Search

Training a neural network for pixel based classification task using low resolution Landsat images is difficult as the size of the training data is usually small due to less number of available pixels that represent a single class without any mixing with other classes. Due to this scarcity of training data, neural network may not be able to attain expected level of accuracy. This limitation could be overcome using a generative network that aims to generate synthetic data having the same distribution as the sample data with which it is trained. In this work, we have proposed a methodology for improving the performance of ANN classifier to identify built-up pixels in the Landsat$7$ image with the help of developing a simple GAN architecture that could generate synthetic training pixels when trained using original set of sample built-up pixels. To ensure that the marginal and joint distributions of all the bands corresponding to the generated and original set of pixels are indistinguishable, non-parametric Kolmogorov Smirnov Test and Ball Divergence based Equality of Distributions Test have been performed respectively. It has been observed that the overall accuracy and kappa coefficient of the ANN model for built-up classification have continuously improved from $0.9331$ to $0.9983$ and $0.8277$ to $0.9958$ respectively, with the inclusion of generated sets of built-up pixels to the original one.

Restless Multi-Armed Bandits (RMABs) have been successfully applied to resource allocation problems in a variety of settings, including public health. With the rapid development of powerful large language models (LLMs), they are increasingly used to design reward functions to better match human preferences. Recent work has shown that LLMs can be used to tailor automated allocation decisions to community needs using language prompts. However, this has been studied primarily for English prompts and with a focus on task performance only. This can be an issue since grassroots workers, especially in developing countries like India, prefer to work in local languages, some of which are low-resource. Further, given the nature of the problem, biases along population groups unintended by the user are also undesirable. In this work, we study the effects on both task performance and fairness when the DLM algorithm, a recent work on using LLMs to design reward functions for RMABs, is prompted with non-English language commands. Specifically, we run the model on a synthetic environment for various prompts translated into multiple languages. The prompts themselves vary in complexity. Our results show that the LLM-proposed reward functions are significantly better when prompted in English compared to other languages. We also find that the exact phrasing of the prompt impacts task performance. Further, as prompt complexity increases, performance worsens for all languages; however, it is more robust with English prompts than with lower-resource languages. On the fairness side, we find that low-resource languages and more complex prompts are both highly likely to create unfairness along unintended dimensions., Comment: Accepted at the AAAI-2025 Deployable AI Workshop

Cloud Operations (CloudOps) is a rapidly growing field focused on the automated management and optimization of cloud infrastructure which is essential for organizations navigating increasingly complex cloud environments. MontyCloud Inc. is one of the major companies in the CloudOps domain that leverages autonomous bots to manage cloud compliance, security, and continuous operations. To make the platform more accessible and effective to the customers, we leveraged the use of GenAI. Developing a GenAI-based solution for autonomous CloudOps for the existing MontyCloud system presented us with various challenges such as i) diverse data sources; ii) orchestration of multiple processes; and iii) handling complex workflows to automate routine tasks. To this end, we developed MOYA, a multi-agent framework that leverages GenAI and balances autonomy with the necessary human control. This framework integrates various internal and external systems and is optimized for factors like task orchestration, security, and error mitigation while producing accurate, reliable, and relevant insights by utilizing Retrieval Augmented Generation (RAG). Evaluations of our multi-agent system with the help of practitioners as well as using automated checks demonstrate enhanced accuracy, responsiveness, and effectiveness over non-agentic approaches across complex workflows., Comment: The paper has been accepted as full paper to CAIN 2025 (https://conf.researchr.org/home/cain-2025), co-located with ICSE 2025 (https://conf.researchr.org/home/icse-2025). The paper was submitted to CAIN for review on 9 November 2024

Multigrid methods are asymptotically optimal algorithms ideal for large-scale simulations. But, they require making numerous algorithmic choices that significantly influence their efficiency. Unlike recent approaches that learn optimal multigrid components using machine learning techniques, we adopt a complementary strategy here, employing evolutionary algorithms to construct efficient multigrid cycles from available individual components. This technology is applied to finite element simulations of the laser beam welding process. The thermo-elastic behavior is described by a coupled system of time-dependent thermo-elasticity equations, leading to nonlinear and ill-conditioned systems. The nonlinearity is addressed using Newton's method, and iterative solvers are accelerated with an algebraic multigrid (AMG) preconditioner using hypre BoomerAMG interfaced via PETSc. This is applied as a monolithic solver for the coupled equations. To further enhance solver efficiency, flexible AMG cycles are introduced, extending traditional cycle types with level-specific smoothing sequences and non-recursive cycling patterns. These are automatically generated using genetic programming, guided by a context-free grammar containing AMG rules. Numerical experiments demonstrate the potential of these approaches to improve solver performance in large-scale laser beam welding simulations.

