Search

Construction robotics increasingly relies on natural language processing for task execution, creating a need for robust methods to interpret commands in complex, dynamic environments. While existing research primarily focuses on what tasks robots should perform, less attention has been paid to how these tasks should be executed safely and efficiently. This paper presents a novel probabilistic framework that uses sentiment analysis from natural language commands to dynamically adjust robot navigation policies in construction environments. The framework leverages Building Information Modeling (BIM) data and natural language prompts to create adaptive navigation strategies that account for varying levels of environmental risk and uncertainty. We introduce an object-aware path planning approach that combines exponential potential fields with a grid-based representation of the environment, where the potential fields are dynamically adjusted based on the semantic analysis of user prompts. The framework employs Bayesian inference to consolidate multiple information sources: the static data from BIM, the semantic content of natural language commands, and the implied safety constraints from user prompts. We demonstrate our approach through experiments comparing three scenarios: baseline shortest-path planning, safety-oriented navigation, and risk-aware routing. Results show that our method successfully adapts path planning based on natural language sentiment, achieving a 50\% improvement in minimum distance to obstacles when safety is prioritized, while maintaining reasonable path lengths. Scenarios with contrasting prompts, such as "dangerous" and "safe", demonstrate the framework's ability to modify paths. This approach provides a flexible foundation for integrating human knowledge and safety considerations into construction robot navigation., Comment: Submitted to International Symposium on Automation and Robotics in Construction (ISARC)

Three-dimensional (3D) multi-slab acquisition is a technique frequently employed in high-resolution diffusion-weighted MRI in order to achieve the best signal-to-noise ratio (SNR) efficiency. However, this technique is limited by slab boundary artifacts that cause intensity fluctuations and aliasing between slabs which reduces the accuracy of anatomical imaging. Addressing this issue is crucial for advancing diffusion MRI quality and making high-resolution imaging more feasible for clinical and research applications. In this work, we propose a regularized slab profile encoding (PEN) method within a Plug-and-Play ADMM framework, incorporating multi-scale energy (MuSE) regularization to effectively improve the slab combined reconstruction. Experimental results demonstrate that the proposed method significantly improves image quality compared to non-regularized and TV-regularized PEN approaches. The regularized PEN framework provides a more robust and efficient solution for high-resolution 3D diffusion MRI, potentially enabling clearer, more reliable anatomical imaging across various applications., Comment: 4 pages, 4 figures, ISBI2025 Conference paper

Methods from machine learning (ML) have transformed the implementation of Perception-Cognition-Communication-Action loops in Cyber-Physical Systems (CPS) and the Internet of Things (IoT), replacing mechanistic and basic statistical models with those derived from data. However, the first generation of ML approaches, which depend on supervised learning with annotated data to create task-specific models, faces significant limitations in scaling to the diverse sensor modalities, deployment configurations, application tasks, and operating dynamics characterizing real-world CPS-IoT systems. The success of task-agnostic foundation models (FMs), including multimodal large language models (LLMs), in addressing similar challenges across natural language, computer vision, and human speech has generated considerable enthusiasm for and exploration of FMs and LLMs as flexible building blocks in CPS-IoT analytics pipelines, promising to reduce the need for costly task-specific engineering. Nonetheless, a significant gap persists between the current capabilities of FMs and LLMs in the CPS-IoT domain and the requirements they must meet to be viable for CPS-IoT applications. In this paper, we analyze and characterize this gap through a thorough examination of the state of the art and our research, which extends beyond it in various dimensions. Based on the results of our analysis and research, we identify essential desiderata that CPS-IoT domain-specific FMs and LLMs must satisfy to bridge this gap. We also propose actions by CPS-IoT researchers to collaborate in developing key community resources necessary for establishing FMs and LLMs as foundational tools for the next generation of CPS-IoT systems.

Designing culturally relevant questionnaires for ICTD research is challenging, particularly when adapting surveys for populations to non-western contexts. Prior work adapted questionnaires through expert reviews and pilot studies, which are resource-intensive and time-consuming. To address these challenges, we propose using large language models (LLMs) to automate the questionnaire pretesting process in cross-cultural settings. Our study used LLMs to adapt a U.S.-focused climate opinion survey for a South African audience. We then tested the adapted questionnaire with 116 South African participants via Prolific, asking them to provide feedback on both versions. Participants perceived the LLM-adapted questions as slightly more favorable than the traditional version. Our note opens discussions on the potential role of LLMs in adapting surveys and facilitating cross-cultural questionnaire design., Comment: Accepted to ICTD 2024 (Notes)

Pronoun translation is a longstanding challenge in neural machine translation (NMT), often requiring inter-sentential context to ensure linguistic accuracy. To address this, we introduce ProNMT, a novel framework designed to enhance pronoun and overall translation quality in context-aware machine translation systems. ProNMT leverages Quality Estimation (QE) models and a unique Pronoun Generation Likelihood-Based Feedback mechanism to iteratively fine-tune pre-trained NMT models without relying on extensive human annotations. The framework combines QE scores with pronoun-specific rewards to guide training, ensuring improved handling of linguistic nuances. Extensive experiments demonstrate significant gains in pronoun translation accuracy and general translation quality across multiple metrics. ProNMT offers an efficient, scalable, and context-aware approach to improving NMT systems, particularly in translating context-dependent elements like pronouns.

A mass-conserving contact line treatment for second-order conservative phase field methods is presented and applied to the conservative diffuse interface (CDI) model. The treatment centers on a no-flux boundary condition for the phase field along with a slip boundary condition for the velocity that is based on the generalized Navier boundary condition (GNBC). Since the CDI model is a second-order partial differential equation, it does not permit a second (contact angle) boundary condition, in contrast to the popular fourth-order Cahn-Hilliard model. As such, we use one-sided stencils and extrapolations from the interior of the domain to compute phase-field-related quantities on and near the wall. Additionally, we propose novel modifications to the GNBC on the continuous and discrete levels that reduce spurious slip velocity when the contact angle achieves its equilibrium value. The proposed treatment is validated with the equilibrium drop and two-phase Couette flow test cases.

