Search

In a landscape where Generative AI is becoming increasingly influential across various sectors, its role and impact in educational settings, particularly from the viewpoint of undergraduate students, becomes essential to explore. This paper delves into the perceptions of students regarding the integration of GenAI tools like Claude AI in a college writing course. The aim is to utilize AI to enhance the processes of drafting and revising written work. This study examines how students perceive the utility and educational implications of AI in writing. Their feedback indicates a positive engagement with AI, providing critical insights into its potential and limitations and highlighting its role in enhancing the quality of writing and equipping students for an AI-driven future.

We calculate the 2024 impact factors of 36 most widely used journals in Astrophysics, using the citations collated by NASA/ADS (Astrophysics Data System) and compare them to the official impact factors. This includes journals which publish papers outside of astrophysics such as PRD, EPJC, Nature etc. We also propose a new metric to gauge the impact factor based on the median number of citations in a journal and calculate the same for all the journals. We find that the ADS-based impact factors are mostly in agreement, albeit higher than the official impact factors for most journals. The journals with the maximum fractional difference in median-based and old impact factors are JHEAP and PTEP. We find the maximum difference between the ADS and official impact factor for Nature., Comment: 5 pages. Comments welcome

Physics-informed neural networks (PINNs) have emerged as a versatile and widely applicable concept across various science and engineering domains over the past decade. This article offers a comprehensive overview of the fundamentals of PINNs, tracing their evolution, modifications, and various variants. It explores the impact of different parameters on PINNs and the optimization algorithms involved. The review also delves into the theoretical advancements related to the convergence, consistency, and stability of numerical solutions using PINNs, while highlighting the current state of the art. Given their ability to address equations involving complex physics, the article discusses various applications of PINNs, with a particular focus on their utility in computational fluid dynamics problems. Additionally, it identifies current gaps in the research and outlines future directions for the continued development of PINNs.

The optimization of expensive black-box simulators arises in a myriad of modern scientific and engineering applications. Bayesian optimization provides an appealing solution, by leveraging a fitted surrogate model to guide the selection of subsequent simulator evaluations. In practice, however, the objective is often not to obtain a single good solution, but rather a ''basket'' of good solutions from which users can choose for downstream decision-making. This need arises in our motivating application for real-time control of internal combustion engines for flight propulsion, where a diverse set of control strategies is essential for stable flight control. There has been little work on this front for Bayesian optimization. We thus propose a new Diverse Expected Improvement (DEI) method that searches for diverse ''$\epsilon$-optimal'' solutions: locally-optimal solutions within a tolerance level $\epsilon > 0$ from a global optimum. We show that DEI yields a closed-form acquisition function under a Gaussian process surrogate model, which facilitates efficient sequential queries via automatic differentiation. This closed form further reveals a novel exploration-exploitation-diversity trade-off, which incorporates the desired diversity property within the well-known exploration-exploitation trade-off. We demonstrate the improvement of DEI over existing methods in a suite of numerical experiments, then explore the DEI in two applications on rover trajectory optimization and engine control for flight propulsion.

Smart focal-plane and in-chip image processing has emerged as a crucial technology for vision-enabled embedded systems with energy efficiency and privacy. However, the lack of special datasets providing examples of the data that these neuromorphic sensors compute to convey visual information has hindered the adoption of these promising technologies. Neuromorphic imager variants, including event-based sensors, produce various representations such as streams of pixel addresses representing time and locations of intensity changes in the focal plane, temporal-difference data, data sifted/thresholded by temporal differences, image data after applying spatial transformations, optical flow data, and/or statistical representations. To address the critical barrier to entry, we provide an annotated, temporal-threshold-based vision dataset specifically designed for face detection tasks derived from the same videos used for Aff-Wild2. By offering multiple threshold levels (e.g., 4, 8, 12, and 16), this dataset allows for comprehensive evaluation and optimization of state-of-the-art neural architectures under varying conditions and settings compared to traditional methods. The accompanying tool flow for generating event data from raw videos further enhances accessibility and usability. We anticipate that this resource will significantly support the development of robust vision systems based on smart sensors that can process based on temporal-difference thresholds, enabling more accurate and efficient object detection and localization and ultimately promoting the broader adoption of low-power, neuromorphic imaging technologies. To support further research, we publicly released the dataset at \url{https://dx.doi.org/10.21227/bw2e-dj78}., Comment: 8 pages

Large Language Models (LLMs) have shown remarkable ability to generalize effectively across numerous industry domains while executing a range of tasks. Many of these competencies are obtained from the data utilized during the pre-training phase of the Language Models (LMs). However, these models exhibit limitations when tasked with performing in specialized or low-resource industry domains. More recent approaches use LLMs for generating domain-specific synthetic data but most often they lack in truthfulness and complexity. Alternatively, in cases where domain data is available like healthcare and finance most of the LMs are proprietary necessitating the need for a scalable method to curate real world industry specific pre-training data. In this work, we propose an automated and scalable framework - DoPAMine:Domain-specific Pre-training Adaptation from seed-guided data Mining, to mine domain specific training data from a large data corpus for domain adaptation of a LM. The framework leverages the parametric knowledge of a LLM to generate diverse and representative seed data tailored to a specific domain which is then used to mine real world data from a large data corpus like Common Crawl. We evaluated our framework's performance in the continual pre-training (CPT) setting by training two domain specific 7B parameter LMs in healthcare and finance with data mined via DoPAMine. Our experiments show that DoPAMine boosts the performance of pre-trained LLMs on average by 4.9% and 5.1% in zero-shot and 5-shot settings respectively on healthcare tasks from MMLU, MedQA, MedMCQA and PubMedQA datasets, and 2.9% and 6.7% for zero-shot and 5-shot settings respectively on finance tasks from FiQA-SA, FPB and Headlines datasets when compared to the baseline.