Astrometry of pulsars, particularly their distances, serves as a critical input for various astrophysical experiments using pulsars. Pulsar timing is a primary approach for determining a pulsar's position, parallax, and distance. In this paper, we explore the influence of the solar wind on astrometric measurements obtained through pulsar timing, focusing on its potential to affect the accuracy of these parameters. Using both theoretical calculation and mock-data simulations, we demonstrate a significant correlation between the pulsar position, annual parallax and the solar-wind density parameters. This correlation strongly depends on the pulsar's ecliptic latitude. We show that fixing solar-wind density to an arbitrary value in the timing analysis can introduce significant bias in the estimated pulsar position and parallax, and its significance is highly dependent on the ecliptic latitude of the pulsar and the timing precision of the data. For pulsars with favourable ecliptic latitude and timing precision, the astrometric and solar-wind parameters can be measured jointly with other timing parameters using single-frequency data. The parameter correlation can be mitigated by using multi-frequency data, which also significantly improves the measurement precision of these parameters; this is particularly important for pulsars at a medium or high ecliptic latitude. Additionally, for a selection of pulsars we reprocess their EPTA Data Release 2 data to include modelling of solar-wind effect in the timing analysis. This delivers significant measurements of both parallax and solar-wind density, the latter of which are consistent with those obtained at low-frequency band. In the future, combining pulsar timing data at gigahertz and lower frequencies will probably deliver the most robust and precise measurements of astrometry and solar wind properties in pulsar timing., Comment: 15 pages, 15 figures, 1 table, accepted for publication in MNRAS

Multigrid methods despite being known to be asymptotically optimal algorithms, depend on the careful selection of their individual components for efficiency. Also, they are mostly restricted to standard cycle types like V-, F-, and W-cycles. We use grammar rules to generate arbitrary-shaped cycles, wherein the smoothers and their relaxation weights are chosen independently at each step within the cycle. We call this a flexible multigrid cycle. These flexible cycles are used in Algebraic Multigrid (AMG) methods with the help of grammar rules and optimized using genetic programming. The flexible AMG methods are implemented in the software library of hypre, and the programs are optimized separately for two cases: a standalone AMG solver for a 3D anisotropic problem and an AMG preconditioner with conjugate gradient for a multiphysics code. We observe that the optimized flexible cycles provide higher efficiency and better performance than the standard cycle types.

Ultra-light axion-like particles (ALPs) can be a viable solution to the dark matter problem. The scalar field associated with ALPs, coupled to the electromagnetic field, acts as an active birefringent medium, altering the polarisation properties of light through which it propagates. In particular, oscillations of the axionic field induce monochromatic variations of the plane of linearly polarised radiation of astrophysical signals. The radio emission of millisecond pulsars provides an excellent tool to search for such manifestations, given their high fractional linear polarisation and negligible fluctuations of their polarisation properties. We have searched for the evidence of ALPs in the polarimetry measurements of pulsars collected and preprocessed for the European Pulsar Timing Array (EPTA) campaign. Focusing on the twelve brightest sources in linear polarisation, we searched for an astrophysical signal from axions using both frequentist and Bayesian statistical frameworks. For the frequentist analysis, which uses Lomb-Scargle periodograms at its core, no statistically significant signal has been found. The model used for the Bayesian analysis has been adjusted to accommodate multiple deterministic systematics that may be present in the data. A statistically significant signal has been found in the dataset of multiple pulsars with common frequency between $10^{-8}$ Hz and $2\times10^{-8}$ Hz, which can most likely be explained by the residual Faraday rotation in the terrestrial ionosphere. Strong bounds on the coupling constant $g_{a\gamma}$, in the same ballpark as other searches, have been obtained in the mass range between $6\times10^{-24}$ eV and $5\times10^{-21}$ eV. We conclude by discussing problems that can limit the sensitivity of our search for ultra-light axions in the polarimetry data of pulsars, and possible ways to resolve them., Comment: 24 pages, 15 figures

In an accompanying publication, the MeerKAT Pulsar Timing Array (MPTA) collaboration reports tentative evidence for the presence of a stochastic gravitational-wave background, following observations of similar signals from the European and Indian Pulsar Timing Arrays, NANOGrav, the Parkes Pulsar Timing Array and the Chinese Pulsar Timing Array. If such a gravitational-wave background signal originates from a population of inspiraling supermassive black-hole binaries, the signal may be anisotropically distributed on the sky. In this Letter we evaluate the anisotropy of the MPTA signal using a spherical harmonic decomposition. We discuss complications arising from the covariance between pulsar pairs and regularisation of the Fisher matrix. Applying our method to the 4.5 yr dataset, we obtain two forms of sky maps for the three most sensitive MPTA frequency bins between 7 -21 nHz. Our "clean maps'' estimate the distribution of gravitational-wave strain power with minimal assumptions. Our radiometer maps answer the question: is there a statistically significant point source? We find a noteworthy hotspot in the 7 nHz clean map with a $p$-factor of $p=0.015$ (not including trial factors). Future observations are required to determine if this hotspot is of astrophysical origin.

Pulsar Timing Arrays search for nanohertz-frequency gravitational waves by regularly observing ensembles of millisecond pulsars over many years to look for correlated timing residuals. Recently the first evidence for a stochastic gravitational wave background has been presented by the major Arrays, with varying levels of significance ($\sim$2-4$\sigma$). In this paper we present the results of background searches with the MeerKAT Pulsar Timing Array. Although of limited duration (4.5 yr), the $\sim$ 250,000 arrival times with a median error of just $3 \mu$s on 83 pulsars make it very sensitive to spatial correlations. Detection of a gravitational wave background requires careful modelling of noise processes to ensure that any correlations represent a fit to the underlying background and not other misspecified processes. Under different assumptions about noise processes we can produce either what appear to be compelling Hellings-Downs correlations of high significance (3-3.4$\sigma$) with a spectrum close to that which is predicted, or surprisingly, under slightly different assumptions, ones that are insignificant. This appears to be related to the fact that many of the highest precision MeerKAT Pulsar Timing Array pulsars are in close proximity and dominate the detection statistics. The sky-averaged characteristic strain amplitude of the correlated signal in our most significant model is $h_{c, {\rm yr}} = 7.5^{+0.8}_{-0.9} \times 10^{-15}$ measured at a spectral index of $\alpha=-0.26$, decreasing to $h_{c, {\rm yr}} = 4.8^{+0.8}_{-0.9} \times 10^{-15}$ when assessed at the predicted $\alpha=-2/3$. These data will be valuable as the International Pulsar Timing Array project explores the significance of gravitational wave detections and their dependence on the assumed noise models.

