Search

We introduce a novel, general-purpose audio generation framework specifically designed for anomaly detection and localization. Unlike existing datasets that predominantly focus on industrial and machine-related sounds, our framework focuses a broader range of environments, particularly useful in real-world scenarios where only audio data are available, such as in video-derived or telephonic audio. To generate such data, we propose a new method inspired by the LLM-Modulo framework, which leverages large language models(LLMs) as world models to simulate such real-world scenarios. This tool is modular allowing a plug-and-play approach. It operates by first using LLMs to predict plausible real-world scenarios. An LLM further extracts the constituent sounds, the order and the way in which these should be merged to create coherent wholes. Much like the LLM-Modulo framework, we include rigorous verification of each output stage, ensuring the reliability of the generated data. The data produced using the framework serves as a benchmark for anomaly detection applications, potentially enhancing the performance of models trained on audio data, particularly in handling out-of-distribution cases. Our contributions thus fill a critical void in audio anomaly detection resources and provide a scalable tool for generating diverse, realistic audio data., Comment: 9 pages, under review

The integration of unmanned platforms equipped with advanced sensors promises to enhance situational awareness and mitigate the "fog of war" in military operations. However, managing the vast influx of data from these platforms poses a significant challenge for Command and Control (C2) systems. This study presents a novel multi-agent learning framework to address this challenge. Our method enables autonomous and secure communication between agents and humans, which in turn enables real-time formation of an interpretable Common Operational Picture (COP). Each agent encodes its perceptions and actions into compact vectors, which are then transmitted, received and decoded to form a COP encompassing the current state of all agents (friendly and enemy) on the battlefield. Using Deep Reinforcement Learning (DRL), we jointly train COP models and agent's action selection policies. We demonstrate resilience to degraded conditions such as denied GPS and disrupted communications. Experimental validation is performed in the Starcraft-2 simulation environment to evaluate the precision of the COPs and robustness of policies. We report less than 5% error in COPs and policies resilient to various adversarial conditions. In summary, our contributions include a method for autonomous COP formation, increased resilience through distributed prediction, and joint training of COP models and multi-agent RL policies. This research advances adaptive and resilient C2, facilitating effective control of heterogeneous unmanned platforms., Comment: 29th International Command and Control Research & Technology Symposium

The Cancer Registry of Norway (CRN) is a part of the Norwegian Institute of Public Health (NIPH) and is tasked with producing statistics on cancer among the Norwegian population. For this task, CRN develops, tests, and evolves a software system called Cancer Registration Support System (CaReSS). It is a complex socio-technical software system that interacts with many entities (e.g., hospitals, medical laboratories, and other patient registries) to achieve its task. For cost-effective testing of CaReSS, CRN has employed EvoMaster, an AI-based REST API testing tool combined with an integrated classical machine learning model. Within this context, we propose Qlinical to investigate the feasibility of using, inside EvoMaster, a Quantum Neural Network (QNN) classifier, i.e., a quantum machine learning model, instead of the existing classical machine learning model. Results indicate that Qlinical can achieve performance comparable to that of EvoClass. We further explore the effects of various QNN configurations on performance and offer recommendations for optimal QNN settings for future QNN developers.

Q-points are cofinal in the RK-ordering under several mild hypotheses., Comment: 5 pages

Machine learning has been extensively applied for various classical software testing activities such as test generation, minimization, and prioritization. Along the same lines, recently, there has been interest in applying quantum machine learning to software testing. For example, Quantum Extreme Learning Machines (QELMs) were recently applied for testing classical software of industrial elevators. However, most studies on QELMs, whether in software testing or other areas, used ideal quantum simulators that fail to account for the noise in current quantum computers. While ideal simulations offer insight into QELM's theoretical capabilities, they do not enable studying their performance on current noisy quantum computers. To this end, we study how quantum noise affects QELM in three industrial and real-world classical software testing case studies, providing insights into QELMs' robustness to noise. Such insights assess QELMs potential as a viable solution for industrial software testing problems in today's noisy quantum computing. Our results show that QELMs are significantly affected by quantum noise, with a performance drop of 250% in regression tasks and 50% in classification tasks. Although introducing noise during both ML training and testing phases can improve results, the reduction is insufficient for practical applications. While error mitigation techniques can enhance noise resilience, achieving an average 3.0% performance drop in classification, but their effectiveness varies by context, highlighting the need for QELM-tailored error mitigation strategies.

Molecular polaritons arise when the collective coupling between an ensemble of $N$ molecules and an optical mode exceeds individual photon and molecular linewidths. The complexity of their description stems from their multiscale nature, where the local dynamics on each molecule can, in principle, be influenced by the collective behavior of the entire ensemble. To address this, we previously introduced a formalism called collective dynamics using truncated equations (CUT-E). CUT-E approaches the problem in two stages. First, it exploits permutational symmetries to obtain a substantial simplification of the problem. However, this is often insufficient for parameter regimes relevant to most experiments. Second, it takes the exact solution of the problem in the $N\to\infty$ limit as a reference and derives systematic $\mathcal{O}(1/N)$ corrections. Here we provide a novel derivation of CUT-E based on recently developed bosonization techniques. We lay down its connections with $1/N$ expansions that are ubiquitous in other fields of physics, and present previously unexplored key aspects of this formalism, including various types of approximations and extensions to high excitation manifolds.

Data rebalancing techniques, including oversampling and undersampling, are a common approach to addressing the challenges of imbalanced data. To tackle unresolved problems related to both oversampling and undersampling, we propose a new undersampling approach that: (i) avoids the pitfalls of noise and overlap caused by synthetic data and (ii) avoids the pitfall of under-fitting caused by random undersampling. Instead of undersampling majority data randomly, our method undersamples datapoints based on their ability to improve model loss. Using improved model loss as a proxy measurement for classification performance, our technique assesses a datapoint's impact on loss and rejects those unable to improve it. In so doing, our approach rejects majority datapoints redundant to datapoints already accepted and, thereby, finds an optimal subset of majority training data for classification. The accept/reject component of our algorithm is motivated by a bilevel optimization problem uniquely formulated to identify the optimal training set we seek. Experimental results show our proposed technique with F1 scores up to 10% higher than state-of-the-art methods.