Identifying and classifying shutdown initiating events (SDIEs) is critical for developing low power shutdown probabilistic risk assessment for nuclear power plants. Existing computational approaches cannot achieve satisfactory performance due to the challenges of unavailable large, labeled datasets, imbalanced event types, and label noise. To address these challenges, we propose a hybrid pipeline that integrates a knowledge-informed machine learning mode to prescreen non-SDIEs and a large language model (LLM) to classify SDIEs into four types. In the prescreening stage, we proposed a set of 44 SDIE text patterns that consist of the most salient keywords and phrases from six SDIE types. Text vectorization based on the SDIE patterns generates feature vectors that are highly separable by using a simple binary classifier. The second stage builds Bidirectional Encoder Representations from Transformers (BERT)-based LLM, which learns generic English language representations from self-supervised pretraining on a large dataset and adapts to SDIE classification by fine-tuning it on an SDIE dataset. The proposed approaches are evaluated on a dataset with 10,928 events using precision, recall ratio, F1 score, and average accuracy. The results demonstrate that the prescreening stage can exclude more than 97% non-SDIEs, and the LLM achieves an average accuracy of 93.4% for SDIE classification.

Skid-steered wheel mobile robots (SSWMRs) operate in a variety of outdoor environments exhibiting motion behaviors dominated by the effects of complex wheel-ground interactions. Characterizing these interactions is crucial both from the immediate robot autonomy perspective (for motion prediction and control) as well as a long-term predictive maintenance and diagnostics perspective. An ideal solution entails capturing precise state measurements for decisions and controls, which is considerably difficult, especially in increasingly unstructured outdoor regimes of operations for these robots. In this milieu, a framework to identify pre-determined discrete modes of operation can considerably simplify the motion model identification process. To this end, we propose an interactive multiple model (IMM) based filtering framework to probabilistically identify predefined robot operation modes that could arise due to traversal in different terrains or loss of wheel traction.

This paper presents an innovative approach to dimensionality reduction and feature extraction in high-dimensional datasets, with a specific application focus on wood surface defect detection. The proposed framework integrates sparse modeling techniques, particularly Lasso and proximal gradient methods, into a comprehensive pipeline for efficient and interpretable feature selection. Leveraging pre-trained models such as VGG19 and incorporating anomaly detection methods like Isolation Forest and Local Outlier Factor, our methodology addresses the challenge of extracting meaningful features from complex datasets. Evaluation metrics such as accuracy and F1 score, alongside visualizations, are employed to assess the performance of the sparse modeling techniques. Through this work, we aim to advance the understanding and application of sparse modeling in machine learning, particularly in the context of wood surface defect detection.

Software Development Waste (SDW) is defined as any resource-consuming activity that does not add value to the client or the organization developing the software. SDW impacts the overall efficiency and productivity of a software project as the scale and size of the project grows. Although engineering leaders usually put in effort to minimize waste, the lack of definitive measures to track and manage SDW is a cause of concern. To address this gap, we propose five measures, namely Stale Forks, Project Diversification Index, PR Rejection Rate, Backlog Inversion Index, and Feature Fulfillment Rate to potentially identify unused artifacts, building the wrong feature/product, mismanagement of backlog types of SDW. We apply these measures on ten open-source projects and share our observations to apply them in practice for managing SDW., Comment: 9 pages, This manuscript is a pre-publication version of the paper that was published at IEEE SEAA 2024

Accurately recognizing a revisited place is crucial for embodied agents to localize and navigate. This requires visual representations to be distinct, despite strong variations in camera viewpoint and scene appearance. Existing visual place recognition pipelines encode the "whole" image and search for matches. This poses a fundamental challenge in matching two images of the same place captured from different camera viewpoints: "the similarity of what overlaps can be dominated by the dissimilarity of what does not overlap". We address this by encoding and searching for "image segments" instead of the whole images. We propose to use open-set image segmentation to decompose an image into `meaningful' entities (i.e., things and stuff). This enables us to create a novel image representation as a collection of multiple overlapping subgraphs connecting a segment with its neighboring segments, dubbed SuperSegment. Furthermore, to efficiently encode these SuperSegments into compact vector representations, we propose a novel factorized representation of feature aggregation. We show that retrieving these partial representations leads to significantly higher recognition recall than the typical whole image based retrieval. Our segments-based approach, dubbed SegVLAD, sets a new state-of-the-art in place recognition on a diverse selection of benchmark datasets, while being applicable to both generic and task-specialized image encoders. Finally, we demonstrate the potential of our method to ``revisit anything'' by evaluating our method on an object instance retrieval task, which bridges the two disparate areas of research: visual place recognition and object-goal navigation, through their common aim of recognizing goal objects specific to a place. Source code: https://github.com/AnyLoc/Revisit-Anything., Comment: Presented at ECCV 2024; Includes supplementary; 29 pages; 8 figures

We focus on recovering 3D object pose and shape from single images. This is highly challenging due to strong (self-)occlusions, depth ambiguities, the enormous shape variance, and lack of 3D ground truth for natural images. Recent work relies mostly on learning from finite datasets, so it struggles generalizing, while it focuses mostly on the shape itself, largely ignoring the alignment with pixels. Moreover, it performs feed-forward inference, so it cannot refine estimates. We tackle these limitations with a novel framework, called SDFit. To this end, we make three key observations: (1) Learned signed-distance-function (SDF) models act as a strong morphable shape prior. (2) Foundational models embed 2D images and 3D shapes in a joint space, and (3) also infer rich features from images. SDFit exploits these as follows. First, it uses a category-level morphable SDF (mSDF) model, called DIT, to generate 3D shape hypotheses. This mSDF is initialized by querying OpenShape's latent space conditioned on the input image. Then, it computes 2D-to-3D correspondences, by extracting and matching features from the image and mSDF. Last, it fits the mSDF to the image in an render-and-compare fashion, to iteratively refine estimates. We evaluate SDFit on the Pix3D and Pascal3D+ datasets of real-world images. SDFit performs roughly on par with state-of-the-art learned methods, but, uniquely, requires no re-training. Thus, SDFit is promising for generalizing in the wild, paving the way for future research. Code will be released, Comment: 11 pages, 7 figures, 2 tables