Pulsar timing arrays are ensembles of regularly observed millisecond pulsars timed to high precision. Each pulsar in an array could be affected by a suite of noise processes, most of which are astrophysically motivated. Analysing them carefully can be used to understand these physical processes. However, the primary purpose of these experiments is to detect signals that are common to all pulsars, in particular signals associated with a stochastic gravitational wave background. To detect this, it is paramount to appropriately characterise other signals that may otherwise impact array sensitivity or cause a spurious detection. Here we describe the second data release and first detailed noise analysis of the pulsars in the MeerKAT Pulsar Timing Array, comprising high-cadence and high-precision observations of $83$ millisecond pulsars over $4.5$ years. We use this analysis to search for a common signal in the data, finding a process with an amplitude of $\log_{10}\mathrm{A_{CURN}} = -14.25^{+0.21}_{-0.36}$ and spectral index $\gamma_\mathrm{CURN} = 3.60^{+1.31}_{-0.89}$. Fixing the spectral index at the value predicted for a background produced by the inspiral of binary supermassive black holes, we measure the amplitude to be $\log_{10}\mathrm{A_{CURN}} = -14.28^{+0.21}_{-0.21}$ at a significance expressed as a Bayes factor of $\ln(\mathcal{B}) = 4.46$. Under both assumptions, the amplitude that we recover is larger than those reported by other PTA experiments. We use the results of this analysis to forecast our sensitivity to a gravitational wave background possessing the spectral properties of the common signal we have measured.

Amyotrophic lateral sclerosis (ALS), a progressive neuromuscular degenerative disease, severely restricts patient communication capacity within a few years of onset, resulting in a significant deterioration of quality of life. The P300 speller brain computer interface (BCI) offers an alternative communication medium by leveraging a subject's EEG response to characters traditionally highlighted on a character grid on a graphical user interface (GUI). A recurring theme in P300-based research is enhancing performance to enable faster subject interaction. This study builds on that theme by addressing key limitations, particularly in the training of multi-subject classifiers, and by integrating advanced language models to optimize stimuli presentation and word prediction, thereby improving communication efficiency. Furthermore, various advanced large language models such as Generative Pre-Trained Transformer (GPT2), BERT, and BART, alongside Dijkstra's algorithm, are utilized to optimize stimuli and provide word completion choices based on the spelling history. In addition, a multi-layered smoothing approach is applied to allow for out-of-vocabulary (OOV) words. By conducting extensive simulations based on randomly sampled EEG data from subjects, we show substantial speed improvements in typing passages that include rare and out-of-vocabulary (OOV) words, with the extent of improvement varying depending on the language model utilized. The gains through such character-level interface optimizations are approximately 10%, and GPT2 for multi-word prediction provides gains of around 40%. In particular, some large language models achieve performance levels within 10% of the theoretical performance limits established in this study. In addition, both within and across subjects, training techniques are explored, and speed improvements are shown to hold in both cases., Comment: 21 pages, 11 figures, 1 table. arXiv admin note: substantial text overlap with arXiv:2405.13329

Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. Prior works have explored ever more complex KD strategies involving different objective functions, teacher-ensembles, and weight inheritance. In this work we explore an alternative, yet simple approach -- active data curation as effective distillation for contrastive multimodal pretraining. Our simple online batch selection method, ACID, outperforms strong KD baselines across various model-, data- and compute-configurations. Further, we find such an active data curation strategy to in fact be complementary to standard KD, and can be effectively combined to train highly performant inference-efficient models. Our simple and scalable pretraining framework, ACED, achieves state-of-the-art results across 27 zero-shot classification and retrieval tasks with upto 11% less inference FLOPs. We further demonstrate that our ACED models yield strong vision-encoders for training generative multimodal models in the LiT-Decoder setting, outperforming larger vision encoders for image-captioning and visual question-answering tasks.

Conformal Prediction is a robust framework that ensures reliable coverage across machine learning tasks. Although recent studies have applied conformal prediction to graph neural networks, they have largely emphasized post-hoc prediction set generation. Improving conformal prediction during the training stage remains unaddressed. In this work, we tackle this challenge from a denoising perspective by introducing SparGCP, which incorporates graph sparsification and a conformal prediction-specific objective into GNN training. SparGCP employs a parameterized graph sparsification module to filter out task-irrelevant edges, thereby improving conformal prediction efficiency. Extensive experiments on real-world graph datasets demonstrate that SparGCP outperforms existing methods, reducing prediction set sizes by an average of 32\% and scaling seamlessly to large networks on commodity GPUs.