Logical ring is a core component in membership protocol. However, the logic ring fails to consider the underlying physical latency, resulting in a high diameter. To address this issue, we introduce Diameter-Guided Ring Optimization (DGRO), which focuses on constructing rings with the smallest possible diameter, selecting the most effective ring configurations, and implementing these configurations in parallel. We first explore an integration of deep Q-learning and graph embedding to optimize the ring topology. We next propose a ring selection strategy that assesses the current topology's average latency against a global benchmark, facilitating integration into modern peer-to-peer protocols and substantially reducing network diameter. To further enhance scalability, we propose a parallel strategy that distributes the topology construction process into separate partitions simultaneously. Our experiment shows that: 1) DGRO efficiently constructs a network topology that achieves up to a 60% reduction in diameter compared to the best results from an extensive search over $10^5$ topologies, all within a significantly shorter computation time, 2) the ring selection of DGRO reduces the diameter of state-of-the-art methods Chord, RAPID, and Perigee by 10%-40%, 44%, and 60%. 3) the parallel construction can scale up to $32$ partitions while maintaining the same diameter compared to the centralized version.

We introduce a novel framework for human-AI collaboration in prediction and decision tasks. Our approach leverages human judgment to distinguish inputs which are algorithmically indistinguishable, or "look the same" to any feasible predictive algorithm. We argue that this framing clarifies the problem of human-AI collaboration in prediction and decision tasks, as experts often form judgments by drawing on information which is not encoded in an algorithm's training data. Algorithmic indistinguishability yields a natural test for assessing whether experts incorporate this kind of "side information", and further provides a simple but principled method for selectively incorporating human feedback into algorithmic predictions. We show that this method provably improves the performance of any feasible algorithmic predictor and precisely quantify this improvement. We demonstrate the utility of our framework in a case study of emergency room triage decisions, where we find that although algorithmic risk scores are highly competitive with physicians, there is strong evidence that physician judgments provide signal which could not be replicated by any predictive algorithm. This insight yields a range of natural decision rules which leverage the complementary strengths of human experts and predictive algorithms., Comment: arXiv admin note: substantial text overlap with arXiv:2402.00793

Text-to-image diffusion models rely on massive, web-scale datasets. Training them from scratch is computationally expensive, and as a result, developers often prefer to make incremental updates to existing models. These updates often compose fine-tuning steps (to learn new concepts or improve model performance) with "unlearning" steps (to "forget" existing concepts, such as copyrighted works or explicit content). In this work, we demonstrate a critical and previously unknown vulnerability that arises in this paradigm: even under benign, non-adversarial conditions, fine-tuning a text-to-image diffusion model on seemingly unrelated images can cause it to "relearn" concepts that were previously "unlearned." We comprehensively investigate the causes and scope of this phenomenon, which we term concept resurgence, by performing a series of experiments which compose "mass concept erasure" (the current state of the art for unlearning in text-to-image diffusion models (Lu et al., 2024)) with subsequent fine-tuning of Stable Diffusion v1.4. Our findings underscore the fragility of composing incremental model updates, and raise serious new concerns about current approaches to ensuring the safety and alignment of text-to-image diffusion models., Comment: 20 pages, 13 figures

Exploration of complex high-dimensional spaces presents significant challenges in fields such as molecular discovery, process optimization, and supply chain management. Genetic Algorithms (GAs), while offering significant power for creating new candidate spaces, often entail high computational demands due to the need for evaluation of each new proposed solution. On the other hand, Deep Kernel Learning (DKL) efficiently navigates the spaces of preselected candidate structures but lacks generative capabilities. This study introduces an approach that amalgamates the generative power of GAs to create new candidates with the efficiency of DKL-based surrogate models to rapidly ascertain the behavior of new candidate spaces. This DKL-GA framework can be further used to build Bayesian Optimization (BO) workflows. We demonstrate the effectiveness of this approach through the optimization of the FerroSIM model, showcasing its broad applicability to diverse challenges, including molecular discovery and battery charging optimization., Comment: 17 pages, 5 figures

Large Language Models (LLMs) have shown remarkable capabilities, but their inherent probabilistic nature often leads to inconsistency and inaccuracy in complex problem-solving tasks. This paper introduces DANA (Domain-Aware Neurosymbolic Agent), an architecture that addresses these issues by integrating domain-specific knowledge with neurosymbolic approaches. We begin by analyzing current AI architectures, including AutoGPT, LangChain ReAct and OpenAI's ChatGPT, through a neurosymbolic lens, highlighting how their reliance on probabilistic inference contributes to inconsistent outputs. In response, DANA captures and applies domain expertise in both natural-language and symbolic forms, enabling more deterministic and reliable problem-solving behaviors. We implement a variant of DANA using Hierarchical Task Plans (HTPs) in the open-source OpenSSA framework. This implementation achieves over 90\% accuracy on the FinanceBench financial-analysis benchmark, significantly outperforming current LLM-based systems in both consistency and accuracy. Application of DANA in physical industries such as semiconductor shows that its flexible architecture for incorporating knowledge is effective in mitigating the probabilistic limitations of LLMs and has potential in tackling complex, real-world problems that require reliability and precision.

We consider the affine Lie algebra $\widehat{\mathfrak{sl}_2}$ and the Kostant-Kumar submodules of tensor products of its level 1 highest weight integrable representations. We construct crystals for these submodules in terms of the charged partitions model and describe their decomposition into irreducibles., Comment: 26 pages

We introduce and study a notion of Borel order dimension for Borel quasi orders. It will be shown that this notion is closely related to the notion of Borel dichromatic number for simple directed graphs. We prove a dichotomy, which generalizes the ${\GGG}_{0}$-dichotomy, for the Borel dichromatic number of Borel simple directed graphs. By applying this dichotomy to Borel quasi orders, another dichotomy that characterizes the Borel quasi orders of uncountable Borel dimension is proved. We obtain further structural information about the Borel quasi orders of countable Borel dimension by showing that they are all Borel linearizable. We then investigate the locally countable Borel quasi orders in more detail, paying special attention to the Turing degrees, and produce models of set theory where the continuum is arbitrarily large and all locally countable Borel quasi orders are of Borel dimension less than the continuum. Combining our results here with earlier work shows that the Borel order dimension of the Turing degrees is usually strictly larger than its classical order dimension., Comment: 30 pages