The integration of large language models (LLMs) with robotics has significantly advanced robots' abilities in perception, cognition, and task planning. The use of natural language interfaces offers a unified approach for expressing the capability differences of heterogeneous robots, facilitating communication between them, and enabling seamless task allocation and collaboration. Currently, the utilization of LLMs to achieve decentralized multi-heterogeneous robot collaborative tasks remains an under-explored area of research. In this paper, we introduce a novel framework that utilizes LLMs to achieve decentralized collaboration among multiple heterogeneous robots. Our framework supports three robot categories, mobile robots, manipulation robots, and mobile manipulation robots, working together to complete tasks such as exploration, transportation, and organization. We developed a rich set of textual feedback mechanisms and chain-of-thought (CoT) prompts to enhance task planning efficiency and overall system performance. The mobile manipulation robot can adjust its base position flexibly, ensuring optimal conditions for grasping tasks. The manipulation robot can comprehend task requirements, seek assistance when necessary, and handle objects appropriately. Meanwhile, the mobile robot can explore the environment extensively, map object locations, and communicate this information to the mobile manipulation robot, thus improving task execution efficiency. We evaluated the framework using PyBullet, creating scenarios with three different room layouts and three distinct operational tasks. We tested various LLM models and conducted ablation studies to assess the contributions of different modules. The experimental results confirm the effectiveness and necessity of our proposed framework.

We introduce a new robotic system that enables a mobile robot to autonomously explore an unknown environment, build a semantic map of the environment, and subsequently update the semantic map to reflect environment changes, such as location changes of objects. Our system leverages a LiDAR scanner for 2D occupancy grid mapping and an RGB-D camera for object perception. We introduce a semantic map representation that combines a 2D occupancy grid map for geometry, with a topological map for object semantics. This map representation enables us to effectively update the semantics by deleting or adding nodes to the topological map. Our system has been tested on a Fetch robot. The robot can semantically map a 93m x 90m floor and update the semantic map once objects are moved in the environment., Comment: 7 pages, 7 figures. Project page is available at https://irvlutd.github.io/SemanticMapping/

Embodied AI agents responsible for executing interconnected, long-sequence household tasks often face difficulties with in-context memory, leading to inefficiencies and errors in task execution. To address this issue, we introduce KARMA, an innovative memory system that integrates long-term and short-term memory modules, enhancing large language models (LLMs) for planning in embodied agents through memory-augmented prompting. KARMA distinguishes between long-term and short-term memory, with long-term memory capturing comprehensive 3D scene graphs as representations of the environment, while short-term memory dynamically records changes in objects' positions and states. This dual-memory structure allows agents to retrieve relevant past scene experiences, thereby improving the accuracy and efficiency of task planning. Short-term memory employs strategies for effective and adaptive memory replacement, ensuring the retention of critical information while discarding less pertinent data. Compared to state-of-the-art embodied agents enhanced with memory, our memory-augmented embodied AI agent improves success rates by 1.3x and 2.3x in Composite Tasks and Complex Tasks within the AI2-THOR simulator, respectively, and enhances task execution efficiency by 3.4x and 62.7x. Furthermore, we demonstrate that KARMA's plug-and-play capability allows for seamless deployment on real-world robotic systems, such as mobile manipulation platforms.Through this plug-and-play memory system, KARMA significantly enhances the ability of embodied agents to generate coherent and contextually appropriate plans, making the execution of complex household tasks more efficient. The experimental videos from the work can be found at https://youtu.be/4BT7fnw9ehs.

In an era where the exponential growth of image data driven by the Internet of Things (IoT) is outpacing traditional storage solutions, this work explores and advances the potential of Implicit Neural Representation (INR) as a transformative approach to image compression. INR leverages the function approximation capabilities of neural networks to represent various types of data. While previous research has employed INR to achieve compression by training small networks to reconstruct large images, this work proposes a novel advancement: representing multiple images with a single network. By modifying the loss function during training, the proposed approach allows a small number of weights to represent a large number of images, even those significantly different from each other. A thorough analytical study of the convergence of this new training method is also carried out, establishing upper bounds that not only confirm the validity of the method but also offer insights into optimal hyperparameter design. The proposed method is evaluated on the Kodak, ImageNet, and CIFAR-10 datasets. Experimental results demonstrate that all 24 images in the Kodak dataset can be represented by linear combinations of two sets of weights, achieving a peak signal-to-noise ratio (PSNR) of 26.5 dB with as low as 0.2 bits per pixel (BPP). The proposed method matches the rate-distortion performance of state-of-the-art image codecs, such as BPG, on the CIFAR-10 dataset. Additionally, the proposed method maintains the fundamental properties of INR, such as arbitrary resolution reconstruction of images., Comment: 10 pages, 13 figures

In today's world of advanced AI technologies, data management is a critical component of any AI/ML solution. Effective data management is vital for the creation and maintenance of high-quality, diverse datasets, which significantly enhance predictive capabilities and lead to smarter business solutions. In this work, we introduce MetaPix, a Data-centric AI platform offering comprehensive data management solutions specifically designed for unstructured data. MetaPix offers robust tools for data ingestion, processing, storage, versioning, governance, and discovery. The platform operates on four key concepts: DataSources, Datasets, Extensions and Extractors. A DataSource serves as MetaPix top level asset, representing a narrow-scoped source of data for a specific use. Datasets are MetaPix second level object, structured collections of data. Extractors are internal tools integrated into MetaPix's backend processing, facilitate data processing and enhancement. Additionally, MetaPix supports extensions, enabling integration with external third-party tools to enhance platform functionality. This paper delves into each MetaPix concept in detail, illustrating how they collectively contribute to the platform's objectives. By providing a comprehensive solution for managing and utilizing unstructured computer vision data, MetaPix equips organizations with a powerful toolset to develop AI applications effectively., Comment: Accepted @ The 22nd International Conference on Software Engineering Research & Practice