Drug discovery typically consists of multiple steps, including identifying a target protein key to a disease's etiology, validating that interacting with this target could prevent symptoms or cure the disease, discovering a small molecule or biologic therapeutic to interact with it, and optimizing the candidate molecule through a complex landscape of required properties. Drug discovery related tasks often involve prediction and generation while considering multiple entities that potentially interact, which poses a challenge for typical AI models. For this purpose we present MAMMAL - Molecular Aligned Multi-Modal Architecture and Language - a method that we applied to create a versatile multi-task multi-align foundation model that learns from large-scale biological datasets (2 billion samples) across diverse modalities, including proteins, small molecules, and genes. We introduce a prompt syntax that supports a wide range of classification, regression, and generation tasks. It allows combining different modalities and entity types as inputs and/or outputs. Our model handles combinations of tokens and scalars and enables the generation of small molecules and proteins, property prediction, and transcriptomic lab test predictions. We evaluated the model on 11 diverse downstream tasks spanning different steps within a typical drug discovery pipeline, where it reaches new SOTA in 9 tasks and is comparable to SOTA in 2 tasks. This performance is achieved while using a unified architecture serving all tasks, in contrast to the original SOTA performance achieved using tailored architectures. The model code and pretrained weights are publicly available at https://github.com/BiomedSciAI/biomed-multi-alignment and https://huggingface.co/ibm/biomed.omics.bl.sm.ma-ted-458m.

The interstellar medium of the Milky Way contains turbulent plasma with structures driven by energetic processes that fuel star formation and shape the evolution of our Galaxy. Radio waves from pulsars are scattered off the small (au-scale and below) structures, resulting in frequency-dependent interference patterns that are modulated in time because of the relative motions of the pulsar, Earth, and plasma. Power spectral analyses of these patterns show parabolic arcs with curvatures that encode the locations and kinematics of individual structures. Here we report the discovery of at least 25 distinct plasma structures in the direction of the brilliant millisecond pulsar, PSR J0437$-$4715, in observations obtained with the MeerKAT radio telescope. Four arcs reveal structures within 5000 au of the pulsar, from a series of shocks induced as the pulsar and its wind interact with the ambient insterstellar medium. The measured radial distance and velocity of the main shock allows us to solve the shock geometry and space velocity of the pulsar in three dimensions, while the velocity of another structure unexpectedly indicates a back flow from the direction of the shock or pulsar-wind tail. The remaining 21 arcs represent a surprising abundance of structures sustained by turbulence within the Local Bubble -- a region of the interstellar medium thought to be depleted of gas by a series of supernova explosions about 14 Myr ago., Comment: 46 pages, 10 figures, 1 table, submitted to Nature Astronomy

Foundation models applied to bio-molecular space hold promise to accelerate drug discovery. Molecular representation is key to building such models. Previous works have typically focused on a single representation or view of the molecules. Here, we develop a multi-view foundation model approach, that integrates molecular views of graph, image and text. Single-view foundation models are each pre-trained on a dataset of up to 200M molecules and then aggregated into combined representations. Our multi-view model is validated on a diverse set of 18 tasks, encompassing ligand-protein binding, molecular solubility, metabolism and toxicity. We show that the multi-view models perform robustly and are able to balance the strengths and weaknesses of specific views. We then apply this model to screen compounds against a large (>100 targets) set of G Protein-Coupled receptors (GPCRs). From this library of targets, we identify 33 that are related to Alzheimer's disease. On this subset, we employ our model to identify strong binders, which are validated through structure-based modeling and identification of key binding motifs., Comment: 37 pages including supplement. 10 figures, 8 tables

We use supersymmetry to enlarge the dimension of the Hilbert space on which the unitary evolution of the state of the quantum fields acts. We discuss how to control the unitary evolution or TPCP maps generated by the quantum evolution of the fields by controlling the vacuum expectations of other fields in the theory. This amounts to breaking supersymmetry using control vacuum expectation values of the other fields. The evolution of the wave functional or TPCP maps obtained by tracing out over other fields is based on the Feynman path integral formula for the fields. By using the methods of quantum stochastic filtering, we estimate the evolving state of the fields from non-demolition noise measurements and then design a family of TPCP maps evolving in time whose outputs match the estimated evolving state. In this way, we are able to simulate the evolution of the state of the quantum noisy fields. Direct matching of the designed TPCP map to output the evolving system state is not possible since there is no way by which we can determine the exact evolving state, we can only estimate it using non-demolition measurements. The family of designed TPCP maps can be based on using a simulated master equation with unknown parameters incorporated into the Hamiltonian and the other Lindblad operators, chosen so as to match the state outputted by the quantum filter.

Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data. To address this, Retrieval-Augmented Generation (RAG) uses external knowledge bases (KBs), but these can also suffer from inaccuracies. We introduce STACKFEED, a novel Structured Textual Actor-Critic Knowledge base editing with FEEDback approach that iteratively refines the KB based on expert feedback using a multi-actor, centralized critic reinforcement learning framework. Each document is assigned to an actor, modeled as a ReACT agent, which performs structured edits based on document-specific targeted instructions from a centralized critic. Experimental results show that STACKFEED significantly improves KB quality and RAG system performance, enhancing accuracy by up to 8% over baselines.