This paper introduces a novel mobile sensing application - life journaling - designed to generate semantic descriptions of users' daily lives. We present AutoLife, an automatic life journaling system based on commercial smartphones. AutoLife only inputs low-cost sensor data (without photos or audio) from smartphones and can automatically generate comprehensive life journals for users. To achieve this, we first derive time, motion, and location contexts from multimodal sensor data, and harness the zero-shot capabilities of Large Language Models (LLMs), enriched with commonsense knowledge about human lives, to interpret diverse contexts and generate life journals. To manage the task complexity and long sensing duration, a multilayer framework is proposed, which decomposes tasks and seamlessly integrates LLMs with other techniques for life journaling. This study establishes a real-life dataset as a benchmark and extensive experiment results demonstrate that AutoLife produces accurate and reliable life journals., Comment: 13 pages

Conversational Swarm Intelligence (CSI) is an AI-facilitated method for enabling real-time conversational deliberations and prioritizations among networked human groups of potentially unlimited size. Based on the biological principle of Swarm Intelligence and modelled on the decision-making dynamics of fish schools, CSI has been shown in prior studies to amplify group intelligence, increase group participation, and facilitate productive collaboration among hundreds of participants at once. It works by dividing a large population into a set of small subgroups that are woven together by real-time AI agents called Conversational Surrogates. The present study focuses on the use of a CSI platform called Thinkscape to enable real-time brainstorming and prioritization among groups of 75 networked users. The study employed a variant of a common brainstorming intervention called an Alternative Use Task (AUT) and was designed to compare through subjective feedback, the experience of participants brainstorming using a CSI structure vs brainstorming in a single large chat room. This comparison revealed that participants significantly preferred brainstorming with the CSI structure and reported that it felt (i) more collaborative, (ii) more productive, and (iii) was better at surfacing quality answers. In addition, participants using the CSI structure reported (iv) feeling more ownership and more buy-in in the final answers the group converged on and (v) reported feeling more heard as compared to brainstorming in a traditional text chat environment. Overall, the results suggest that CSI is a very promising AI-facilitated method for brainstorming and prioritization among large-scale, networked human groups.

Two-dimensional (2D) Janus materials hold a great importance in spintronic and valleytronic applications due to their unique lattice structures and emergent properties. They intrinsically exhibit both an in-plane inversion and out-of-plane mirror symmetry breakings, which offer a new degree of freedom to electrons in the material. One of the main limitations in the multifunctional applications of these materials is, however, that, they are usually non-magnetic in nature. Here, using first-principles calculations, we propose to induce magnetic degree of freedom in non-magnetic WSTe via doping with transition metal (TM) elements -- Fe, Mn and Co. Further, we comprehensively probe the electronic, spintronic and valleytronic properties in these systems. Our simulations predict intrinsic Rashba and Zeeman-type spin splitting in pristine WSTe. The obtained Rashba parameter is $\sim$ 422 meV\AA\; along the $\Gamma - K$ direction. Our study shows a strong dependence on uniaxial and biaxial strains where we observe an enhancement of $\sim$ 2.1\% with 3\% biaxial compressive strain. The electronic structure of TM-substituted WSTe reveals half-metallic nature for 6.25 and 18.75\% of Fe, 25\% of Mn, and 18.75 and 25\% of Co structures, which leads to 100\% spin polarization. The obtained values of valley polarization 65, 54.4 and 46.3 meV for 6.25\% of Fe, Mn and Co, respectively, are consistent with the literature data for other Janus materials. Further, our calculations show a strain dependent tunability of valley polarization, where we find an increasing (decreasing) trend with uniaxial and biaxial tensile (compressive) strains. We observed a maximum enhancement of $\sim$ 1.72\% for 6.25\% of Fe on application of 3\% biaxial tensile strain., Comment: 13 figure, 3 tables

Despite the rising prevalence of deep neural networks (DNNs) in cyber-physical systems, their vulnerability to adversarial bit-flip attacks (BFAs) is a noteworthy concern. This paper proposes B3FA, a semi-black-box BFA-based parameter attack on DNNs, assuming the adversary has limited knowledge about the model. We consider practical scenarios often feature a more restricted threat model for real-world systems, contrasting with the typical BFA models that presuppose the adversary's full access to a network's inputs and parameters. The introduced bit-flip approach utilizes a magnitude-based ranking method and a statistical re-construction technique to identify the vulnerable bits. We demonstrate the effectiveness of B3FA on several DNN models in a semi-black-box setting. For example, B3FA could drop the accuracy of a MobileNetV2 from 69.84% to 9% with only 20 bit-flips in a real-world setting.

Distinguishing between swarming and swimming, the two principal forms of bacterial movement, holds significant conceptual and clinical relevance. This is because bacteria that exhibit swarming capabilities often possess unique properties crucial to the pathogenesis of infectious diseases and may also have therapeutic potential. Here, we report a deep learning-based swarming classifier that rapidly and autonomously predicts swarming probability using a single blurry image. Compared with traditional video-based, manually-processed approaches, our method is particularly suited for high-throughput environments and provides objective, quantitative assessments of swarming probability. The swarming classifier demonstrated in our work was trained on Enterobacter sp. SM3 and showed good performance when blindly tested on new swarming (positive) and swimming (negative) test images of SM3, achieving a sensitivity of 97.44% and a specificity of 100%. Furthermore, this classifier demonstrated robust external generalization capabilities when applied to unseen bacterial species, such as Serratia marcescens DB10 and Citrobacter koseri H6. It blindly achieved a sensitivity of 97.92% and a specificity of 96.77% for DB10, and a sensitivity of 100% and a specificity of 97.22% for H6. This competitive performance indicates the potential to adapt our approach for diagnostic applications through portable devices or even smartphones. This adaptation would facilitate rapid, objective, on-site screening for bacterial swarming motility, potentially enhancing the early detection and treatment assessment of various diseases, including inflammatory bowel diseases (IBD) and urinary tract infections (UTI)., Comment: 17 Pages, 4 Figures