We introduce a novel method for joint expression and audio-guided talking face generation. Recent approaches either struggle to preserve the speaker identity or fail to produce faithful facial expressions. To address these challenges, we propose a NeRF-based network. Since we train our network on monocular videos without any ground truth, it is essential to learn disentangled representations for audio and expression. We first learn audio features in a self-supervised manner, given utterances from multiple subjects. By incorporating a contrastive learning technique, we ensure that the learned audio features are aligned to the lip motion and disentangled from the muscle motion of the rest of the face. We then devise a transformer-based architecture that learns expression features, capturing long-range facial expressions and disentangling them from the speech-specific mouth movements. Through quantitative and qualitative evaluation, we demonstrate that our method can synthesize high-fidelity talking face videos, achieving state-of-the-art facial expression transfer along with lip synchronization to unseen audio., Comment: Accepted by BMVC 2024. Project Page: https://starc52.github.io/publications/2024-07-19-JEAN

We introduce MoRAG, a novel multi-part fusion based retrieval-augmented generation strategy for text-based human motion generation. The method enhances motion diffusion models by leveraging additional knowledge obtained through an improved motion retrieval process. By effectively prompting large language models (LLMs), we address spelling errors and rephrasing issues in motion retrieval. Our approach utilizes a multi-part retrieval strategy to improve the generalizability of motion retrieval across the language space. We create diverse samples through the spatial composition of the retrieved motions. Furthermore, by utilizing low-level, part-specific motion information, we can construct motion samples for unseen text descriptions. Our experiments demonstrate that our framework can serve as a plug-and-play module, improving the performance of motion diffusion models. Code, pretrained models and sample videos will be made available at: https://motion-rag.github.io/

Object manipulation capabilities are essential skills that set apart embodied agents engaging with the world, especially in the realm of robotics. The ability to predict outcomes of interactions with objects is paramount in this setting. While model-based control methods have started to be employed for tackling manipulation tasks, they have faced challenges in accurately manipulating objects. As we analyze the causes of this limitation, we identify the cause of underperformance in the way current world models represent crucial positional information, especially about the target's goal specification for object positioning tasks. We introduce a general approach that empowers world model-based agents to effectively solve object-positioning tasks. We propose two declinations of this approach for generative world models: position-conditioned (PCP) and latent-conditioned (LCP) policy learning. In particular, LCP employs object-centric latent representations that explicitly capture object positional information for goal specification. This naturally leads to the emergence of multimodal capabilities, enabling the specification of goals through spatial coordinates or a visual goal. Our methods are rigorously evaluated across several manipulation environments, showing favorable performance compared to current model-based control approaches.

One way to understand planet formation is through studying the correlations between planet occurrence rates and stellar mass. However, measuring stellar mass in the red giant regime is very difficult. In particular, the spectroscopic masses of certain evolved stars, often referred to as "retired A-stars", have been questioned in the literature. Efforts to resolve this mass controversy using spectroscopy, interferometry and asteroseismology have so far been inconclusive. A recent ensemble study found a mass-dependent mass offset, but the result was based on only 16 stars. With NASA's Transiting Exoplanet Survey Satellite (TESS), we expand the investigation of the mass discrepancy to a total of 92 low-luminosity stars, synonymous with the retired A-stars. We measure their characteristic oscillation frequency, $\mathrm{\nu}_{\mathrm{max}}$, and the large frequency separation, $\mathrm{\Delta\nu}$, from their TESS photometric time series. Using these measurements and asteroseismic scaling relations, we derive asteroseismic masses and compare them with spectroscopic masses from five surveys, to comprehensively study the alleged mass-dependent mass offset. We find a mass offset between spectroscopy and seismology that increases with stellar mass. However, we note that adopting the seismic mass scale does not have a significant effect on the planet occurrence-mass-metallicity correlation for the so-called retired A-stars. We also report seismic measurements and masses for 157 higher luminosity giants (mostly helium-core-burning) from the spectroscopic surveys., Comment: 13 pages, 7 figues

As robotic systems become increasingly integrated into complex real-world environments, there is a growing need for approaches that enable robots to understand and act upon natural language instructions without relying on extensive pre-programmed knowledge of their surroundings. This paper presents PLATO, an innovative system that addresses this challenge by leveraging specialized large language model agents to process natural language inputs, understand the environment, predict tool affordances, and generate executable actions for robotic systems. Unlike traditional systems that depend on hard-coded environmental information, PLATO employs a modular architecture of specialized agents to operate without any initial knowledge of the environment. These agents identify objects and their locations within the scene, generate a comprehensive high-level plan, translate this plan into a series of low-level actions, and verify the completion of each step. The system is particularly tested on challenging tool-use tasks, which involve handling diverse objects and require long-horizon planning. PLATO's design allows it to adapt to dynamic and unstructured settings, significantly enhancing its flexibility and robustness. By evaluating the system across various complex scenarios, we demonstrate its capability to tackle a diverse range of tasks and offer a novel solution to integrate LLMs with robotic platforms, advancing the state-of-the-art in autonomous robotic task execution. For videos and prompt details, please see our project website: https://sites.google.com/andrew.cmu.edu/plato, Comment: 7 pages, 4 figures, submitted to ICRA 2025

We present a Morphology-Informed Heterogeneous Graph Neural Network (MI-HGNN) for learning-based contact perception. The architecture and connectivity of the MI-HGNN are constructed from the robot morphology, in which nodes and edges are robot joints and links, respectively. By incorporating the morphology-informed constraints into a neural network, we improve a learning-based approach using model-based knowledge. We apply the proposed MI-HGNN to two contact perception problems, and conduct extensive experiments using both real-world and simulated data collected using two quadruped robots. Our experiments demonstrate the superiority of our method in terms of effectiveness, generalization ability, model efficiency, and sample efficiency. Our MI-HGNN improved the performance of a state-of-the-art model that leverages robot morphological symmetry by 8.4% with only 0.21% of its parameters. Although MI-HGNN is applied to contact perception problems for legged robots in this work, it can be seamlessly applied to other types of multi-body dynamical systems and has the potential to improve other robot learning frameworks. Our code is made publicly available at https://github.com/lunarlab-gatech/Morphology-Informed-HGNN., Comment: 6 pages, 5 figures; This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

This paper intends to address the challenge of personalized recipe recommendation in the realm of diverse culinary preferences. The problem domain involves recipe recommendations, utilizing techniques such as association analysis and classification. Association analysis explores the relationships and connections between different ingredients to enhance the user experience. Meanwhile, the classification aspect involves categorizing recipes based on user-defined ingredients and preferences. A unique aspect of the paper is the consideration of recipes and ingredients belonging to multiple classes, recognizing the complexity of culinary combinations. This necessitates a sophisticated approach to classification and recommendation, ensuring the system accommodates the nature of recipe categorization. The paper seeks not only to recommend recipes but also to explore the process involved in achieving accurate and personalized recommendations.