Machine learning (ML) course for undergraduates face challenges in assessing student learning and providing practical exposure. Group project-based learning, an increasingly popular form of experiential learning in CS education, encounters certain limitation in participation and non-participation from a few students. Studies also suggest that students find longer programming assignments and project-based assessments distracting and struggle to maintain focus when they coincide with other courses. To tackle these issues, we introduced FlashHack: a monitored, incremental, in-classroom micro Hackathon that combines project-based learning with Hackathon elements. Engaging 229 third year CS undergraduate students in teams of four, FlashHack prompted them to tackle predefined challenges using machine learning techniques within a set timeframe. Assessment criteria emphasized machine learning application, problem-solving, collaboration, and creativity. Our results indicate high student engagement and satisfaction, alongside simplified assessment processes for instructors. This experience report outlines the Hackathon design and implementation, highlights successes and areas for improvement making it feasible for replication by interested computing educators.

Conformal prediction has become increasingly popular for quantifying the uncertainty associated with machine learning models. Recent work in graph uncertainty quantification has built upon this approach for conformal graph prediction. The nascent nature of these explorations has led to conflicting choices for implementations, baselines, and method evaluation. In this work, we analyze the design choices made in the literature and discuss the tradeoffs associated with existing methods. Building on the existing implementations for existing methods, we introduce techniques to scale existing methods to large-scale graph datasets without sacrificing performance. Our theoretical and empirical results justify our recommendations for future scholarship in graph conformal prediction.

Nowadays, transit timing variations (TTVs) are proving to be a very valuable tool in exoplanetary science to detect exoplanets by observing variations in transit times. To study the transit timing variation of the hot Jupiter, TrES-2b, we have combined 64 high-quality transit light curves from all seven sectors of NASA's Transiting Exoplanet Survey Satellite (TESS) along with 60 best-quality light curves from the ground-based facility Exoplanet Transit Database (ETD) and 106 mid-transit times from the previous works. From the precise transit timing analysis, we have observed a significant improvement in the orbital ephemerides, but we did not detect any short period TTVs that might result from an additional body. The inability to detect short-term TTVs further motivates us to investigate long-term TTVs, which might be caused by orbital decay, apsidal precession, Applegate mechanism, and $R{\phi}$mer effect and the orbital decay appeared to be a better explanation for the observed TTV with $\Delta BIC$ = 4.32. The orbital period of the hot Jupiter TrES-2b appears to be shrinking at a rate of $-5.58 \pm 1.81$ ms/yr. Assuming this decay is primarily caused by tidal dissipation within the host star, we have subsequently calculated the stellar tidal quality factor value to be 9900, which is 2 to 3 orders of magnitude smaller than the theoretically predicted values for other hot-Jupiter systems and its low value indicates more efficient tidal dissipation within the host star. Additional precise photometric and radial velocity observations are required to pinpoint the cause of the change in the orbital period., Comment: 38 pages, accepted by AJ on 2nd August

There have been several modifications of how basic calculus has been taught, but very few of these modifications have considered the computational tools available at our disposal. Here, we present a few tools that are easy to develop and use. Doing so also addresses a different way to view calculus, and attempts to fill the gaps in students' understanding of both differentiation and integration. We will describe the basics of both these topics in a way that might be much more useful and relevant to students, and hence possible ways in refining calculus pedagogy to make calculus more accessible to them. For integration, an elementary development of Gaussian quadrature using basic linear algebra is presented. This numerical method can be extended to integrate functions over various domains in higher dimensions, a subject that is not currently well covered in multivariable calculus or other Mathematics courses. We also briefly discuss series that may be more useful than some of those taught in current calculus courses., Comment: 9 pages

The Prony method for approximating signals comprising sinusoidal/exponential components is known through the pioneering work of Prony in his seminal dissertation in the year 1795. However, the Prony method saw the light of real world application only upon the advent of the computational era, which made feasible the extensive numerical intricacies and labor which the method demands inherently. The Adaptive LMS Filter which has been the most pervasive method for signal filtration and approximation since its inception in 1965 does not provide a consistently assured level of highly precise results as the extended experiment in this work proves. As a remedy this study improvises upon the Prony method by observing that a better (more precise) computational approximation can be obtained under the premise that adjustment can be made for computational error , in the autoregressive model setup in the initial step of the Prony computation itself. This adjustment is in proportion to the deviation of the coefficients in the same autoregressive model. The results obtained by this improvisation live up to the expectations of obtaining consistency and higher value in the precision of the output (recovered signal) approximations as shown in this current work and as compared with the results obtained using the Adaptive LMS Filter.

Amyotrophic lateral sclerosis (ALS) severely impairs patients' ability to communicate, often leading to a decline in their quality of life within a few years of diagnosis. The P300 speller brain-computer interface (BCI) offers an alternative communication method by interpreting a subject's EEG response to characters presented on a grid interface. This paper addresses the common speed limitations encountered in training efficient P300-based multi-subject classifiers by introducing innovative "across-subject" classifiers. We leverage a combination of the second-generation Generative Pre-Trained Transformer (GPT2) and Dijkstra's algorithm to optimize stimuli and suggest word completion choices based on typing history. Additionally, we employ a multi-layered smoothing technique to accommodate out-of-vocabulary (OOV) words. Through extensive simulations involving random sampling of EEG data from subjects, we demonstrate significant speed enhancements in typing passages containing rare and OOV words. These optimizations result in approximately 10% improvement in character-level typing speed and up to 40% improvement in multi-word prediction. We demonstrate that augmenting standard row/column highlighting techniques with layered word prediction yields close-to-optimal performance. Furthermore, we explore both "within-subject" and "across-subject" training techniques, showing that speed improvements are consistent across both approaches.