A general approach for transforming phase field equations into generalized curvilinear coordinates is proposed in this work. The proposed transformation can be applied to isotropic, non-isotropic, and curvilinear grids without adding any ambiguity in determining the phase field parameters. Moreover, it accurately adapts the interface thickness to the local grid-size for a general curvilinear grid without creating oscillations. Three canonical verification tests are presented on four grids with varying skewness levels. The classic advection and drop in shear tests are extended to curvilinear grids and show that the original phase field on Cartesian grids and the proposed curvilinear form have an identical order of convergence. Additionally, the proposed method is shown to provide grid-independent convergence on a two-way coupled compressible Rayleigh-Taylor instability. These simulations illustrate the robustness and accuracy of the proposed method for handling complex interfacial structures on generalized curvilinear grids.

Spin relaxation of electrons in materials involve both reversible dephasing and irreversible decoherence processes. Their interplay leads to a complex dependence of spin relaxation times on the direction and magnitude of magnetic fields, relevant for spintronics and quantum information applications. Here, we use real-time first-principles density matrix dynamics simulations to directly simulate Hahn echo measurements, disentangle dephasing from decoherence, and predict T1, T2 and T2* spin lifetimes. We show that g-factor fluctuations lead to non-trivial magnetic field dependence of each of these lifetimes in inversion-symmetric crystals of CsPbBr3 and silicon, even when only intrinsic spin-phonon scattering is present. Most importantly, fluctuations in the off-diagonal components of the g-tensor lead to a strong magnetic field dependence of even the T1 lifetime in silicon. Our calculations elucidate the detailed role of anisotropic g-factors in determining the spin dynamics even in simple, low spin-orbit coupling materials such as silicon.

The newly introduced Visual State Space Model (VMamba), which employs \textit{State Space Mechanisms} (SSM) to interpret images as sequences of patches, has shown exceptional performance compared to Vision Transformers (ViT) across various computer vision tasks. However, recent studies have highlighted that deep models are susceptible to adversarial attacks. One common approach is to embed a trigger in the training data to retrain the model, causing it to misclassify data samples into a target class, a phenomenon known as a backdoor attack. In this paper, we first evaluate the robustness of the VMamba model against existing backdoor attacks. Based on this evaluation, we introduce a novel architectural backdoor attack, termed BadScan, designed to deceive the VMamba model. This attack utilizes bit plane slicing to create visually imperceptible backdoored images. During testing, if a trigger is detected by performing XOR operations between the $k^{th}$ bit planes of the modified triggered patches, the traditional 2D selective scan (SS2D) mechanism in the visual state space (VSS) block of VMamba is replaced with our newly designed BadScan block, which incorporates four newly developed scanning patterns. We demonstrate that the BadScan backdoor attack represents a significant threat to visual state space models and remains effective even after complete retraining from scratch. Experimental results on two widely used image classification datasets, CIFAR-10, and ImageNet-1K, reveal that while visual state space models generally exhibit robustness against current backdoor attacks, the BadScan attack is particularly effective, achieving a higher Triggered Accuracy Ratio (TAR) in misleading the VMamba model and its variants.

Construction robots have gained significant traction in recent years in research and development. However, the application of industrial robots has unique challenges. Dynamic environments, domain-specific tasks, and complex localization and mapping are significant obstacles in their development. In construction job sites, moving objects and complex machinery can make pathfinding a difficult task due to the possibility of object collisions. Existing methods such as simultaneous localization and mapping are viable solutions to this problem, however, due to the precision and data quality required by the sensors and the processing of the information, they can be very computationally expensive. We propose using spatial and semantic information in building information modeling (BIM) to develop domain-specific pathfinding strategies. In this work, we integrate a multi-heuristic A* (MHA*) algorithm using APFs from the BIM spatial information and process textual information from the BIM using large language models (LLMs) to adjust the algorithm for dynamic object avoidance. We show increased robot object proximity by 80% while maintaining similar path lengths., Comment: Submitted to IEEE Access

Effective communication is essential in collaborative tasks, so AI-equipped robots working alongside humans need to be able to explain their behaviour in order to cooperate effectively and earn trust. We analyse and classify communications among human participants collaborating to complete a simulated emergency response task. The analysis identifies messages that relate to various kinds of interactive explanations identified in the explainable AI literature. This allows us to understand what type of explanations humans expect from their teammates in such settings, and thus where AI-equipped robots most need explanation capabilities. We find that most explanation-related messages seek clarification in the decisions or actions taken. We also confirm that messages have an impact on the performance of our simulated task., Comment: 4 pages, 3 figures, published as a Late Breaking Report in RO-MAN 2024

Multimodal sensing systems are increasingly prevalent in various real-world applications. Most existing multimodal learning approaches heavily rely on training with a large amount of complete multimodal data. However, such a setting is impractical in real-world IoT sensing applications where data is typically collected by distributed nodes with heterogeneous data modalities, and is also rarely labeled. In this paper, we propose MMBind, a new framework for multimodal learning on distributed and heterogeneous IoT data. The key idea of MMBind is to construct a pseudo-paired multimodal dataset for model training by binding data from disparate sources and incomplete modalities through a sufficiently descriptive shared modality. We demonstrate that data of different modalities observing similar events, even captured at different times and locations, can be effectively used for multimodal training. Moreover, we propose an adaptive multimodal learning architecture capable of training models with heterogeneous modality combinations, coupled with a weighted contrastive learning approach to handle domain shifts among disparate data. Evaluations on ten real-world multimodal datasets highlight that MMBind outperforms state-of-the-art baselines under varying data incompleteness and domain shift, and holds promise for advancing multimodal foundation model training in IoT applications.

Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pretraining on publicly available biomedical corpora. These works typically claim that such domain-adaptive pretraining (DAPT) improves performance on downstream medical tasks, such as answering medical licensing exam questions. In this paper, we compare ten public "medical" LLMs and two VLMs against their corresponding base models, arriving at a different conclusion: all medical VLMs and nearly all medical LLMs fail to consistently improve over their base models in the zero-/few-shot prompting and supervised fine-tuning regimes for medical question-answering (QA). For instance, across all tasks and model pairs we consider in the 3-shot setting, medical LLMs only outperform their base models in 22.7% of cases, reach a (statistical) tie in 36.8% of cases, and are significantly worse than their base models in the remaining 40.5% of cases. Our conclusions are based on (i) comparing each medical model head-to-head, directly against the corresponding base model; (ii) optimizing the prompts for each model separately in zero-/few-shot prompting; and (iii) accounting for statistical uncertainty in comparisons. While these basic practices are not consistently adopted in the literature, our ablations show that they substantially impact conclusions. Meanwhile, we find that after fine-tuning on specific QA tasks, medical LLMs can show performance improvements, but the benefits do not carry over to tasks based on clinical notes. Our findings suggest that state-of-the-art general-domain models may already exhibit strong medical knowledge and reasoning capabilities, and offer recommendations to strengthen the conclusions of future studies., Comment: Extended version of EMNLP 2024 paper arXiv:2411.04118. Includes additional results on clinical note QA tasks and supervised fine-tuning evaluations

With the increasing focus on flexible automation, which emphasizes systems capable of adapting to varied tasks and conditions, exploring future deployments of cloud and edge-based network infrastructures in robotic systems becomes crucial. This work, examines how wireless solutions could support the shift from rigid, wired setups toward more adaptive, flexible automation in industrial environments. We provide a quality of control (QoC) based abstraction for robotic workloads, parameterized on loop latency and reliability, and jointly optimize system performance. The setup involves collaborative robots working on distributed tasks, underscoring how wireless communication can enable more dynamic coordination in flexible automation systems. We use our abstraction to optimally maximize the QoC ensuring efficient operation even under varying network conditions. Additionally, our solution allocates the communication resources in time slots, optimizing the balance between communication and control costs. Our simulation results highlight that minimizing the delay in the system may not always ensure the best QoC but can lead to substantial gains in QoC if delays are sometimes relaxed, allowing more packets to be delivered reliably., Comment: Accepted in IEEE CCNC 2025

In a seminal paper, Weitz showed that for two-state spin systems, such as the Ising and hardcore models from statistical physics, correlation decay on trees implies correlation decay on arbitrary graphs. The key gadget in Weitz's reduction has been instrumental in recent advances in approximate counting and sampling, from analysis of local Markov chains like Glauber dynamics to the design of deterministic algorithms for estimating the partition function. A longstanding open problem in the field has been to find such a reduction for more general multispin systems like the uniform distribution over proper colorings of a graph. In this paper, we show that for a rich class of multispin systems, including the ferromagnetic Potts model, there are fundamental obstacles to extending Weitz's reduction to the multispin setting. A central component of our investigation is establishing nonconvexity of the image of the belief propagation functional, the standard tool for analyzing spin systems on trees. On the other hand, we provide evidence of convexity for the antiferromagnetic Potts model.

Fiber Specklegram Sensors (FSS) are vital for environmental monitoring due to their high temperature sensitivity, but their complex data poses challenges for predictive models. This study introduces Prion-ViT, a prion-inspired Vision Transformer model, inspired by biological prion memory mechanisms, to improve long-term dependency modeling and temperature prediction accuracy using FSS data. Prion-ViT leverages a persistent memory state to retain and propagate key features across layers, reducing mean absolute error (MAE) to 0.71$^\circ$C and outperforming models like ResNet, Inception Net V2, and Standard Vision Transformers. This paper also discusses Explainable AI (XAI) techniques, providing a perspective on specklegrams through attention and saliency maps, which highlight key regions contributing to predictions

We investigate the use of sequence analysis for behavior modeling, emphasizing that sequential context often outweighs the value of aggregate features in understanding human behavior. We discuss framing common problems in fields like healthcare, finance, and e-commerce as sequence modeling tasks, and address challenges related to constructing coherent sequences from fragmented data and disentangling complex behavior patterns. We present a framework for sequence modeling using Ensembles of Hidden Markov Models, which are lightweight, interpretable, and efficient. Our ensemble-based scoring method enables robust comparison across sequences of different lengths and enhances performance in scenarios with imbalanced or scarce data. The framework scales in real-world scenarios, is compatible with downstream feature-based modeling, and is applicable in both supervised and unsupervised learning settings. We demonstrate the effectiveness of our method with results on a longitudinal human behavior dataset.

The integration of the Internet of Things (IoT) and modern Artificial Intelligence (AI) has given rise to a new paradigm known as the Artificial Intelligence of Things (AIoT). In this survey, we provide a systematic and comprehensive review of AIoT research. We examine AIoT literature related to sensing, computing, and networking & communication, which form the three key components of AIoT. In addition to advancements in these areas, we review domain-specific AIoT systems that are designed for various important application domains. We have also created an accompanying GitHub repository, where we compile the papers included in this survey: https://github.com/AIoT-MLSys-Lab/AIoT-Survey. This repository will be actively maintained and updated with new research as it becomes available. As both IoT and AI become increasingly critical to our society, we believe AIoT is emerging as an essential research field at the intersection of IoT and modern AI. We hope this survey will serve as a valuable resource for those engaged in AIoT research and act as a catalyst for future explorations to bridge gaps and drive advancements in this exciting field., Comment: Accepted in ACM Transactions on Sensor Networks (TOSN)