Food computing is both important and challenging in computer vision (CV). It significantly contributes to the development of CV algorithms due to its frequent presence in datasets across various applications, ranging from classification and instance segmentation to 3D reconstruction. The polymorphic shapes and textures of food, coupled with high variation in forms and vast multimodal information, including language descriptions and nutritional data, make food computing a complex and demanding task for modern CV algorithms. 3D food modeling is a new frontier for addressing food-related problems, due to its inherent capability to deal with random camera views and its straightforward representation for calculating food portion size. However, the primary hurdle in the development of algorithms for food object analysis is the lack of nutrition values in existing 3D datasets. Moreover, in the broader field of 3D research, there is a critical need for domain-specific test datasets. To bridge the gap between general 3D vision and food computing research, we propose MetaFood3D. This dataset consists of 637 meticulously labeled 3D food objects across 108 categories, featuring detailed nutrition information, weight, and food codes linked to a comprehensive nutrition database. The dataset emphasizes intra-class diversity and includes rich modalities such as textured mesh files, RGB-D videos, and segmentation masks. Experimental results demonstrate our dataset's significant potential for improving algorithm performance, highlight the challenging gap between video captures and 3D scanned data, and show the strength of the MetaFood3D dataset in high-quality data generation, simulation, and augmentation., Comment: Dataset is coming soon

Remote epitaxy has garnered considerable attention as a promising method that facilitates the growth of thin films that replicate the crystallographic characteristics of a substrate by utilizing two-dimensional (2D) material interlayers like graphene. The resulting film can be exfoliated to form a freestanding membrane, and the substrate, if expensive, can be reused. However, atomically thin 2-D materials are susceptible to damage before and during film growth in the chamber, leading to a poor epitaxy. Oxide remote epitaxy using graphene, the most commonly available 2D material, is particularly challenging because the conventional conditions employed for the growth of epitaxial oxides also degrade graphene. In this study, we show for the first time that a direct correlation exists between the microstructure of graphene, its getting defective on exposure to the pulsed laser deposition plume, and the crystalline quality of the barium titanate film deposited on top. A controlled aperture method was used to reduce graphene damage. Even so, the degree of damage is more at the graphene grain boundaries than within the grains. Large grain-sized greater than 300 microns, graphene suffered less damage and yielded a film comparable to that grown directly on a strontium titanate substrate with a rocking curve half width of 0.6 degrees. Using large grain-sized bi-layer graphene, 4 mm x 5 mm oxide layers were successfully exfoliated and transferred onto SiOx-Si. These insights pave the way for the heterogeneous integration of functional oxides on foreign substrates, holding significant implications for commercializing perovskite oxides by integrating them with Si-CMOS and flexible electronics., Comment: 36 pages, 18 figures

Recent advancements in sensors have led to high resolution and high data throughput at the pixel level. Simultaneously, the adoption of increasingly large (deep) neural networks (NNs) has lead to significant progress in computer vision. Currently, visual intelligence comes at increasingly high computational complexity, energy, and latency. We study a data-driven system that combines dynamic sensing at the pixel level with computer vision analytics at the video level and propose a feedback control loop to minimize data movement between the sensor front-end and computational back-end without compromising detection and tracking precision. Our contributions are threefold: (1) We introduce anticipatory attention and show that it leads to high precision prediction with sparse activation of pixels; (2) Leveraging the feedback control, we show that the dimensionality of learned feature vectors can be significantly reduced with increased sparsity; and (3) We emulate analog design choices (such as varying RGB or Bayer pixel format and analog noise) and study their impact on the key metrics of the data-driven system. Comparative analysis with traditional pixel and deep learning models shows significant performance enhancements. Our system achieves a 10X reduction in bandwidth and a 15-30X improvement in Energy-Delay Product (EDP) when activating only 30% of pixels, with a minor reduction in object detection and tracking precision. Based on analog emulation, our system can achieve a throughput of 205 megapixels/sec (MP/s) with a power consumption of only 110 mW per MP, i.e., a theoretical improvement of ~30X in EDP., Comment: Accepted to the Conference on Dynamic Data-Driven Applications Systems (DDDAS2024)

We exhibit a forcing for producing a model with no nowhere dense ultrafilters that satisfies the full Sacks Property. By interleaving this forcing with other forcing notions, a model containing a $(2, {\aleph}_{0})$-selective ultrafilter, but no nowhere dense ultrafilters is produced. It is thus proved that the existence of $(2, {\aleph}_{0})$-selective ultrafilters does not imply the existence of nowhere dense ultrafilters., Comment: 17 Pages, Submitted

The iterated composition of two operators, both of which are involutions and translation invariant, partitions the set of lattice points in the plane into an infinite sequence of discrete parabolas. Each such parabola contains an associated stairway-like path connecting certain points on it, induced by the alternating application of the aforementioned operators. Any two lattice points in the plane can be connected by paths along the square grid composed of steps either on these stairways or towards taxicab neighbors. This leads to the notion of the parabolic-taxicab distance between two lattice points, obtained as the minimum number of steps of this kind needed to reach one point from the other. In this paper, we describe patterns generated by points on paths of bounded parabolic-taxicab length and provide a complete description of the balls centered at the origin. In particular, we prove an earlier conjecture on the area of these balls., Comment: 20 pages, 6 figures