This report examines the fine-tuning of Large Language Models (LLMs), integrating theoretical insights with practical applications. It outlines the historical evolution of LLMs from traditional Natural Language Processing (NLP) models to their pivotal role in AI. A comparison of fine-tuning methodologies, including supervised, unsupervised, and instruction-based approaches, highlights their applicability to different tasks. The report introduces a structured seven-stage pipeline for fine-tuning LLMs, spanning data preparation, model initialization, hyperparameter tuning, and model deployment. Emphasis is placed on managing imbalanced datasets and optimization techniques. Parameter-efficient methods like Low-Rank Adaptation (LoRA) and Half Fine-Tuning are explored for balancing computational efficiency with performance. Advanced techniques such as memory fine-tuning, Mixture of Experts (MoE), and Mixture of Agents (MoA) are discussed for leveraging specialized networks and multi-agent collaboration. The report also examines novel approaches like Proximal Policy Optimization (PPO) and Direct Preference Optimization (DPO), which align LLMs with human preferences, alongside pruning and routing optimizations to improve efficiency. Further sections cover validation frameworks, post-deployment monitoring, and inference optimization, with attention to deploying LLMs on distributed and cloud-based platforms. Emerging areas such as multimodal LLMs, fine-tuning for audio and speech, and challenges related to scalability, privacy, and accountability are also addressed. This report offers actionable insights for researchers and practitioners navigating LLM fine-tuning in an evolving landscape.

Traditional methods for making software deployment decisions in the automotive industry typically rely on manual analysis of tabular software test data. These methods often lead to higher costs and delays in the software release cycle due to their labor-intensive nature. Large Language Models (LLMs) present a promising solution to these challenges. However, their application generally demands multiple rounds of human-driven prompt engineering, which limits their practical deployment, particularly for industrial end-users who need reliable and efficient results. In this paper, we propose GoNoGo, an LLM agent system designed to streamline automotive software deployment while meeting both functional requirements and practical industrial constraints. Unlike previous systems, GoNoGo is specifically tailored to address domain-specific and risk-sensitive systems. We evaluate GoNoGo's performance across different task difficulties using zero-shot and few-shot examples taken from industrial practice. Our results show that GoNoGo achieves a 100% success rate for tasks up to Level 2 difficulty with 3-shot examples, and maintains high performance even for more complex tasks. We find that GoNoGo effectively automates decision-making for simpler tasks, significantly reducing the need for manual intervention. In summary, GoNoGo represents an efficient and user-friendly LLM-based solution currently employed in our industrial partner's company to assist with software release decision-making, supporting more informed and timely decisions in the release process for risk-sensitive vehicle systems.

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

This paper demonstrates the impact of state-of-the-art instrumental calibration techniques on the precision of arrival times obtained from 9.6 years of observations of millisecond pulsars using the Murriyang 64-m CSIRO Parkes Radio Telescope. Our study focuses on 21-cm observations of 25 high-priority pulsars that are regularly observed as part of the Parkes Pulsar Timing Array (PPTA) project, including those predicted to be the most susceptible to calibration errors. We employ Measurement Equation Template Matching (METM) for instrumental calibration and Matrix Template Matching (MTM) for arrival time estimation, resulting in significantly improved timing residuals with up to a sixfold reduction in white noise compared to arrival times estimated using Scalar Template Matching and conventional calibration based on the Ideal Feed Assumption. The median relative reduction in white noise is 33 percent, and the maximum absolute reduction is 4.5 microseconds. For PSR J0437-4715, METM and MTM reduce the best-fit power-law amplitude (2.7 sigma) and spectral index (1.7 sigma) of the red noise in the arrival time residuals, which can can be tentatively interpreted as mitigation of 1/f noise due to otherwise unmodeled steps in polarimetric response. These findings demonstrate the potential to directly enhance the sensitivity of pulsar timing array experiments through more accurate methods of instrumental calibration and arrival time estimation., Comment: 30 pages, 9 figures, accepted for publication in The Astrophysical Journal

Program verification tools are often implemented as front-end translations of an input program into an intermediate verification language (IVL) such as Boogie, GIL, Viper, or Why3. The resulting IVL program is then verified using an existing back-end verifier. A soundness proof for such a translational verifier needs to relate the input program and verification logic to the semantics of the IVL, which in turn needs to be connected with the verification logic implemented in the back-end verifiers. Performing such proofs is challenging due to the large semantic gap between the input and output programs and logics, especially for complex verification logics such as separation logic. This paper presents a formal framework for reasoning about translational separation logic verifiers. At its center is a generic core IVL that captures the essence of different separation logics. We define its operational semantics and formally connect it to two different back-end verifiers, which use symbolic execution and verification condition generation, resp. Crucially, this semantics uses angelic non-determinism to enable the application of different proof search algorithms and heuristics in the back-end verifiers. An axiomatic semantics for the core IVL simplifies reasoning about the front-end translation by performing essential proof steps once and for all in the equivalence proof with the operational semantics rather than for each concrete front-end translation. We illustrate the usefulness of our formal framework by instantiating our core IVL with elements of Viper and connecting it to two Viper back-ends as well as a front-end for concurrent separation logic. All our technical results have been formalized in Isabelle/HOL, including the core IVL and its semantics, the semantics of two back-ends for a subset of Viper, and all proofs., Comment: Extended version of POPL'25 paper