Direct numerical simulations (DNS) are one of the main ab initio tools to study turbulent flows. However, due to their considerable computational cost, DNS are primarily restricted to canonical flows at moderate Reynolds numbers, in which turbulence is isolated from the realistic, large-scale flow dynamics. In contrast, lower fidelity techniques, such as large eddy simulations (LES), are employed for modelling real-life systems. Such approaches rely on closure models that make multiple assumptions, including turbulent equilibrium, small-scale universality, etc., which require prior knowledge of the flow and can be violated. We propose a method, which couples a lower-fidelity, unresolved, time-dependent calculation of an entire system (LES) with an embedded Small-Eddy Simulation (SES) that provides a high-fidelity, fully resolved solution in a sub-region of interest of the LES. Such coupling is achieved by continuous replacement of the large SES scales with a low-pass filtered LES velocity field. The method is formulated in physical space, makes no assumptions of equilibrium, small-scale structure, and boundary conditions. A priori tests of both steady and unsteady homogeneous, isotropic turbulence are used to demonstrate the method accuracy in recovering turbulence properties, including spectra, probability density functions of the intermittent quantities, and sub-grid dissipation. Finally, SES is compared with two alternative approaches: one embedding a high-resolution region through static mesh refinement and a generalization of the traditional volumetric spectral forcing. Unlike these methods, SES is shown to achieve DNS-level accuracy at a fraction of the cost of the full DNS, thus opening the possibility to study high-Re flows., Comment: 31 pages, 18 figures

The use of multi-threading and file prioritization methods has accelerated the speed at which ransomware encrypts files. To minimize file loss during the ransomware attack, detecting file modifications at the earliest execution stage is considered very important. To achieve this, selecting files as traps and monitoring changes to them is a practical way to deal with modern ransomware variants. This approach minimizes overhead on the endpoint, facilitating early identification of ransomware. This paper evaluates various machine learning-based trap selection methods for reducing file loss, detection delay, and endpoint overhead. We specifically examine non-parametric clustering methods such as Affinity Propagation, Gaussian Mixture Models, Mean Shift, and Optics to assess their effectiveness in trap selection for ransomware detection. These methods select M files from a directory with N files (M

Diffusion Transformers (DiTs) have recently attracted significant interest from both industry and academia due to their enhanced capabilities in visual generation, surpassing the performance of traditional diffusion models that employ U-Net. However, the improved performance of DiTs comes at the expense of higher parameter counts and implementation costs, which significantly limits their deployment on resource-constrained devices like mobile phones. We propose DiTAS, a data-free post-training quantization (PTQ) method for efficient DiT inference. DiTAS relies on the proposed temporal-aggregated smoothing techniques to mitigate the impact of the channel-wise outliers within the input activations, leading to much lower quantization error under extremely low bitwidth. To further enhance the performance of the quantized DiT, we adopt the layer-wise grid search strategy to optimize the smoothing factor. Experimental results demonstrate that our approach enables 4-bit weight, 8-bit activation (W4A8) quantization for DiTs while maintaining comparable performance as the full-precision model.

Adversarial multiplayer games are an important object of study in multiagent learning. In particular, polymatrix zero-sum games are a multiplayer setting where Nash equilibria are known to be efficiently computable. Towards understanding the limits of tractability in polymatrix games, we study the computation of Nash equilibria in such games where each pair of players plays either a zero-sum or a coordination game. We are particularly interested in the setting where players can be grouped into a small number of teams of identical interest. While the three-team version of the problem is known to be PPAD-complete, the complexity for two teams has remained open. Our main contribution is to prove that the two-team version remains hard, namely it is CLS-hard. Furthermore, we show that this lower bound is tight for the setting where one of the teams consists of multiple independent adversaries. On the way to obtaining our main result, we prove hardness of finding any stationary point in the simplest type of non-convex-concave min-max constrained optimization problem, namely for a class of bilinear polynomial objective functions.

Investigating Li$^+$ transport within the amorphous lithium phosphorous oxynitride (LiPON) framework, especially across a Li||LiPON interface, has proven challenging due to its amorphous nature and varying stoichiometry, necessitating large supercells and long timescales for computational models. Notably, machine learned interatomic potentials (MLIPs) can combine the computational speed of classical force fields with the accuracy of density functional theory (DFT), making them the ideal tool for modelling such amorphous materials. Thus, in this work, we train and validate the neural equivariant Interatomic potential (NequIP) framework on a comprehensive DFT-based dataset consisting of 13,454 chemically relevant structures to describe LiPON. With an optimized training (validation) energy and force mean absolute errors of 5.5 (6.1) meV/atom and 13.6 (13.2) meV/{\AA}, respectively, we employ the trained potential in model Li-transport in both bulk LiPON and across a Li||LiPON interface. Amorphous LiPON structures generated by the optimized potential do resemble those generated by ab initio molecular dynamics, with N being incorporated on non-bridging apical and bridging sites. Subsequent analysis of Li$^+$ diffusivity in the bulk LiPON structures indicates broad agreement with computational and experimental literature so far. Further, we investigate the anisotropy in Li$^+$ transport across the Li(110)||LiPON interface, where we observe Li-transport across the interface to be one order-of-magnitude slower than Li-motion within the bulk Li and LiPON phases. Nevertheless, we note that this anisotropy of Li-transport across the interface is minor and do not expect it to cause any significant impedance buildup. Finally, our work highlights the efficiency of MLIPs in enabling high-fidelity modelling of complex non-crystalline systems over large length and time scales.