The rapid integration of machine learning methodologies in healthcare has ignited innovative strategies for disease prediction, particularly with the vast repositories of Electronic Health Records (EHR) data. This article delves into the realm of multi-disease prediction, presenting a comprehensive study that introduces a pioneering ensemble feature selection model. This model, designed to optimize learning systems, combines statistical, deep, and optimally selected features through the innovative Stabilized Energy Valley Optimization with Enhanced Bounds (SEV-EB) algorithm. The objective is to achieve unparalleled accuracy and stability in predicting various disorders. This work proposes an advanced ensemble model that synergistically integrates statistical, deep, and optimally selected features. This combination aims to enhance the predictive power of the model by capturing diverse aspects of the health data. At the heart of the proposed model lies the SEV-EB algorithm, a novel approach to optimal feature selection. The algorithm introduces enhanced bounds and stabilization techniques, contributing to the robustness and accuracy of the overall prediction model. To further elevate the predictive capabilities, an HSC-AttentionNet is introduced. This network architecture combines deep temporal convolution capabilities with LSTM, allowing the model to capture both short-term patterns and long-term dependencies in health data. Rigorous evaluations showcase the remarkable performance of the proposed model. Achieving a 95% accuracy and 94% F1-score in predicting various disorders, the model surpasses traditional methods, signifying a significant advancement in disease prediction accuracy. The implications of this research extend beyond the confines of academia., Comment: 16 Pages, 4 Figures

Physical imaging is a foundational characterization method in areas from condensed matter physics and chemistry to astronomy and spans length scales from atomic to universe. Images encapsulate crucial data regarding atomic bonding, materials microstructures, and dynamic phenomena such as microstructural evolution and turbulence, among other phenomena. The challenge lies in effectively extracting and interpreting this information. Variational Autoencoders (VAEs) have emerged as powerful tools for identifying underlying factors of variation in image data, providing a systematic approach to distilling meaningful patterns from complex datasets. However, a significant hurdle in their application is the definition and selection of appropriate descriptors reflecting local structure. Here we introduce the scale-invariant VAE approach (SI-VAE) based on the progressive training of the VAE with the descriptors sampled at different length scales. The SI-VAE allows the discovery of the length scale dependent factors of variation in the system. Here, we illustrate this approach using the ferroelectric domain images and generalize it to the movies of the electron-beam induced phenomena in graphene and topography evolution across combinatorial libraries. This approach can further be used to initialize the decision making in automated experiments including structure-property discovery and can be applied across a broad range of imaging methods. This approach is universal and can be applied to any spatially resolved data including both experimental imaging studies and simulations, and can be particularly useful for exploration of phenomena such as turbulence, scale-invariant transformation fronts, etc.

Anomaly detection in computational workflows is critical for ensuring system reliability and security. However, traditional rule-based methods struggle to detect novel anomalies. This paper leverages large language models (LLMs) for workflow anomaly detection by exploiting their ability to learn complex data patterns. Two approaches are investigated: 1) supervised fine-tuning (SFT), where pre-trained LLMs are fine-tuned on labeled data for sentence classification to identify anomalies, and 2) in-context learning (ICL) where prompts containing task descriptions and examples guide LLMs in few-shot anomaly detection without fine-tuning. The paper evaluates the performance, efficiency, generalization of SFT models, and explores zero-shot and few-shot ICL prompts and interpretability enhancement via chain-of-thought prompting. Experiments across multiple workflow datasets demonstrate the promising potential of LLMs for effective anomaly detection in complex executions., Comment: 12 pages, 14 figures, paper is accepted by SC'24, source code, see: https://github.com/PoSeiDon-Workflows/LLM_AD

Integrating epitaxial BaTiO$_3$ (BTO) with Si is essential for leveraging its ferroelectric, piezoelectric, and nonlinear optical properties in microelectronics. Recently, heterogeneous integration approaches that involve growth of BTO on ideal substrates followed by transfer to a desired substrate show promise of achieving excellent device-quality films. However, beyond simple demonstrations of the existence of ferroelectricity, robust devices with high endurance were not yet demonstrated on Si using the latter approach. Here, using a novel two-step approach to synthesize epitaxial BTO using pulsed laser deposition (PLD) on water soluble Sr3Al2O7 (SAO) (on SrTiO$_3$ (STO) substrates), we demonstrate successful integration of high-quality BTO capacitors on Si, with Pr of 7 uC/cm2, Ec 150 kV/cm, ferroelectric and electromechanical endurance of greater than $10^6$ cycles. We further address the challenge of cracking and disintegration of thicker films by first transferring a large area (5 mm x 5 mm) of the templated layer of BTO (~30 nm thick) on the desired substrate, followed by the growth of high-quality BTO on this substrate, as revealed by HRXRD and HRSTEM measurements. These templated Si substrates offer a versatile platform for integrating any epitaxial complex oxides with diverse functionalities onto any inorganic substrate., Comment: 29 pages, 12 figures

A chemical reaction mechanism (CRM) is a sequence of molecular-level events involving bond-breaking/forming processes, generating transient intermediates along the reaction pathway as reactants transform into products. Understanding such mechanisms is crucial for designing and discovering new reactions. One of the currently available methods to probe CRMs is quantum mechanical (QM) computations. The resource-intensive nature of QM methods and the scarcity of mechanism-based datasets motivated us to develop reliable ML models for predicting mechanisms. In this study, we created a comprehensive dataset with seven distinct classes, each representing uniquely characterized elementary steps. Subsequently, we developed an interpretable attention-based GNN that achieved near-unity and 96% accuracy, respectively for reaction step classification and the prediction of reactive atoms in each such step, capturing interactions between the broader reaction context and local active regions. The near-perfect classification enables accurate prediction of both individual events and the entire CRM, mitigating potential drawbacks of Seq2Seq approaches, where a wrongly predicted character leads to incoherent CRM identification. In addition to interpretability, our model adeptly identifies key atom(s) even from out-of-distribution classes. This generalizabilty allows for the inclusion of new reaction types in a modular fashion, thus will be of value to experts for understanding the reactivity of new molecules., Comment: Accepted to 27th ECAI main track

We consider a collaborative iterative algorithm with two agents and a fusion center for estimation of a real valued function (or ``model") on the set of real numbers. While the data collected by the agents is private, in every iteration of the algorithm, the models estimated by the agents are uploaded to the fusion center, fused, and, subsequently downloaded by the agents. We consider the estimation spaces at the agents and the fusion center to be Reproducing Kernel Hilbert Spaces (RKHS). Under suitable assumptions on these spaces, we prove that the algorithm is consistent, i.e., there exists a subsequence of the estimated models which converges to a model in the strong topology. To this end, we define estimation operators for the agents, fusion center, and, for every iteration of the algorithm constructively. We define valid input data sequences, study the asymptotic properties of the norm of the estimation operators, and, find sufficient conditions under which the estimation operator until any iteration is uniformly bounded. Using these results, we prove the existence of an estimation operator for the algorithm which implies the consistency of the considered estimation algorithm., Comment: arXiv admin note: text overlap with arXiv:2401.03012

