local galaxies spanning a range of properties and morphologies across the star-forming main sequence have been observed as part of the PHANGS-JWST Cycle 1 Treasury program at spatial scales of $\sim$5-50pc. Here, we describe pjpipe, an image processing pipeline developed for the PHANGS-JWST program that wraps around and extends the official JWST pipeline. We release this pipeline to the community as it contains a number of tools generally useful for JWST NIRCam and MIRI observations. Particularly for extended sources, pjpipe products provide significant improvements over mosaics from the MAST archive in terms of removing instrumental noise in NIRCam data, background flux matching, and calibration of relative and absolute astrometry. We show that slightly smoothing F2100W MIRI data to 0.9" (degrading the resolution by about 30 percent) reduces the noise by a factor of $\approx$3. We also present the first public release (DR1.1.0) of the pjpipe processed eight-band 2-21 $\mu$m imaging for all nineteen galaxies in the PHANGS-JWST Cycle 1 Treasury program. An additional 55 galaxies will soon follow from a new PHANGS-JWST Cycle 2 Treasury program., Comment: 49 pages (27 in Appendices), 54 Figures (39 in Appendices), 3 Tables. Accepted for publication in ApJS. Updated to match accepted version. Data available at https://archive.stsci.edu/hlsp/phangs/phangs-jwst