Superhydrophobic surfaces (SHS) are textured hydrophobic surfaces which have the ability to trap air pockets when immersed in water. This can result in significant drag reduction, due to substantially lower viscosity of air resulting in substantial effective slip velocity at the interface. Past studies of both laminar and turbulent flows model this slip velocity in terms of a homogenized Navier slip boundary condition with a slip length relating the wall slip velocity to the wall-normal velocity gradient. In this work, we seek to understand the effects of superhydrophobic surfaces in the context of mean scalar and momentum mixing. We use the macroscopic forcing method (Mani and Park, 2021) to compute the generalized eddy viscosity and slip length operators of a turbulent channel over SHS, implemented as both a pattern-resolved boundary condition and homogenized slip length boundary condition, for several pattern sizes and geometries. We present key differences in the mixing behavior of both boundary conditions through quantification of their near-wall eddy viscosity. Analysis of transport in turbulent flow over pattern-resolved surfaces reveals substantial nonlocality in the measured homogenized slip length for both scalar and momentum mixing when the Reynolds and Peclet numbers based on pattern size are finite. We present several metrics to quantify this nonlocality and observe possible trends relating to Reynolds number, texture size, and pattern geometry. The importance of nonlocality in the slip length operator and in the eddy diffusivity operator is demonstrated by examining the impact on Reynolds-averaged solutions for the mean scalar and velocity fields.

We study the number of monochromatic solutions to linear equations in a $2$-coloring of $\{1,\ldots,n\}$. We show that any nontrivial linear equation has a constant fraction of solutions that are monochromatic in any $2$-coloring of $\{1,\ldots,n\}$. We further study commonness of four-term equations and disprove a conjecture of Costello and Elvin by showing that, unlike over $\mathbb{F}_p$, the four-term equation $x_1 + 2x_2 - x_3 - 2x_4 = 0$ is uncommon over $\{1,\ldots,n\}$., Comment: 12 pages

A myriad of factors affect large scale ads delivery systems and influence both user experience and revenue. One such factor is proactive detection and calibration of seasonal advertisements to help with increasing conversion and user satisfaction. In this paper, we present Proactive Detection and Calibration of Seasonal Advertisements (PDCaSA), a research problem that is of interest for the ads ranking and recommendation community, both in the industrial setting as well as in research. Our paper provides detailed guidelines from various angles of this problem tested in, and motivated by a large-scale industrial ads ranking system. We share our findings including the clear statement of the problem and its motivation rooted in real-world systems, evaluation metrics, and sheds lights to the existing challenges, lessons learned, and best practices of data annotation and machine learning modeling to tackle this problem. Lastly, we present a conclusive solution we took during this research exploration: to detect seasonality, we leveraged Multimodal LLMs (MLMs) which on our in-house benchmark achieved 0.97 top F1 score. Based on our findings, we envision MLMs as a teacher for knowledge distillation, a machine labeler, and a part of the ensembled and tiered seasonality detection system, which can empower ads ranking systems with enriched seasonal information.

This project proposes the development of a comprehensive real-time biodiversity monitoring system that harnesses sound data through a network of acoustic sensors and advanced artificial intelligence algorithms. The system analyzes sound recordings from various ecosystems to identify and classify different species, providing valuable insights into ecosystem health and biodiversity patterns while facilitating the detection of subtle changes in species presence and behavior over time. By addressing critical challenges such as noise pollution and species overlap, the system employs sophisticated filtering and classification techniques to ensure accurate and reliable monitoring, distinguishing between natural sounds and anthropogenic noise. Ultimately, this initiative aims to enhance our understanding of biodiversity dynamics and provide essential information to support effective conservation strategies and inform policy decisions, empowering stakeholders with actionable insights to protect and preserve vital ecosystems.

The concepts of precision, and accuracy are domain and problem dependent. The simplified numeric hard and soft measures used in the fields of statistical learning, many types of machine learning, and binary or multiclass classification problems are known to be of limited use for understanding the meaningfulness of models or their relevance. Arguably, they are neither of patterns nor proofs. Further, there are no good measures or representations for analogous concepts in the cognition domain. In this research, the key issues are reflected upon, and a compositional knowledge representation approach in a minimalist general rough framework is proposed for the problem contexts. The latter is general enough to cover most application contexts, and may be applicable in the light of improved computational tools available., Comment: 16 Pages

Effective processing, interpretation, and management of sensor data have emerged as a critical component of cyber-physical systems. Traditionally, processing sensor data requires profound theoretical knowledge and proficiency in signal-processing tools. However, recent works show that Large Language Models (LLMs) have promising capabilities in processing sensory data, suggesting their potential as copilots for developing sensing systems. To explore this potential, we construct a comprehensive benchmark, SensorBench, to establish a quantifiable objective. The benchmark incorporates diverse real-world sensor datasets for various tasks. The results show that while LLMs exhibit considerable proficiency in simpler tasks, they face inherent challenges in processing compositional tasks with parameter selections compared to engineering experts. Additionally, we investigate four prompting strategies for sensor processing and show that self-verification can outperform all other baselines in 48% of tasks. Our study provides a comprehensive benchmark and prompting analysis for future developments, paving the way toward an LLM-based sensor processing copilot.

The advancement in deep implicit modeling and articulated models has significantly enhanced the process of digitizing human figures in 3D from just a single image. While state-of-the-art methods have greatly improved geometric precision, the challenge of accurately inferring texture remains, particularly in obscured areas such as the back of a person in frontal-view images. This limitation in texture prediction largely stems from the scarcity of large-scale and diverse 3D datasets, whereas their 2D counterparts are abundant and easily accessible. To address this issue, our paper proposes leveraging extensive 2D fashion datasets to enhance both texture and shape prediction in 3D human digitization. We incorporate 2D priors from the fashion dataset to learn the occluded back view, refined with our proposed domain alignment strategy. We then fuse this information with the input image to obtain a fully textured mesh of the given person. Through extensive experimentation on standard 3D human benchmarks, we demonstrate the superior performance of our approach in terms of both texture and geometry. Code and dataset is available at https://github.com/humansensinglab/FAMOUS.