This paper presents NT-Java-1.1B, an open-source specialized code language model built on StarCoderBase-1.1B, designed for coding tasks in Java programming. NT-Java-1.1B achieves state-of-the-art performance, surpassing its base model and majority of other models of similar size on MultiPL-E Java code benchmark. While there have been studies on extending large, generic pre-trained models to improve proficiency in specific programming languages like Python, similar investigations on small code models for other programming languages are lacking. Large code models require specialized hardware like GPUs for inference, highlighting the need for research into building small code models that can be deployed on developer desktops. This paper addresses this research gap by focusing on the development of a small Java code model, NT-Java-1.1B, and its quantized versions, which performs comparably to open models around 1.1B on MultiPL-E Java code benchmarks, making them ideal for desktop deployment. This paper establishes the foundation for specialized models across languages and sizes for a family of NT Models., Comment: Updated Authors list

This study, conducted in 2017, explores the use of Machine learning algorithms to predict Characteristics of Transmission Lines such as Impedance or resonance frequency using design parameters of Transmission Lines. Using formulas and equations that define the characteristics of Transmission lines, training data was generated. We trained different models for this dataset. The extent of deviation of predicted output from the actual output was measured in terms of maximum error and average error. This helped determine how well an algorithm worked for a particular transmission line. Further, the best-suited algorithm for each transmission line under consideration was found based on the error, Comment: 6 pages, 8 figures, 2 tables

We describe micro-fabricated rubidium vapor cells with integrated temperature-control functionality and demonstrate their suitability for use in miniaturized ultra-sensitive magnetometers. These functionalized vapor cells (FVCs) embody a dual-chamber design in low-conductivity silicon with anti-permeation coatings and micro-structured thin-film platinum surface traces as resistive heaters and temperature sensors. Thermal tests show our ability to control alkali metal distribution within the FVCs, ensuring a clean sensing chamber for optical measurements. Optical absorption spectroscopy is used to correlate the temperature readings with vapor density and to measure buffer gas pressure, of interest for optimizing sensitivity. Finally, we demonstrate zero-field resonance magnetometry with 18 fT/Hz$^{1/2}$ sensitivity in the 10 Hz to 100 Hz band, limited by laser noise and magnetic shield noise, which indicates that the functionalization does not introduce significant magnetic noise., Comment: Authors HR and MCDT contributed equally

Combinatorial spread libraries offer a unique approach to explore evolution of materials properties over the broad concentration, temperature, and growth parameter spaces. However, the traditional limitation of this approach is the requirement for the read-out of functional properties across the library. Here we demonstrate the application of automated Piezoresponse Force Microscopy (PFM) for the exploration of the physics in the SmxBi1-xFeO3 system with the ferroelectric-antiferroelectric morphotropic phase boundary. This approach relies on the synergy of the quantitative nature of PFM and the implementation of automated experiments that allows PFM-based gird sampling over macroscopic samples. The concentration dependence of pertinent ferroelectric parameters has been determined and used to develop the mathematical framework based on Ginzburg-Landau theory describing the evolution of these properties across the concentration space. We pose that combination of automated scanning probe microscope and combinatorial spread library approach will emerge as an efficient research paradigm to close the characterization gap in the high-throughput materials discovery. We make the data sets open to the community and hope that will stimulate other efforts to interpret and understand the physics of these systems., Comment: 19 pages; 5 figures

Synthetic data generation is increasingly recognized as a crucial solution to address data related challenges such as scarcity, bias, and privacy concerns. As synthetic data proliferates, the need for a robust evaluation framework to select a synthetic data generator becomes more pressing given the variety of options available. In this research study, we investigate two primary questions: 1) How can we select the most suitable synthetic data generator from a set of options for a specific purpose? 2) How can we make the selection process more transparent, accountable, and auditable? To address these questions, we introduce a novel approach in which the proposed ranking algorithm is implemented as a smart contract within a permissioned blockchain framework called Sawtooth. Through comprehensive experiments and comparisons with state-of-the-art baseline ranking solutions, our framework demonstrates its effectiveness in providing nuanced rankings that consider both desirable and undesirable properties. Furthermore, our framework serves as a valuable tool for selecting the optimal synthetic data generators for specific needs while ensuring compliance with data protection principles.

A computational workflow, also known as workflow, consists of tasks that are executed in a certain order to attain a specific computational campaign. Computational workflows are commonly employed in science domains, such as physics, chemistry, genomics, to complete large-scale experiments in distributed and heterogeneous computing environments. However, running computations at such a large scale makes the workflow applications prone to failures and performance degradation, which can slowdown, stall, and ultimately lead to workflow failure. Learning how these workflows behave under normal and anomalous conditions can help us identify the causes of degraded performance and subsequently trigger appropriate actions to resolve them. However, learning in such circumstances is a challenging task because of the large volume of high-quality historical data needed to train accurate and reliable models. Generating such datasets not only takes a lot of time and effort but it also requires a lot of resources to be devoted to data generation for training purposes. Active learning is a promising approach to this problem. It is an approach where the data is generated as required by the machine learning model and thus it can potentially reduce the training data needed to derive accurate models. In this work, we present an active learning approach that is supported by an experimental framework, Poseidon-X, that utilizes a modern workflow management system and two cloud testbeds. We evaluate our approach using three computational workflows. For one workflow we run an end-to-end live active learning experiment, for the other two we evaluate our active learning algorithms using pre-captured data traces provided by the Flow-Bench benchmark. Our findings indicate that active learning not only saves resources, but it also improves the accuracy of the detection of anomalies.