Power Line Autonomous Inspection (PLAI) plays a crucial role in the construction of smart grids due to its great advantages of low cost, high efficiency, and safe operation. PLAI is completed by accurately detecting the electrical components and defects in the aerial images captured by Unmanned Aerial Vehicles (UAVs). However, the visible quality of aerial images is inevitably degraded by adverse weather like haze, rain, or snow, which are found to drastically decrease the detection accuracy in our research. To circumvent this problem, we propose a new task of Power Line Aerial Image Restoration under Adverse Weather (PLAIR-AW), which aims to recover clean and high-quality images from degraded images with bad weather thus improving detection performance for PLAI. In this context, we are the first to release numerous corresponding datasets, namely, HazeCPLID, HazeTTPLA, HazeInsPLAD for power line aerial image dehazing, RainCPLID, RainTTPLA, RainInsPLAD for power line aerial image deraining, SnowCPLID, SnowInsPLAD for power line aerial image desnowing, which are synthesized upon the public power line aerial image datasets of CPLID, TTPLA, InsPLAD following the mathematical models. Meanwhile, we select numerous state-of-the-art methods from image restoration community as the baseline methods for PLAIR-AW. At last, we conduct large-scale empirical experiments to evaluate the performance of baseline methods on the proposed datasets. The proposed datasets and trained models are available at https://github.com/ntuhubin/PLAIR-AW.

Large Language Models (LLMs) are increasingly integrated into diverse applications. The rapid evolution of LLMs presents opportunities for developers to enhance applications continuously. However, this constant adaptation can also lead to performance regressions during model migrations. While several interactive tools have been proposed to streamline the complexity of prompt engineering, few address the specific requirements of regression testing for LLM Migrations. To bridge this gap, we introduce RETAIN (REgression Testing guided LLM migrAtIoN), a tool designed explicitly for regression testing in LLM Migrations. RETAIN comprises two key components: an interactive interface tailored to regression testing needs during LLM migrations, and an error discovery module that facilitates understanding of differences in model behaviors. The error discovery module generates textual descriptions of various errors or differences between model outputs, providing actionable insights for prompt refinement. Our automatic evaluation and empirical user studies demonstrate that RETAIN, when compared to manual evaluation, enabled participants to identify twice as many errors, facilitated experimentation with 75% more prompts, and achieves 12% higher metric scores in a given time frame., Comment: Preprint

The paper presents a theoretical study on small-signal stability and damping in bulk power systems with multiple grid-forming inverter-based storage resources. A detailed analysis is presented, characterizing the impacts of inverter droop gains and storage size on the slower eigenvalues, particularly those concerning inter-area oscillation modes. From these parametric sensitivity studies, a set of necessary conditions are derived that the design of droop gain must satisfy to enhance damping performance. The analytical findings are structured into propositions highlighting potential design considerations for improving system stability. The findings are illustrated via numerical studies on an IEEE 68-bus grid-forming storage network., Comment: accepted for presentation at The 63rd IEEE Conference on Decision and Control

Speech models have gained traction thanks to increase in accuracy from novel transformer architectures. While this impressive increase in performance across automatic speech recognition (ASR) benchmarks is noteworthy, there is still much that is unknown about the use of attention mechanisms for speech-related tasks. For example, while it is assumed that these models are learning language-independent (i.e., universal) speech representations, there has not yet been an in-depth exploration of what it would mean for the models to be language-independent. In the current paper, we explore this question within the realm of self-attention mechanisms of one small self-supervised speech transformer model (TERA). We find that even with a small model, the attention heads learned are diverse ranging from almost entirely diagonal to almost entirely global regardless of the training language. We highlight some notable differences in attention patterns between Turkish and English and demonstrate that the models do learn important phonological information during pretraining. We also present a head ablation study which shows that models across languages primarily rely on diagonal heads to classify phonemes., Comment: 10 pages, 18 figures

Volunteer Edge-Cloud (VEC) computing has a significant potential to support scientific workflows in user communities contributing volunteer edge nodes. However, managing heterogeneous and intermittent resources to support machine/deep learning (ML/DL) based workflows poses challenges in resource governance for reliability, and confidentiality for model/data privacy protection. There is a need for approaches to handle the volatility of volunteer edge node availability, and also to scale the confidential data-intensive workflow execution across a large number of VEC nodes. In this paper, we present VECA, a reliable and confidential VEC resource clustering solution featuring three-fold methods tailored for executing ML/DL-based scientific workflows on VEC resources. Firstly, a capacity-based clustering approach enhances system reliability and minimizes VEC node search latency. Secondly, a novel two-phase, globally distributed scheduling scheme optimizes job allocation based on node attributes and using time-series-based Recurrent Neural Networks. Lastly, the integration of confidential computing ensures privacy preservation of the scientific workflows, where model and data information are not shared with VEC resources providers. We evaluate VECA in a Function-as-a-Service (FaaS) cloud testbed that features OpenFaaS and MicroK8S to support two ML/DL-based scientific workflows viz., G2P-Deep (bioinformatics) and PAS-ML (health informatics). Results from tested experiments demonstrate that our proposed VECA approach outperforms state-of-the-art methods; especially VECA exhibits a two-fold reduction in VEC node search latency and over 20% improvement in productivity rates following execution failures compared to the next best method., Comment: Accepted - IC2E 2024 Conference

The paper proposes a new architecture for Distributed MIMO (D-MIMO) in which the base station (BS) jointly transmits with wireless mobile nodes to serve users (UEs) within a cell for 6G communication systems. The novelty of the architecture lies in the wireless mobile nodes participating in joint D-MIMO transmission with the BS (referred to as D-MIMO nodes), which are themselves users on the network. The D-MIMO nodes establish wireless connections with the BS, are generally near the BS, and ideally benefit from higher SNR links and better connections with edge-located UEs. These D-MIMO nodes can be existing handset UEs, Unmanned Aerial Vehicles (UAVs), or Vehicular UEs. Since the D-MIMO nodes are users sharing the access channel, the proposed architecture operates in two phases. First, the BS communicates with the D-MIMO nodes to forward data for the joint transmission, and then the BS and D-MIMO nodes jointly serve the UEs through coherent D-MIMO operation. Capacity analysis of this architecture is studied based on realistic 3GPP channel models, and the paper demonstrates that despite the two-phase operation, the proposed architecture enhances the system's capacity compared to the baseline where the BS communicates directly with the UEs.