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

We introduce Cadenza, a new multi-stage generative framework for predicting expressive variations of symbolic musical ideas as well as unconditional generations. To accomplish this we propose a novel MIDI encoding method, PerTok (Performance Tokenizer) that captures minute expressive details whilst reducing sequence length up to 59% and vocabulary size up to 95% for polyphonic, monophonic and rhythmic tasks. The proposed framework comprises of two sequential stages: 1) Composer and 2) Performer. The Composer model is a transformer-based Variational Autoencoder (VAE), with Rotary Positional Embeddings (RoPE)ROPE and an autoregressive decoder modified to more effectively integrate the latent codes of the input musical idea. The Performer model is a bidirectional transformer encoder that is separately trained to predict velocities and microtimings on MIDI sequences. Objective and human evaluations demonstrate Cadenza's versatile capability in 1) matching other unconditional state-of-the-art symbolic models in musical quality whilst sounding more expressive, and 2) composing new, expressive ideas that are both stylistically related to the input whilst providing novel ideas to the user. Our framework is designed, researched and implemented with the objective of ethically providing inspiration for musicians.

The ZrSiS-class of layered materials offer interesting topological and magnetic characteristics suitable for spintronics applications. In this work, we have synthesized a polycrystalline NdBiTe using solid-state reaction technique and have examined the magnetic properties in 2 - 300 K temperature range using temperature and field-dependent magnetization measurements. Our magnetic and specific heat data demonstrates a long-range antiferromagnetic ordering in the material below 4.5 K. Furthermore, our isothermal magnetization data show a signature of spin-reorientation below Neel temperature. The observed nonlinearity in inverse susceptibility vs temperature data, and a hump in specific heat in 5-20 K range, indicate the existence of crystal field splitting in the material. Our transport properties measurements show the metallic behavior with positive magnetoresistance in the temperature range of 2 - 300 K. The observed rise in resistivity as function of temperature below Neel temperature infers the strongly correlated fermions, which is consistent with the observed large Sommerfeld coefficient. Consistent with experimental results, our first-principles calculations predict an antiferromagnetic semimetallic nature of NdBiTe. Further, our spin-orbit coupled simulations of electronic structure show a signature of weak topological nature of the material., Comment: 17 pages, 10 Figures

Clouds in satellite images are a deterrent to qualitative and quantitative study. Time compositing methods compare a series of co-registered images and retrieve only those pixels that have comparatively lesser cloud cover for the resultant image. Two different approaches of time compositing were tested. The first method recoded the clouds to value 0 on all the constituent images and ran a 'max' function. The second method directly ran a 'min' function without recoding on all the images for the resultant image. The 'max' function gave a highly mottled image while the 'min' function gave a superior quality image with smoother texture. Persistent clouds on all constituent images were retained in both methods, but they were readily identifiable and easily extractable in the 'max' function image as they were recoded to 0, while that in the 'min' function appeared with varying DN values. Hence a hybrid technique was created which recodes the clouds to value 255 and runs a 'min' function. This method preserved the quality of the 'min' function and the advantage of retrieving clouds as in the 'max' function image. The models were created using Erdas Imagine Modeler 9.1 and MODIS 250 m resolution images of coastal Karnataka in the months of May, June 2008 were used. A detailed investigation on the different methods is described and scope for automating different techniques is discussed., Comment: 10 pages, 8 figures

We analyze the staggered entry of rideshare services across U.S. metropolitan areas, estimating its effect on the spatial redistribution and real outcomes of residents. Ridesharing services gentrify urban areas-especially those with ex-ante lower housing values-causing housing prices to rise 9 percent, with the in-migration of rich-younger individuals more than offsetting the out-migration of incumbent residents and reduced in-migration of poorer individuals. Impact on incumbent residents is conditional on ex-ante homeownership. For homeowners, there is no displacement and a decline in delinquency rates. For non-homeowners, displacement and delinquency rates rise 11 percent and 42 percent, respectively. Our study emphasizes how the private provision of high-end transportation technologies can increase urbanization and exacerbate inequality.

Target selection is crucial in pharmaceutical drug discovery, directly influencing clinical trial success. Despite its importance, drug development remains resource-intensive, often taking over a decade with significant financial costs. High failure rates highlight the need for better early-stage target selection. We present GATher, a graph attention network designed to predict therapeutic gene-disease links by integrating data from diverse biomedical sources into a graph with over 4.4 million edges. GATher incorporates GATv3, a novel graph attention convolution layer, and GATv3HeteroConv, which aggregates transformations for each edge type, enhancing its ability to manage complex interactions within this extensive dataset. Utilizing hard negative sampling and multi-task pre-training, GATher addresses topological imbalances and improves specificity. Trained on data up to 2018 and evaluated through 2024, our results show GATher predicts clinical trial outcomes with a ROC AUC of 0.69 for unmet efficacy failures and 0.79 for positive efficacy. Feature attribution methods, using Captum, highlight key nodes and relationships, enhancing model interpretability. By 2024, GATher improved precision in prioritizing the top 200 clinical trial targets to 14.1%, an absolute increase of over 3.5% compared to other methods. GATher outperforms existing models like GAT, GATv2, and HGT in predicting clinical trial outcomes, demonstrating its potential in enhancing target validation and predicting clinical efficacy and safety.