This paper presents Hardware Description Language Generative Pre-trained Transformers (HDL-GPT), a novel approach that leverages the vast repository of open-source High Definition Language (HDL) codes to train superior quality large code models. The core premise of this paper is the hypothesis that high-quality HDL is all you need to create models with exceptional performance and broad zero-shot generalization abilities. The paper elucidates the methods employed for the curation and augmentation of large corpora from open-source HDL code, transforming highly variable quality data into high-quality data through careful prompting and context maintenance. We demonstrate that the careful selection, filtering, and augmentation of data across HDLs can yield powerful models that surpass current state-of-the-art models. We also explore the impact of different fine-tuning methods on the quality of results. We describe experimental results across a range of fine-tuned SOTA LLMs, substantiating our claims. We demonstrate improvements of 50% to 200% over SOTA HDL models on current benchmarks in tasks ranging from HDL circuit explanations, code generation, formal and simulation testbench creation, triaging bugs, and fixing them. HDL-GPT opens new avenues for the development of advanced model training techniques for circuit design tasks., Comment: DAC 2024 Invited Paper

Thin Si-doped Al-rich (Al>0.85) regrown Al(Ga)N layers were deposited on AlN on Sapphire template using metal-organic chemical vapor deposition (MOCVD) techniques. The optimization of the deposition conditions such as temperature, V/III ratio, deposition rate, and Si concentration resulted in a high charge carrier concentration (>$10^{15}/cm^{3}$) in the Si-doped Al-rich Al(Ga)N films. A pulsed deposition condition was employed to achieve a controllable Al composition greater than 95% and to prevent unintended Ga incorporation in the AlGaN material deposited using the close-coupled showerhead reactor. Also, the effect of unintentional Si incorporation on free charge carrier concentration at the regrowth interface was observed by varying the thickness of the regrown Al(Ga)N layer. A maximum charge carrier concentration of $4.8\times 10^{16}/cm^3$ and $7.5\times 10^{15}/cm^3$ were achieved for Al0.97Ga0.03N and AlN films with thickness <300 nm compared to previously reported n-Al(Ga)N films with thickness $\ge$400 nm deposited using MOCVD technique., Comment: 13 pages, 5 figures

Educating students about academic integrity expectations has been suggested as one of the ways to reduce malpractice in take-home programming assignments. We test this hypothesis using data collected from an artificial intelligence course with 105 participants (N=105) at a university in India. The AI course had two programming assignments. Plagiarism through collusion was quantified using the Measure of Software Similarity (MOSS) tool. Students were educated about what constitutes academic dishonesty and were required to take an honor pledge before the start of the second take-home programming assignment. The two programming assignments were novel and did not have solutions available on the internet. We expected the mean percentage of similar lines of code to be significantly less in the second programming assignment. However, our results show no significant difference in the mean percentage of similar lines of code across the two programming assignments. We also study how the Big-five personality traits affect the propensity for plagiarism in the two take-home assignments. Our results across both assignments show that the extraversion trait of the Big Five personality exhibits a positive association, and the conscientiousness trait exhibits a negative association with plagiarism tendencies. Our result suggests that the policy of educating students about academic integrity will have a limited impact as long as students perceive an opportunity for plagiarism to be present. We explain our results using the Fraud triangle model., Comment: 11 pages, 3 figures, To be published in ACM International Conference on Computing Education Research (ICER) 2024

Data curation is an essential component of large-scale pretraining. In this work, we demonstrate that jointly selecting batches of data is more effective for learning than selecting examples independently. Multimodal contrastive objectives expose the dependencies between data and thus naturally yield criteria for measuring the joint learnability of a batch. We derive a simple and tractable algorithm for selecting such batches, which significantly accelerate training beyond individually-prioritized data points. As performance improves by selecting from larger super-batches, we also leverage recent advances in model approximation to reduce the associated computational overhead. As a result, our approach--multimodal contrastive learning with joint example selection (JEST)--surpasses state-of-the-art models with up to 13$\times$ fewer iterations and 10$\times$ less computation. Essential to the performance of JEST is the ability to steer the data selection process towards the distribution of smaller, well-curated datasets via pretrained reference models, exposing the level of data curation as a new dimension for neural scaling laws., Comment: Main text: 9 pages, 5 figures, 3 tables, 1 algorithm. Appendix: 7 pages, 5 figures, 1 table, 2. algorithm

A recent frontier in computer vision has been the task of 3D video generation, which consists of generating a time-varying 3D representation of a scene. To generate dynamic 3D scenes, current methods explicitly model 3D temporal dynamics by jointly optimizing for consistency across both time and views of the scene. In this paper, we instead investigate whether it is necessary to explicitly enforce multiview consistency over time, as current approaches do, or if it is sufficient for a model to generate 3D representations of each timestep independently. We hence propose a model, Vid3D, that leverages 2D video diffusion to generate 3D videos by first generating a 2D "seed" of the video's temporal dynamics and then independently generating a 3D representation for each timestep in the seed video. We evaluate Vid3D against two state-of-the-art 3D video generation methods and find that Vid3D is achieves comparable results despite not explicitly modeling 3D temporal dynamics. We further ablate how the quality of Vid3D depends on the number of views generated per frame. While we observe some degradation with fewer views, performance degradation remains minor. Our results thus suggest that 3D temporal knowledge may not be necessary to generate high-quality dynamic 3D scenes, potentially enabling simpler generative algorithms for this task., Comment: 14 pages, 10 figures, 3 tables