The burgeoning influence of Large Language Models (LLMs) in shaping public discourse and decision-making underscores the imperative to address inherent biases within these AI systems. In the wake of AI's expansive integration across sectors, addressing racial bias in LLMs has never been more critical. This paper introduces a novel framework called Comprehensive Bias Neutralization Framework (CBNF) which embodies an innovative approach to quantifying and mitigating biases within LLMs. Our framework combines the Large Language Model Bias Index (LLMBI) [Oketunji, A., Anas, M., Saina, D., (2023)] and Bias removaL with No Demographics (BLIND) [Orgad, H., Belinkov, Y. (2023)] methodologies to create a new metric called Bias Intelligence Quotient (BiQ)which detects, measures, and mitigates racial bias in LLMs without reliance on demographic annotations. By introducing a new metric called BiQ that enhances LLMBI with additional fairness metrics, CBNF offers a multi-dimensional metric for bias assessment, underscoring the necessity of a nuanced approach to fairness in AI [Mehrabi et al., 2021]. This paper presents a detailed analysis of Latimer AI (a language model incrementally trained on black history and culture) in comparison to ChatGPT 3.5, illustrating Latimer AI's efficacy in detecting racial, cultural, and gender biases through targeted training and refined bias mitigation strategies [Latimer & Bender, 2023]., Comment: 41 pages

This paper investigates the impact of domain-specific model fine-tuning and of reasoning mechanisms on the performance of question-answering (Q&A) systems powered by large language models (LLMs) and Retrieval-Augmented Generation (RAG). Using the FinanceBench SEC financial filings dataset, we observe that, for RAG, combining a fine-tuned embedding model with a fine-tuned LLM achieves better accuracy than generic models, with relatively greater gains attributable to fine-tuned embedding models. Additionally, employing reasoning iterations on top of RAG delivers an even bigger jump in performance, enabling the Q&A systems to get closer to human-expert quality. We discuss the implications of such findings, propose a structured technical design space capturing major technical components of Q&A AI, and provide recommendations for making high-impact technical choices for such components. We plan to follow up on this work with actionable guides for AI teams and further investigations into the impact of domain-specific augmentation in RAG and into agentic AI capabilities such as advanced planning and reasoning., Comment: Fixed typo of OODA's score on harder-question set in Table 2

The US Decennial Census provides valuable data for both research and policy purposes. Census data are subject to a variety of disclosure avoidance techniques prior to release in order to preserve respondent confidentiality. While many are interested in studying the impacts of disclosure avoidance methods on downstream analyses, particularly with the introduction of differential privacy in the 2020 Decennial Census, these efforts are limited by a critical lack of data: The underlying "microdata," which serve as necessary input to disclosure avoidance methods, are kept confidential. In this work, we aim to address this limitation by providing tools to generate synthetic microdata solely from published Census statistics, which can then be used as input to any number of disclosure avoidance algorithms for the sake of evaluation and carrying out comparisons. We define a principled distribution over microdata given published Census statistics and design algorithms to sample from this distribution. We formulate synthetic data generation in this context as a knapsack-style combinatorial optimization problem and develop novel algorithms for this setting. While the problem we study is provably hard, we show empirically that our methods work well in practice, and we offer theoretical arguments to explain our performance. Finally, we verify that the data we produce are "close" to the desired ground truth.

A significant challenge in achieving ubiquitous Artificial Intelligence is the limited ability of models to rapidly learn new information in real-world scenarios where data follows long-tailed distributions, all while avoiding forgetting previously acquired knowledge. In this work, we study the under-explored problem of Long-Tailed Online Continual Learning (LTOCL), which aims to learn new tasks from sequentially arriving class-imbalanced data streams. Each data is observed only once for training without knowing the task data distribution. We present DELTA, a decoupled learning approach designed to enhance learning representations and address the substantial imbalance in LTOCL. We enhance the learning process by adapting supervised contrastive learning to attract similar samples and repel dissimilar (out-of-class) samples. Further, by balancing gradients during training using an equalization loss, DELTA significantly enhances learning outcomes and successfully mitigates catastrophic forgetting. Through extensive evaluation, we demonstrate that DELTA improves the capacity for incremental learning, surpassing existing OCL methods. Our results suggest considerable promise for applying OCL in real-world applications., Comment: CVPR Workshop acceptance archival track

We survey some recent results about the order structure of various kinds of ultrafilters. More precisely, we study Rudin-Keisler and Tukey reducibility in classes of selective, stable ordered-union, and P-point ultrafilters. Although these reductions are fundamentally different, there are connections between them. On the other hand, even though the classes of ultrafilters we consider are similar, there are significant differences in their order structure, as will be seen in the survey.

In this paper, we describe the different approaches explored by the Jetsons team for the Multi-Lingual ESG Impact Duration Inference (ML-ESG-3) shared task. The shared task focuses on predicting the duration and type of the ESG impact of a news article. The shared task dataset consists of 2,059 news titles and articles in English, French, Korean, and Japanese languages. For the impact duration classification task, we fine-tuned XLM-RoBERTa with a custom fine-tuning strategy and using self-training and DeBERTa-v3 using only English translations. These models individually ranked first on the leaderboard for Korean and Japanese and in an ensemble for the English language, respectively. For the impact type classification task, our XLM-RoBERTa model fine-tuned using a custom fine-tuning strategy ranked first for the English language.

With the increasing emphasis on machine learning and artificial intelligence to drive knowledge discovery in the agricultural sciences, spatial internet of things (IoT) technologies have become increasingly important for collecting real-time, high resolution data for these models. However, managing large fleets of devices while maintaining high data quality remains an ongoing challenge as scientists iterate from prototype to mature end-to-end applications. Here, we provide a set of case studies using the framework of technology readiness levels for an open source spatial IoT system. The spatial IoT systems underwent 3 major and 14 minor system versions, had over 2,727 devices manufactured both in academic and commercial contexts, and are either in active or planned deployment across four continents. Our results show the evolution of a generalizable, open source spatial IoT system designed for agricultural scientists, and provide a model for academic researchers to overcome the challenges that exist in going from one-off prototypes to thousands of internet-connected devices., Comment: 20 pages, 5 figures, 1 table

MiMiC is a framework for performing multiscale simulations in which loosely coupled external programs describe individual subsystems at different resolutions and levels of theory. To make it highly efficient and flexible, we adopt an interoperable approach based on a multiple-program multiple-data (MPMD) paradigm, serving as an intermediary responsible for fast data exchange and interactions between the subsystems. The main goal of MiMiC is to avoid interfering with the underlying parallelization of the external programs, including the operability on hybrid architectures (e.g., CPU/GPU), and keep their setup and execution as close as possible to the original. At the moment, MiMiC offers an efficient implementation of electrostatic embedding QM/MM that has demonstrated unprecedented parallel scaling in simulations of large biomolecules using CPMD and GROMACS as QM and MM engines, respectively. However, as it is designed for high flexibility with general multiscale models in mind, it can be straightforwardly extended beyond QM/MM. In this article, we illustrate the software design and the features of the framework, which make it a compelling choice for multiscale simulations in the upcoming era of exascale high-performance computing.