Understanding the electrical conductivity of warm dense hydrogen is critical for both fundamental physics and applications in planetary science and inertial confinement fusion. We demonstrate how to calculate the electrical conductivity using the continuum form of Ohm's law, with the current density obtained from real-time time-dependent density functional theory. This approach simulates the dynamic response of hydrogen under warm dense matter conditions, with temperatures around 30,000 K and mass densities ranging from 0.02 to 0.98 g/cc. We systematically address finite-size errors in real-time time-dependent density functional theory, demonstrating that our calculations are both numerically feasible and reliable. Our results show good agreement with other approaches, highlighting the effectiveness of this method for modeling electronic transport properties from ambient to extreme conditions., Comment: 9 pages, 6 figures

Conversational Swarm Intelligence (CSI) is an AI-powered communication and collaboration technology that allows large, networked groups (of potentially unlimited size) to hold thoughtful conversational deliberations in real-time. Inspired by the efficient decision-making dynamics of fish schools, CSI divides a human population into a set of small subgroups connected by AI agents. This enables the full group to hold a unified conversation. In this study, groups of 25 participants were tasked with selecting a roster of players in a real Fantasy Baseball contest. A total of 10 trials were run using CSI. In half the trials, each subgroup was augmented with a fact-providing AI agent referred to herein as an Infobot. The Infobot was loaded with a wide range of MLB statistics. The human participants could query the Infobot the same way they would query other persons in their subgroup. Results show that when using CSI, the 25-person groups outperformed 72% of individually surveyed participants and showed significant intelligence amplification versus the mean score (p=0.016). The CSI-enabled groups also significantly outperformed the most popular picks across the collected surveys for each daily contest (p<0.001). The CSI sessions that used Infobots scored slightly higher than those that did not, but it was not statistically significant in this study. That said, 85% of participants agreed with the statement 'Our decisions were stronger because of information provided by the Infobot' and only 4% disagreed. In addition, deliberations that used Infobots showed significantly less variance (p=0.039) in conversational content across members. This suggests that Infobots promoted more balanced discussions in which fewer members dominated the dialog. This may be because the infobot enabled participants to confidently express opinions with the support of factual data

Human Activity Recognition (HAR) is a pivotal component of robot perception for physical Human Robot Interaction (pHRI) tasks. In construction robotics, it is vital that robots have an accurate and robust perception of worker activities. This enhanced perception is the foundation of trustworthy and safe Human-Robot Collaboration (HRC) in an industrial setting. Many developed HAR algorithms lack the robustness and adaptability to ensure seamless HRC. Recent works have employed multi-modal approaches to increase feature considerations. This paper further expands previous research to include 4D building information modeling (BIM) schedule data. We created a pipeline that transforms high-level BIM schedule activities into a set of low-level tasks in real-time. The framework then utilizes this subset as a tool to restrict the solution space that the HAR algorithm can predict activities from. By limiting this subspace through 4D BIM schedule data, the algorithm has a higher chance of predicting the true possible activities from a smaller pool of possibilities in a localized setting as compared to calculating all global possibilities at every point. Results indicate that the proposed approach achieves higher confidence predictions over the base model without leveraging the BIM data., Comment: International Conference on Computing in Civil Engineering 2024

We identify delta Scuti pulsators amongst members of the recently-discovered Cep--Her Complex using light curves from the Transiting Exoplanet Survey Satellite (TESS). We use Gaia colours and magnitudes to isolate a subsample of provisional Cep--Her members that are located in a narrow band on the colour--magnitude diagram compatible with the zero-age main sequence. The $\delta$ Sct pulsator fraction amongst these stars peaks at 100% and we describe a trend of higher pulsator fractions for younger stellar associations. We use four methods to measure the frequency of maximum amplitude or power, $\nu_{\rm max}$, to minimise methodological bias and we demonstrate their sound performance. The $\nu_{\rm max}$ measurements display a correlation with effective temperature, but with scatter that is too large for the relation to be useful. We find two ridges in the $\nu_{\rm max}$--$T_{\rm eff}$ diagram, one of which appears to be the result of rapid rotation causing stars to pulsate in low-order modes. We measure the $\nu_{\rm max}$ values of $\delta$ Sct stars in four other clusters or associations of similar age (Trumpler 10, the Pleiades, NGC 2516, and Praesepe) and find similar behaviour with $T_{\rm eff}$. Using \'echelle diagrams we measure the asteroseismic large spacing, $\Delta\nu$, for 70 stars, and find a correlation between $\Delta\nu$, rotation, and luminosity that allows rapid rotators seen at low inclinations to be distinguished from slow rotators. We find that rapid rotators are more likely than slow rotators to pulsate, but they do so with less regular pulsation patterns. We also investigate the reliability of Gaia's vbroad measurement for A-type stars, finding that it is mostly accurate but underestimates $v\sin i$ for slow rotators ($v\sin i < 50$ km.s$^{-1}$) by 10--15%., Comment: 19 pages, or 12 without end-matter. Accepted in MNRAS. Supplementary online material will be made available via the MNRAS webpage and CDS. Version 2 has an updated reference list

Mental health disorders are among the most prevalent diseases worldwide, affecting nearly one in four people. Despite their widespread impact, the intervention rate remains below 25%, largely due to the significant cooperation required from patients for both diagnosis and intervention. The core issue behind this low treatment rate is stigma, which discourages over half of those affected from seeking help. This paper presents MindGuard, an accessible, stigma-free, and professional mobile mental healthcare system designed to provide mental health first aid. The heart of MindGuard is an innovative edge LLM, equipped with professional mental health knowledge, that seamlessly integrates objective mobile sensor data with subjective Ecological Momentary Assessment records to deliver personalized screening and intervention conversations. We conduct a broad evaluation of MindGuard using open datasets spanning four years and real-world deployment across various mobile devices involving 20 subjects for two weeks. Remarkably, MindGuard achieves results comparable to GPT-4 and outperforms its counterpart with more than 10 times the model size. We believe that MindGuard paves the way for mobile LLM applications, potentially revolutionizing mental healthcare practices by substituting self-reporting and intervention conversations with passive, integrated monitoring within daily life, thus ensuring accessible and stigma-free mental health support.

