Search

The behavior of many complex systems, from nanostructured materials to animal colonies, is governed by local transitions that, while involving a restricted number of interacting units, may generate collective cascade phenomena. Tracking such local events and understanding how they emerge and propagate throughout these systems represent often a challenge. Common strategies monitor specific parameters, tailored ad hoc to describe certain systems, over time. However, such approaches typically require prior knowledge of the underpinning physics and are poorly transferable to different systems. Here we present LEAP, a general, transferable, agnostic analysis approach that can reveal precious information on the physics of a variety of complex dynamical systems simply starting from the trajectory of their constitutive units. Built on a bivariate combination of two abstract descriptors, LENS and TimeSOAP, the LEAP analysis allows (i) detecting the emergence of local fluctuations in simulation or experimentally-acquired trajectories of any type of multicomponent system, (ii) classifying fluctuations into categories, and (iii) correlating them in space and time. We demonstrate how LEAP, just building on the abstract concepts of local fluctuations and their spatiotemporal correlation, efficiently reveals precious insights on the emergence and propagation of local and collective phenomena in a variety of complex dynamical systems ranging from the atomic- to the microscopic-scale. Given its abstract character, we expect that LEAP will offer an important tool to understand and predict the behavior of systems whose physics is unknown a priori, as well as to revisit a variety of known complex physical phenomena under a new perspective.

This paper evaluates and compares the performance of model-free and model-based reinforcement learning for the attitude control of fixed-wing unmanned aerial vehicles using PID as a reference point. The comparison focuses on their ability to handle varying flight dynamics and wind disturbances in a simulated environment. Our results show that the Temporal Difference Model Predictive Control agent outperforms both the PID controller and other model-free reinforcement learning methods in terms of tracking accuracy and robustness over different reference difficulties, particularly in nonlinear flight regimes. Furthermore, we introduce actuation fluctuation as a key metric to assess energy efficiency and actuator wear, and we test two different approaches from the literature: action variation penalty and conditioning for action policy smoothness. We also evaluate all control methods when subject to stochastic turbulence and gusts separately, so as to measure their effects on tracking performance, observe their limitations and outline their implications on the Markov decision process formalism., Comment: Published at ICINCO 2024

The anisotropic light-matter interactions in 2D materials have garnered significant attention for their potential to develop futuristic polarization-based optoelectronic devices, such as photodetectors and photo-actuators. In this study, we investigate the polarization-dependent interactions in ferroelectric 3R alpha-In2Se3 using Angle-Resolved Polarized Raman Spectroscopy (ARPRS) with different excitation lasers. Our experimental findings supported by complementary Density Functional Theory calculations demonstrate that the light-matter interactions depend not only on the crystallographic orientation but also on the excitation energy. Scanning transmission electron microscopy (STEM) confirms the highly anisotropic 3R crystal structure of alpha-In2Se3. This anisotropy in crystal structure facilitates significant optical anisotropy, driven by a complex interplay of electron-photon and electron-phonon interactions, which is reflected in the complex nature of the Raman tensor elements. These anisotropy interactions extend to the materials electrical response under light illumination. Remarkably, the anisotropic photo-response can be tuned by both polarization and wavelength of the incident light, making In2Se3 a promising material for advanced polarization-sensitive photodetection applications., Comment: 19 pages, 6 figures, supporting information

Tumors in the brain result from abnormal cell growth within the brain tissue, arising from various types of brain cells. When left undiagnosed, they lead to severe neurological deficits such as cognitive impairment, motor dysfunction, and sensory loss. As the tumor grows, it causes an increase in intracranial pressure, potentially leading to life-threatening complications such as brain herniation. Therefore, early detection and treatment are necessary to manage the complications caused by such tumors to slow down their growth. Numerous works involving deep learning (DL) and artificial intelligence (AI) are being carried out to assist physicians in early diagnosis by utilizing the scans obtained through Magnetic Resonance Imaging (MRI). Our research proposes DL frameworks for localizing, segmenting, and classifying the grade of these gliomas from MRI images to solve this critical issue. In our localization framework, we enhance the LinkNet framework with a VGG19- inspired encoder architecture for improved multimodal tumor feature extraction, along with spatial and graph attention mechanisms to refine feature focus and inter-feature relationships. Following this, we integrated the SeResNet101 CNN model as the encoder backbone into the LinkNet framework for tumor segmentation, which achieved an IoU Score of 96%. To classify the segmented tumors, we combined the SeResNet152 feature extractor with an Adaptive Boosting classifier, which yielded an accuracy of 98.53%. Our proposed models demonstrated promising results, with the potential to advance medical AI by enabling early diagnosis and providing more accurate treatment options for patients., Comment: 36 pages, 27 figures, 5 tables