A given region in 2-D Euclidean space is divided by a unknown linear classifier in to two sets each carrying a label. The objective of an agent with known dynamics traversing the region is to identify the true classifier while paying a control cost across its trajectory. We consider two scenarios: (i) the agent is able to measure the true label perfectly; (ii) the observed label is the true label multiplied by noise. We present the following: (i) the classifier identification problem formulated as a control problem; (ii) geometric interpretation of the control problem resulting in one step modified control problems; (iii) control algorithms that result in data sets which are used to identify the true classifier with accuracy; (iv) convergence of estimated classifier to the true classifier when the observed label is not corrupted by noise; (iv) numerical example demonstrating the utility of the control algorithms.

We consider the problem of estimation of a function by a system consisting of two agents and a fusion center. The two agents collect data comprising of samples of an independent variable and the corresponding value of a dependent variable. The objective of the system is to collaboratively estimate the function without any exchange of data among the members of the system. To this end, we propose the following framework. The agents are given a set of features using which they construct suitable function spaces to formulate and solve the estimation problems locally. The estimated functions are uploaded to a fusion space where an optimization problem is solved to fuse the estimates (also known as meta-learning) to obtain the system estimate of the mapping. The fused function is then downloaded by the agents to gather knowledge about the other agents estimate of the function. With respect to the framework, we present the following: a systematic construction of fusion space given the features of the agents; the derivation of an uploading operator for the agents to upload their estimated functions to a fusion space; the derivation of a downloading operator for the fused function to be downloaded. Through an example on least squares regression, we illustrate the distributed estimation architecture that has been developed.

We present ALTO, a network orchestrator for efficiently serving compound AI systems such as pipelines of language models. ALTO achieves high throughput and low latency by taking advantage of an optimization opportunity specific to generative language models: streaming intermediate outputs. As language models produce outputs token by token, ALTO exposes opportunities to stream intermediate outputs between stages when possible. We highlight two new challenges of correctness and load balancing which emerge when streaming intermediate data across distributed pipeline stage instances. We also motivate the need for an aggregation-aware routing interface and distributed prompt-aware scheduling to address these challenges. We demonstrate the impact of ALTO's partial output streaming on a complex chatbot verification pipeline, increasing throughput by up to 3x for a fixed latency target of 4 seconds / request while also reducing tail latency by 1.8x compared to a baseline serving approach.

We present INDICVOICES, a dataset of natural and spontaneous speech containing a total of 7348 hours of read (9%), extempore (74%) and conversational (17%) audio from 16237 speakers covering 145 Indian districts and 22 languages. Of these 7348 hours, 1639 hours have already been transcribed, with a median of 73 hours per language. Through this paper, we share our journey of capturing the cultural, linguistic and demographic diversity of India to create a one-of-its-kind inclusive and representative dataset. More specifically, we share an open-source blueprint for data collection at scale comprising of standardised protocols, centralised tools, a repository of engaging questions, prompts and conversation scenarios spanning multiple domains and topics of interest, quality control mechanisms, comprehensive transcription guidelines and transcription tools. We hope that this open source blueprint will serve as a comprehensive starter kit for data collection efforts in other multilingual regions of the world. Using INDICVOICES, we build IndicASR, the first ASR model to support all the 22 languages listed in the 8th schedule of the Constitution of India. All the data, tools, guidelines, models and other materials developed as a part of this work will be made publicly available

Many existing end-to-end systems for hybrid question answering tasks can often be boiled down to a "prompt-and-pray" paradigm, where the user has limited control and insight into the intermediate reasoning steps used to achieve the final result. Additionally, due to the context size limitation of many transformer-based LLMs, it is often not reasonable to expect that the full structured and unstructured context will fit into a given prompt in a zero-shot setting, let alone a few-shot setting. We introduce BlendSQL, a superset of SQLite to act as a unified dialect for orchestrating reasoning across both unstructured and structured data. For hybrid question answering tasks involving multi-hop reasoning, we encode the full decomposed reasoning roadmap into a single interpretable BlendSQL query. Notably, we show that BlendSQL can scale to massive datasets and improve the performance of end-to-end systems while using 35% fewer tokens. Our code is available and installable as a package at https://github.com/parkervg/blendsql., Comment: For associated codebase, see https://github.com/parkervg/blendsql

Professional networks -- the social networks among people in a given line of work -- can serve as a conduit for job prospects and other opportunities. Here we propose a model for the formation of such networks and the transfer of opportunities within them. In our theoretical model, individuals strategically connect with others to maximize the probability that they receive opportunities from them. We explore how professional networks balance connectivity, where connections facilitate opportunity transfers to those who did not get them from outside sources, and congestion, where some individuals receive too many opportunities from their connections and waste some of them. We show that strategic individuals are over-connected at equilibrium relative to a social optimum, leading to a price of anarchy for which we derive nearly tight asymptotic bounds. We also show that, at equilibrium, individuals form connections to those who provide similar benefit to them as they provide to others. Thus, our model provides a microfoundation in professional networking contexts for the fundamental sociological principle of homophily, that "similarity breeds connection," which in our setting is realized as a form of status homophily based on alignment in individual benefit. We further explore how, even if individuals are a priori equally likely to receive opportunities from outside sources, equilibria can be unequal, and we provide nearly tight bounds on how unequal they can be. Finally, we explore the ability for online platforms to intervene to improve social welfare and show that natural heuristics may result in adverse effects at equilibrium. Our simple model allows for a surprisingly rich analysis of coordination problems in professional networks and suggests many directions for further exploration., Comment: 53 pages, 6 figures