We present a lightweight approach to sequence classification using Ensemble Methods for Hidden Markov Models (HMMs). HMMs offer significant advantages in scenarios with imbalanced or smaller datasets due to their simplicity, interpretability, and efficiency. These models are particularly effective in domains such as finance and biology, where traditional methods struggle with high feature dimensionality and varied sequence lengths. Our ensemble-based scoring method enables the comparison of sequences of any length and improves performance on imbalanced datasets. This study focuses on the binary classification problem, particularly in scenarios with data imbalance, where the negative class is the majority (e.g., normal data) and the positive class is the minority (e.g., anomalous data), often with extreme distribution skews. We propose a novel training approach for HMM Ensembles that generalizes to multi-class problems and supports classification and anomaly detection. Our method fits class-specific groups of diverse models using random data subsets, and compares likelihoods across classes to produce composite scores, achieving high average precisions and AUCs. In addition, we compare our approach with neural network-based methods such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs), highlighting the efficiency and robustness of HMMs in data-scarce environments. Motivated by real-world use cases, our method demonstrates robust performance across various benchmarks, offering a flexible framework for diverse applications.

Models for solving the Reynolds-averaged Navier-Stokes equations are popular tools for predicting complex turbulent flows due to their computational affordability and ability to provide or estimate quantities of engineering interest. However, results depend on a proper treatment of unclosed terms, which require progress in the development and assessment of model forms. In this study, we consider the Reynolds stress transport equations as a framework for second-moment turbulence closure modeling. We specifically focus on the terms responsible for decay of the Reynolds stresses, which can be isolated and evaluated separately from other terms in a canonical setup of homogeneous turbulence. We show that by using anisotropic forcing of the momentum equation, we can access states of turbulence traditionally not probed in a triply-periodic domain. The resulting data span a wide range of anisotropic turbulent behavior in a more comprehensive manner than extant literature. We then consider a variety of model forms for which these data allow us to perform a robust selection of model coefficients and select an optimal model that extends to cubic terms when expressed in terms of the principal coordinate Reynolds stresses. Performance of the selected decay model is then examined relative to the simulation data and popular models from the literature, demonstrating the superior accuracy of the developed model and, in turn, the efficacy of this framework for model selection and tuning.

We present a sublinear time algorithm that gives random local access to the uniform distribution over satisfying assignments to an arbitrary k-CNF formula $\Phi$, at exponential clause density. Our algorithm provides memory-less query access to variable assignments, such that the output variable assignments consistently emulate a single global satisfying assignment whose law is close to the uniform distribution over satisfying assignments to $\Phi$. Such models were formally defined (for the more general task of locally sampling from exponentially sized sample spaces) in 2017 by Biswas, Rubinfeld, and Yodpinyanee, who studied the analogous problem for the uniform distribution over proper q-colorings. This model extends a long line of work over multiple decades that studies sublinear time algorithms for problems in theoretical computer science. Random local access and related models have been studied for a wide variety of natural Gibbs distributions and random graphical processes. Here, we establish feasiblity of random local access models for one of the most canonical such sample spaces, the set of satisfying assignments to a k-CNF formula., Comment: 21 pages

This study focuses on enhancing the design of an existing knee exoskeleton by addressing limitations in the range of motion (ROM) during Sit-to-Stand (STS) motions. While current knee exoskeletons emphasize toughness and rehabilitation, their closed-loop mechanisms hinder optimal ROM, which is crucial for effective rehabilitation. This research aims to optimize the exoskeleton design to achieve the necessary ROM, improving its functionality in rehabilitation. This can be achieved by utilizing kinematic modeling and formulation, the existing design was represented in the non-linear and non-convex mathematical functions. Optimization techniques, considering constraints based on human leg measurements, were applied to determine the best dimensions for the exoskeleton. This resulted in a significant increase in ROM compared to existing models. A MATLAB program was developed to compare the ROM of the optimized exoskeleton with the original design. To validate the practicality of the optimized design, analysis was conducted using a mannequin with average human dimensions, followed by constructing a cardboard dummy model to confirm simulation results. The STS motion of an average human was captured using a camera and TRACKER software, and the motion was compared with that of the dummy model to identify any misalignments between the human and exoskeleton knee joints. Furthermore, a prototype of the knee joint exoskeleton is being developed to further investigate misalignments and improve the design. Future work includes the use of EMG sensors for more detailed analysis and better results.

We present a comprehensive study aimed at elucidating the complex magnetic correlations in Co$_2$TiSi$_{0.5}$Al$_{0.5}$ Heusler alloy having the partial B2-type structure amid L2$_1$ cubic main phase. The thermo-magnetization measurements at 100 Oe reveal the presence of two magnetic transitions at T$\rm_{C1}=278~K$ and T$\rm_{C2}=270~K$, respectively, with saturation magnetization of around 1.2 $\mu \rm_ B$/f.u. at 5~K. Our magnetic field dependent studies reveal the dominance of T$\rm_{C1}$ transition at lower fields ($\mu_0\rm H \leqslant 0.03~Tesla$); however, at higher fields the T$\rm_{C2}$ transition becomes more pronounced. The observation of remnant magnetization above Curie temperature suggests the development of Griffiths-like phase, which is extensively analyzed through {\it ac} and {\it dc}- magnetic susceptibility ($\chi$) data. The evaluation of magnetocaloric potential indicates second order phase transition with notable $\Delta S_{\rm M}=$ 2.22 Jkg$^{-1}$K$^{-1}$ at 7 Tesla. The low-field ($\mu_0\rm H \leqslant 0.1~Tesla$) magnetic entropy ($\Delta S_{\rm M}$) curves exhibit two non-identical positive peaks. The nature and range of spin interactions near T$\rm_C$ were scrutinized through rigorous critical phenomenon analysis, and the values of exponents $\alpha, \beta, \gamma$ and $\delta$ to be $0.063, 0.361, 1.108$ and $3.943$, respectively, which are found to be slightly deviating from mean-field theory towards 3D Heisenberg model. Additionally, the exchange magnetic interactions are found to decay as $J(r) \sim r^{-4.6}$. Furthermore, the density functional theory results reveal the half-metallic nature exhibiting 100\% spin polarization (SP). However, the electronic and magnetic properties are greatly affected by the incorporation of structural disorder, which results in drastic reduction of SP to mere 8.3\%., Comment: submitted