In recent years, there has been rising interest from both governments and private industry in developing software that is accessible to all, including people with disabilities. However, the computer science (CS) courses that ought to prepare future professionals to develop such accessible software hardly cover topics related to accessibility. While there is growing literature on incorporating accessibility topics in computing education in the West, there is little work on this in the Global South, particularly in India, which has a large number of computing students and software professionals. In this replication report, we present (A) our findings from a replication of surveys used in the US and Switzerland on who teaches accessibility and barriers to teaching accessibility and (B) a qualitative analysis of perceptions of CS faculty in India about digital accessibility and teaching accessibility. Our study corroborates the findings of the earlier surveys: very few CS faculty teach accessibility, and the top barriers they perceive are the same. The qualitative analysis further reveals that the faculty in India need training on accessibility concepts and disabilities sensitization, and exposure to existing and ongoing CS education research and pedagogies. In light of these findings, we present recommendations aimed at addressing these challenges and enhancing the integration of accessibility into computing education., Comment: Accepted to be published in proceedings of the ACM International Conference on Computing Education Research (ICER) 2024

An analysis of high-resolution ($R\sim48\,000$) optical spectrum of hot (B1Ibe) post-AGB star LS 4331 (IRAS 17381-1616) is presented. The detailed identification of the observed absorption and emission features in the wavelength range 3700-9200 \r{A} is carried out for the first time. From non-LTE analysis of absorption lines the atmospheric parameters and chemical composition of the star are derived. We estimate $T_{\rm eff}=20~900\pm500$ K, $\log g=2.57\pm0.08$, $V_r=-51.7\pm0.8$ km s$^{-1}$, $\xi_{\rm t}=24\pm4$ km s$^{-1}$ and $v \sin i=30\pm5$ km s$^{-1}$. A abundance analysis for C, N, O, Mg, Al, S and Si reveals that the N and O abundance is close to solar while metal underabundances relative to the solar value (i.e. [Mg/H] = -1.04 dex, [Al/H] = -1.20 dex, [Si/H] = -0.46 dex) are found. We conclude that LS 4331 is a high galactic latitude metal-poor and carbon deficient hot post-AGB star. The underabundance of carbon ([C/H]= -0.64 dex) is similar to that found in other hot post-AGB stars and indicates that the star's AGB phase of evolution was terminated before the third dredge up. From the nebular emission lines the plasma diagnostics are derived. The presence of nebular emission lines in the spectrum of LS 4331 indicates that the photoionization of circumstellar envelope has already started. The nebular parameters and expansion velocity of the nebula is derived. Using the Gaia DR3 distance the absolute luminosity of the star is derived and the star's position on the post-AGB evolutionary tracks suggests that its initial main sequence mass is about 1.2$M_{\odot}$. It is also reported that fast irregular brightness variations with an amplitude of up to 0.3 mag in $V$ band have been found in the star, typical of hot post-AGB objects.

This paper forms the second of a two-part series on the value of a participatory approach to AI development and deployment. The first paper had crafted a principled, as well as pragmatic, justification for deploying participatory methods in these two exercises (that is, development and deployment of AI). The pragmatic justification is that it improves the quality of the overall algorithm by providing more granular and minute information. The more principled justification is that it offers a voice to those who are going to be affected by the deployment of the algorithm, and through engagement attempts to build trust and buy-in for an AI system. By a participatory approach, we mean including various stakeholders (defined a certain way) in the actual decision making process through the life cycle of an AI system. Despite the justifications offered above, actual implementation depends crucially on how stakeholders in the entire process are identified, what information is elicited from them, and how it is incorporated. This paper will test these preliminary conclusions in two sectors, the use of facial recognition technology in the upkeep of law and order and the use of large language models in the healthcare sector. These sectors have been chosen for two primary reasons. Since Facial Recognition Technologies are a branch of AI solutions that are well-researched and the impact of which is well documented, it provides an established space to illustrate the various aspects of adapting PAI to an existing domain, especially one that has been quite contentious in the recent past. LLMs in healthcare provide a canvas for a relatively less explored space, and helps us illustrate how one could possibly envision enshrining the principles of PAI for a relatively new technology, in a space where innovation must always align with patient welfare.

The widespread adoption of Artificial Intelligence (AI) technologies in the public and private sectors has resulted in them significantly impacting the lives of people in new and unexpected ways. In this context, it becomes important to inquire how their design, development and deployment takes place. Upon this inquiry, it is seen that persons who will be impacted by the deployment of these systems have little to no say in how they are developed. Seeing this as a lacuna, this research study advances the premise that a participatory approach is beneficial (both practically and normatively) to building and using more responsible, safe, and human-centric AI systems. Normatively, it enhances the fairness of the process and empowers citizens in voicing concerns to systems that may heavily impact their lives. Practically, it provides developers with new avenues of information which will be beneficial to them in improving the quality of the AI algorithm. The paper advances this argument first, by describing the life cycle of an AI system; second, by identifying criteria which may be used to identify relevant stakeholders for a participatory exercise; and third, by mapping relevant stakeholders to different stages of AI lifecycle. This paper forms the first part of a two-part series on participatory governance in AI. The second paper will expand upon and concretise the principles developed in this paper and apply the same to actual use cases of AI systems.