Learning molecular representation is a critical step in molecular machine learning that significantly influences modeling success, particularly in data-scarce situations. The concept of broadly pre-training neural networks has advanced fields such as computer vision, natural language processing, and protein engineering. However, similar approaches for small organic molecules have not achieved comparable success. In this work, we introduce a novel pre-training strategy, substrate scope contrastive learning, which learns atomic representations tailored to chemical reactivity. This method considers the grouping of substrates and their yields in published substrate scope tables as a measure of their similarity or dissimilarity in terms of chemical reactivity. We focus on 20,798 aryl halides in the CAS Content Collection spanning thousands of publications to learn a representation of aryl halide reactivity. We validate our pre-training approach through both intuitive visualizations and comparisons to traditional reactivity descriptors and physical organic chemistry principles. The versatility of these embeddings is further evidenced in their application to yield prediction, regioselectivity prediction, and the diverse selection of new substrates. This work not only presents a chemistry-tailored neural network pre-training strategy to learn reactivity-aligned atomic representations, but also marks a first-of-its-kind approach to benefit from the human bias in substrate scope design.

Deep neural networks are susceptible to adversarial attacks, which can compromise their performance and accuracy. Adversarial Training (AT) has emerged as a popular approach for protecting neural networks against such attacks. However, a key challenge of AT is robust overfitting, where the network's robust performance on test data deteriorates with further training, thus hindering generalization. Motivated by the concept of active forgetting in the brain, we introduce a novel learning paradigm called "Forget to Mitigate Overfitting (FOMO)". FOMO alternates between the forgetting phase, which randomly forgets a subset of weights and regulates the model's information through weight reinitialization, and the relearning phase, which emphasizes learning generalizable features. Our experiments on benchmark datasets and adversarial attacks show that FOMO alleviates robust overfitting by significantly reducing the gap between the best and last robust test accuracy while improving the state-of-the-art robustness. Furthermore, FOMO provides a better trade-off between standard and robust accuracy, outperforming baseline adversarial methods. Finally, our framework is robust to AutoAttacks and increases generalization in many real-world scenarios., Comment: Published as a conference paper at ICLR 2024

Background: Acute kidney injury (AKI), the decline of kidney excretory function, occurs in up to 18% of hospitalized admissions. Progression of AKI may lead to irreversible kidney damage. Methods: This retrospective cohort study includes adult patients admitted to a non-intensive care unit at the University of Pittsburgh Medical Center (UPMC) (n = 46,815) and University of Florida Health (UFH) (n = 127,202). We developed and compared deep learning and conventional machine learning models to predict progression to Stage 2 or higher AKI within the next 48 hours. We trained local models for each site (UFH Model trained on UFH, UPMC Model trained on UPMC) and a separate model with a development cohort of patients from both sites (UFH-UPMC Model). We internally and externally validated the models on each site and performed subgroup analyses across sex and race. Results: Stage 2 or higher AKI occurred in 3% (n=3,257) and 8% (n=2,296) of UFH and UPMC patients, respectively. Area under the receiver operating curve values (AUROC) for the UFH test cohort ranged between 0.77 (UPMC Model) and 0.81 (UFH Model), while AUROC values ranged between 0.79 (UFH Model) and 0.83 (UPMC Model) for the UPMC test cohort. UFH-UPMC Model achieved an AUROC of 0.81 (95% confidence interval [CI] [0.80, 0.83]) for UFH and 0.82 (95% CI [0.81,0.84]) for UPMC test cohorts; an area under the precision recall curve values (AUPRC) of 0.6 (95% CI, [0.05, 0.06]) for UFH and 0.13 (95% CI, [0.11,0.15]) for UPMC test cohorts. Kinetic estimated glomerular filtration rate, nephrotoxic drug burden and blood urea nitrogen remained the top three features with the highest influence across the models and health centers. Conclusion: Locally developed models displayed marginally reduced discrimination when tested on another institution, while the top set of influencing features remained the same across the models and sites.

We introduce a novel framework for incorporating human expertise into algorithmic predictions. Our approach leverages human judgment to distinguish inputs which are algorithmically indistinguishable, or "look the same" to predictive algorithms. We argue that this framing clarifies the problem of human-AI collaboration in prediction tasks, as experts often form judgments by drawing on information which is not encoded in an algorithm's training data. Algorithmic indistinguishability yields a natural test for assessing whether experts incorporate this kind of "side information", and further provides a simple but principled method for selectively incorporating human feedback into algorithmic predictions. We show that this method provably improves the performance of any feasible algorithmic predictor and precisely quantify this improvement. We find empirically that although algorithms often outperform their human counterparts on average, human judgment can improve algorithmic predictions on specific instances (which can be identified ex-ante). In an X-ray classification task, we find that this subset constitutes nearly $30\%$ of the patient population. Our approach provides a natural way of uncovering this heterogeneity and thus enabling effective human-AI collaboration., Comment: 35 pages, 13 figures

Many High Performance Computing (HPC) facilities have developed and deployed frameworks in support of continuous monitoring and operational data analytics (MODA) to help improve efficiency and throughput. Because of the complexity and scale of systems and workflows and the need for low-latency response to address dynamic circumstances, automated feedback and response have the potential to be more effective than current human-in-the-loop approaches which are laborious and error prone. Progress has been limited, however, by factors such as the lack of infrastructure and feedback hooks, and successful deployment is often site- and case-specific. In this position paper we report on the outcomes and plans from a recent Dagstuhl Seminar, seeking to carve a path for community progress in the development of autonomous feedback loops for MODA, based on the established formalism of similar (MAPE-K) loops in autonomous computing and self-adaptive systems. By defining and developing such loops for significant cases experienced across HPC sites, we seek to extract commonalities and develop conventions that will facilitate interoperability and interchangeability with system hardware, software, and applications across different sites, and will motivate vendors and others to provide telemetry interfaces and feedback hooks to enable community development and pervasive deployment of MODA autonomy loops.