Directional motion is commonly observed in various living active systems, such as bacterial colonies moving through confined environments. In these systems, the dynamics arise from the collective effects of mutual interactions between individual elements, as well as their interactions with obstacles or boundaries. In this study, we turn our focus to an artificial system and experimentally investigate the emergence of directional revolution in dimer and trimer structures composed of colloidal particles in ring-shaped optical illumination. In this case, the movement of these colloidal structures is exclusively facilitated by optothermal interactions without any direct mechanical force applied from the external optical field. Depending on the optical absorption properties of the colloidal particles, these optothermal interactions can exhibit both attractive and repulsive characteristics. The attractive interactions provide the necessary driving force that propels the motion, while the repulsive interactions serve to control the structural parameters of the system. The arrangement and interaction of the colloidal particles within these dimer and trimer structures fuel the controlled, directional revolution, with the optical gradient force acting as a confining factor, guiding the movement along a specific path. Notably, the dynamics of these systems can be tuned by altering the intensity of the optical field. This study can be useful as a model for understanding insights into biological systems where group dynamics and environmental interactions are key to coordinated movement.

This paper introduces Adaptive Mixture Importance Sampling (AMIS) as a novel approach for optimizing key performance indicators (KPIs) in large-scale recommender systems, such as online ad auctions. Traditional importance sampling (IS) methods face challenges in dynamic environments, particularly in navigating through complexities of multi-modal landscapes and avoiding entrapment in local optima for the optimization task. Instead of updating importance weights and mixing samples across iterations, as in canonical adaptive IS and multiple IS, our AMIS framework leverages a mixture distribution as the proposal distribution and dynamically adjusts both the mixture parameters and their mixing rates at each iteration, thereby enhancing search diversity and efficiency. Through extensive offline simulations, we demonstrate that AMIS significantly outperforms simple Gaussian Importance Sampling (GIS), particularly in noisy environments. Moreover, our approach is validated in real-world scenarios through online A/B experiments on a major search engine, where AMIS consistently identifies optimal tuning points that are more likely to be adopted as mainstream configurations. These findings indicate that AMIS enhances convergence in noisy environments, leading to more accurate and reliable decision-making in the context of importance sampling off-policy estimators., Comment: Accepted at the CONSEQUENCES '24 workshop, co-located with ACM RecSys '24

Clustering artworks based on style has many potential real-world applications like art recommendations, style-based search and retrieval, and the study of artistic style evolution in an artwork corpus. However, clustering artworks based on style is largely an unaddressed problem. A few present methods for clustering artworks principally rely on generic image feature representations derived from deep neural networks and do not specifically deal with the artistic style. In this paper, we introduce and deliberate over the notion of style-based clustering of visual artworks. Our main objective is to explore neural feature representations and architectures that can be used for style-based clustering and observe their impact and effectiveness. We develop different methods and assess their relative efficacy for style-based clustering through qualitative and quantitative analysis by applying them to four artwork corpora and four curated synthetically styled datasets. Our analysis provides some key novel insights on architectures, feature representations, and evaluation methods suitable for style-based clustering., Comment: 29 pages

Modern music streaming services are heavily based on recommendation engines to serve content to users. Sequential recommendation -- continuously providing new items within a single session in a contextually coherent manner -- has been an emerging topic in current literature. User feedback -- a positive or negative response to the item presented -- is used to drive content recommendations by learning user preferences. We extend this idea to session-based recommendation to provide context-coherent music recommendations by modelling negative user feedback, i.e., skips, in the loss function. We propose a sequence-aware contrastive sub-task to structure item embeddings in session-based music recommendation, such that true next-positive items (ignoring skipped items) are structured closer in the session embedding space, while skipped tracks are structured farther away from all items in the session. This directly affects item rankings using a K-nearest-neighbors search for next-item recommendations, while also promoting the rank of the true next item. Experiments incorporating this task into SoTA methods for sequential item recommendation show consistent performance gains in terms of next-item hit rate, item ranking, and skip down-ranking on three music recommendation datasets, strongly benefiting from the increasing presence of user feedback., Comment: To-appear at 18th ACM Conference on Recommendation Systems

We conduct systematic experiments to investigate the dynamics of liquid jet breakup and the resulting droplet size distribution, emphasizing the influence of liquid jet velocity and needle exit diameter. We precisely control jet formation using a pressurized water tank equipped with needles of different sizes. Our study quantifies breakup dynamics through dimensionless parameters such as the liquid Weber number and the needle exit area ratio. Our key findings identify three distinct breakup regimes, such as dripping, Rayleigh, and wind-induced, each dictated by the interplay of surface tension and aerodynamic forces for various combinations of liquid jet velocity and needle exit diameter. We construct a regime map to delineate different breakup behaviours in the We - Ar space. It is observed that lower jet velocities produce narrow probability density functions for jet breakup length due to stable jets, whereas higher velocities result in broader distributions. Increasing jet velocity extends breakup lengths for moderate flow rates due to enhanced stability in the Rayleigh regime, but higher velocities induce instability, leading to shorter breakup lengths. Additionally, we analyze the effects of the needle exit area ratio and liquid Weber number on droplet size distribution, highlighting the transition from mono-modal to bi-modal distribution under varying conditions., Comment: 15 pages, 12 figures, Physics of Fluids