Passive reflectors mitigate millimeter-wave (mmwave) link blockages by extending coverage to non-line-ofsight (NLoS) regions. However, their deployment often leads to irregular reflected beam patterns and coverage gaps. This results in rapid channel fluctuations and potential outages. In this paper, we propose two LiDAR-aided link enhancement techniques to address these challenges. Leveraging user position information, we introduce a location-dependent link control strategy and a user selection technique to improve NLoS link reliability and coverage. Experimental results validate the efficacy of the proposed techniques in reducing outages and enhancing NLoS signal strength.

In the following work, a new hybrid model of the form $ f(Q)=Q(1+a)+b\frac{Q_0^2}{Q} $ has been proposed and confronted using both early as well as late-time constraints. We first use conditions from the era of Big Bang Nucleosynthesis (BBN) in order to constrain the models which are further used to study the evolution of the Universe through the deceleration parameter. This methodology is employed for the hybrid model as well as a simple model of the form $ \alpha_1 Q+\alpha_2 Q_0 $ which is found to reduce to $\Lambda$CDM. The error bar plot for the Cosmic Chronometer (CC) and Pantheon+SH0ES datasets which includes the comparison with $\Lambda$CDM, has been studied for the constrained hybrid model. Additionally, we perform a Monte Carlo Markov Chain (MCMC) sampling of the model against three datasets -- CC, Pantheon+SH0ES, and Baryon Acoustic Oscillations (BAO) to find the best-fit ranges of the free parameters. It is found that the constraint range of the model parameter ($a$) from the BBN study has a region of overlap with the ranges obtained from the MCMC analysis. Finally, we perform a statistical comparison between our model and the $\Lambda$CDM model using AIC and BIC method., Comment: EPJ C published version

There is a growing interest in designing tools to support interactivity specification and authoring in data visualization. To develop expressive and flexible tools, we need theories and models that describe the task space of interaction authoring. Although multiple taxonomies and frameworks exist for interactive visualization, they primarily focus on how visualizations are used, not how interactivity is composed. To fill this gap, we conduct an analysis of 592 interaction units from 47 real-world visualization applications. Based on the analysis, we present a unified analysis of interaction authoring tasks across three levels of description: intents, representative techniques, and low-level implementation components. We examine our framework's descriptive, evaluative, and generative powers for critiquing existing interactivity authoring tools and informing new tool development.

Deep neural networks are increasingly used as an effective way to represent control policies in a wide-range of learning-based control methods. For continuous-time optimal control problems (OCPs), which are central to many decision-making tasks, control policy learning can be cast as a neural ordinary differential equation (NODE) problem wherein state and control constraints are naturally accommodated. This paper presents a Lyapunov-NODE control (L-NODEC) approach to solving continuous-time OCPs for the case of stabilizing a known constrained nonlinear system around a terminal equilibrium point. We propose a Lyapunov loss formulation that incorporates a control-theoretic Lyapunov condition into the problem of learning a state-feedback neural control policy. We establish that L-NODEC ensures exponential stability of the controlled system, as well as its adversarial robustness to uncertain initial conditions. The performance of L-NODEC is illustrated on a benchmark double integrator problem and for optimal control of thermal dose delivery using a cold atmospheric plasma biomedical system. L-NODEC can substantially reduce the inference time necessary to reach the equilibrium state.

With the ubiquitous use of document corpora for question answering, one important aspect which is especially relevant for technical documents is the ability to extract information from tables which are interspersed with text. The major challenge in this is that unlike free-flow text or isolated set of tables, the representation of a table in terms of what is a relevant chunk is not obvious. We conduct a series of experiments examining various representations of tabular data interspersed with text to understand the relative benefits of different representations. We choose a corpus of $3^{rd}$ Generation Partnership Project (3GPP) documents since they are heavily interspersed with tables. We create expert curated dataset of question answers to evaluate our approach. We conclude that row level representations with corresponding table header information being included in every cell improves the performance of the retrieval, thus leveraging the structural information present in the tabular data., Comment: 10 pages, 4 figures, 2 tables

Salient Object Detection (SOD) has traditionally relied on feature refinement modules that utilize the features of an ImageNet pre-trained backbone. However, this approach limits the possibility of pre-training the entire network because of the distinct nature of SOD and image classification. Additionally, the architecture of these backbones originally built for Image classification is sub-optimal for a dense prediction task like SOD. To address these issues, we propose a novel encoder-decoder-style neural network called SODAWideNet++ that is designed explicitly for SOD. Inspired by the vision transformers ability to attain a global receptive field from the initial stages, we introduce the Attention Guided Long Range Feature Extraction (AGLRFE) module, which combines large dilated convolutions and self-attention. Specifically, we use attention features to guide long-range information extracted by multiple dilated convolutions, thus taking advantage of the inductive biases of a convolution operation and the input dependency brought by self-attention. In contrast to the current paradigm of ImageNet pre-training, we modify 118K annotated images from the COCO semantic segmentation dataset by binarizing the annotations to pre-train the proposed model end-to-end. Further, we supervise the background predictions along with the foreground to push our model to generate accurate saliency predictions. SODAWideNet++ performs competitively on five different datasets while only containing 35% of the trainable parameters compared to the state-of-the-art models. The code and pre-computed saliency maps are provided at https://github.com/VimsLab/SODAWideNetPlusPlus., Comment: Accepted at ICPR 2024

This work demonstrates a fast thermo-optic switching mechanism on silicon nitride on insulator platform leveraging parity-time symmetry breaking. The cladding-free design enables low-loss optical propagation in a partially metal-covered waveguide, with the same metal layer serving as an integrated heater for rapid phase tuning. The fabricated device exhibits an 8.5 {\mu}s rise time for a {\pi} phase shift, despite the weak thermo-optic coefficient in silicon nitride. Additionally, the impact of thermal cross-talk is investigated and an insertion loss as low as 0.39 dB for a 100-{\mu}m-long heater-waveguide section is demonstrated., Comment: 15 pages, 6 figures

Multimodal foundation models (MFMs) such as OFASys show the potential to unlock analysis of complex data such as images, videos, and audio data via text prompts alone. However, their performance may suffer in the face of text input that differs even slightly from their training distribution, which is surprising considering the use of modality-specific data to "ground" the text input. This study demonstrates that prompt instability is a major concern for MFMs, leading to a consistent drop in performance across all modalities, but that instability can be mitigated with additional training with augmented data. We evaluate several methods for grounded prompt perturbation, where we generate perturbations and filter based on similarity to text and/or modality data. After re-training the models on the augmented data, we find improved accuracy and more stable performance on the perturbed test data regardless of perturbation condition, suggesting that the data augmentation strategy helps the models handle domain shifts more effectively. In error analysis, we find consistent patterns of performance improvement across domains, suggesting that retraining on prompt perturbations tends to help general reasoning capabilities in MFMs., Comment: in submission

In recent times a number of platforms are using badge-based achievements or leaderboards to increase user involvement and participation. Due to recent advancements, there is a question of up to what extent virtual achievement systems have on users using particular platforms. Here in this paper, we discuss measuring the impact of the leaderboard-based achievement system by integrating it into an online learning android application UPSC Pre that has thousands of questions and answers categorized topic wise related to UPSC exams, one of the toughest exams to crack in the world. We are conducting the experiment on 10 randomly chosen students who are using the app in a controlled setting and the data measurement is done using the Firebase Analytics tool by Google. We observed that the students using the leaderboard have increased participation without any reductions in their quality and the time of using the platform has increased compared to previous engagements. Students who participated in the experiment felt the leaderboard was competitive and enjoyed gaining positions on the leaderboard and wanted it in the User interface for other platforms as well. The research has an impact in designing the learning applications to cater and improve the user experience in the future. The results are not limited to educational purposes but can be expanded to other fields such as self development applications, other research projects, Gaming industry and many more., Comment: 4 Pages, 4 Figures

Gene therapy is poised to transition from niche to mainstream medicine, with recombinant adeno-associated virus (rAAV) as the vector of choice. However, this requires robust, scalable, industrialized production to meet demand and provide affordable patient access, which has thus far failed to materialize. Closing the chasm between demand and supply requires innovation in biomanufacturing to achieve the essential step change in rAAV product yield and quality. Omics provides a rich source of mechanistic knowledge that can be applied to HEK293, the prevailing cell line for rAAV production. In this review, the findings from a growing number of disparate studies that apply genomics, epigenomics, transcriptomics, proteomics, and metabolomics to HEK293 bioproduction are explored. Learnings from CHO-Omics, application of omics approaches to improve CHO bioproduction, provide context for the potential of "HEK-Omics" as a multiomics-informed approach providing actionable mechanistic insights for improved transient and stable production of rAAV and other recombinant products in HEK293., Comment: 41 pages, 1 figure, 1 table

Physics-Informed Neural Networks (PINNs) have shown continuous and increasing promise in approximating partial differential equations (PDEs), although they remain constrained by the curse of dimensionality. In this paper, we propose a generalized PINN version of the classical variable separable method. To do this, we first show that, using the universal approximation theorem, a multivariate function can be approximated by the outer product of neural networks, whose inputs are separated variables. We leverage tensor decomposition forms to separate the variables in a PINN setting. By employing Canonic Polyadic (CP), Tensor-Train (TT), and Tucker decomposition forms within the PINN framework, we create robust architectures for learning multivariate functions from separate neural networks connected by outer products. Our methodology significantly enhances the performance of PINNs, as evidenced by improved results on complex high-dimensional PDEs, including the 3d Helmholtz and 5d Poisson equations, among others. This research underscores the potential of tensor decomposition-based variably separated PINNs to surpass the state-of-the-art, offering a compelling solution to the dimensionality challenge in PDE approximation., Comment: 15 pages, 6 figures, ICPR-accepted

Speech-driven 3D motion synthesis seeks to create lifelike animations based on human speech, with potential uses in virtual reality, gaming, and the film production. Existing approaches reply solely on speech audio for motion generation, leading to inaccurate and inflexible synthesis results. To mitigate this problem, we introduce a novel text-guided 3D human motion synthesis method, termed \textit{T3M}. Unlike traditional approaches, T3M allows precise control over motion synthesis via textual input, enhancing the degree of diversity and user customization. The experiment results demonstrate that T3M can greatly outperform the state-of-the-art methods in both quantitative metrics and qualitative evaluations. We have publicly released our code at \href{https://github.com/Gloria2tt/T3M.git}{https://github.com/Gloria2tt/T3M.git}, Comment: 10 pages,4figures

Forecasting the behaviour of complex dynamical systems such as interconnected sensor networks characterized by high-dimensional multivariate time series(MTS) is of paramount importance for making informed decisions and planning for the future in a broad spectrum of applications. Graph forecasting networks(GFNs) are well-suited for forecasting MTS data that exhibit spatio-temporal dependencies. However, most prior works of GFN-based methods on MTS forecasting rely on domain-expertise to model the nonlinear dynamics of the system, but neglect the potential to leverage the inherent relational-structural dependencies among time series variables underlying MTS data. On the other hand, contemporary works attempt to infer the relational structure of the complex dependencies between the variables and simultaneously learn the nonlinear dynamics of the interconnected system but neglect the possibility of incorporating domain-specific prior knowledge to improve forecast accuracy. To this end, we propose a hybrid architecture that combines explicit prior knowledge with implicit knowledge of the relational structure within the MTS data. It jointly learns intra-series temporal dependencies and inter-series spatial dependencies by encoding time-conditioned structural spatio-temporal inductive biases to provide more accurate and reliable forecasts. It also models the time-varying uncertainty of the multi-horizon forecasts to support decision-making by providing estimates of prediction uncertainty. The proposed architecture has shown promising results on multiple benchmark datasets and outperforms state-of-the-art forecasting methods by a significant margin. We report and discuss the ablation studies to validate our forecasting architecture., Comment: Paper accepted at ML4IoT Workshop, International Conference on Learning Representations(ICLR) 2023