Autonomous agent applications powered by large language models (LLMs) have recently risen to prominence as effective tools for addressing complex real-world tasks. At their core, agentic workflows rely on LLMs to plan and execute the use of tools and external Application Programming Interfaces (APIs) in sequence to arrive at the answer to a user's request. Various benchmarks and leaderboards have emerged to evaluate an LLM's capabilities for tool and API use; however, most of these evaluations only track single or multiple isolated API calling capabilities. In this paper, we present NESTFUL, a benchmark to evaluate LLMs on nested sequences of API calls, i.e., sequences where the output of one API call is passed as input to a subsequent call. NESTFUL has a total of 300 human annotated samples divided into two types - executable and non-executable. The executable samples are curated manually by crawling Rapid-APIs whereas the non-executable samples are hand picked by human annotators from data synthetically generated using an LLM. We evaluate state-of-the-art LLMs with function calling abilities on NESTFUL. Our results show that most models do not perform well on nested APIs in NESTFUL as compared to their performance on the simpler problem settings available in existing benchmarks.

Cardiac arrest remains a leading cause of death worldwide, necessitating proactive measures for early detection and intervention. This project aims to develop and assess predictive models for the timely identification of cardiac arrest incidents, utilizing a comprehensive dataset of clinical parameters and patient histories. Employing machine learning (ML) algorithms like XGBoost, Gradient Boosting, and Naive Bayes, alongside a deep learning (DL) approach with Recurrent Neural Networks (RNNs), we aim to enhance early detection capabilities. Rigorous experimentation and validation revealed the superior performance of the RNN model, which effectively captures complex temporal dependencies within the data. Our findings highlight the efficacy of these models in accurately predicting cardiac arrest likelihood, emphasizing the potential for improved patient care through early risk stratification and personalized interventions. By leveraging advanced analytics, healthcare providers can proactively mitigate cardiac arrest risk, optimize resource allocation, and improve patient outcomes. This research highlights the transformative potential of machine learning and deep learning techniques in managing cardiovascular risk and advances the field of predictive healthcare analytics.

Brain tumors are abnormalities that can severely impact a patient's health, leading to life-threatening conditions such as cancer. These can result in various debilitating effects, including neurological issues, cognitive impairment, motor and sensory deficits, as well as emotional and behavioral changes. These symptoms significantly affect a patient's quality of life, making early diagnosis and timely treatment essential to prevent further deterioration. However, accurately segmenting the tumor region from medical images, particularly MRI scans, is a challenging and time-consuming task that requires the expertise of radiologists. Manual segmentation can also be prone to human errors. To address these challenges, this research leverages the synergy of SeNet and ResNet architectures within an encoder-decoder framework, designed specifically for glioma detection and segmentation. The proposed model incorporates the power of SeResNet-152 as the backbone, integrated into a robust encoder-decoder structure to enhance feature extraction and improve segmentation accuracy. This novel approach significantly reduces the dependency on manual tasks and improves the precision of tumor identification. Evaluation of the model demonstrates strong performance, achieving 87% in Dice Coefficient, 89.12% in accuracy, 88% in IoU score, and 82% in mean IoU score, showcasing its effectiveness in tackling the complex problem of brain tumor segmentation., Comment: 9 pages, 6 figures, 1 table

Monitoring edge-geodetic sets in a graph are subsets of vertices such that every edge of the graph must lie on all the shortest paths between two vertices of the monitoring set. These objects were introduced in a work by Foucaud, Krishna and Ramasubramony Sulochana with relation to several prior notions in the area of network monitoring like distance edge-monitoring. In this work, we explore the extension of those notions unto oriented graphs, modelling oriented networks, and call these objects monitoring arc-geodetic sets. We also define the lower and upper monitoring arc-geodetic number of an undirected graph as the minimum and maximum of the monitoring arc-geodetic number of all orientations of the graph. We determine the monitoring arc-geodetic number of fundamental graph classes such as bipartite graphs, trees, cycles, etc. Then, we characterize the graphs for which every monitoring arc-geodetic set is the entire set of vertices, and also characterize the solutions for tournaments. We also cover some complexity aspects by studying two algorithmic problems. We show that the problem of determining if an undirected graph has an orientation with the minimal monitoring arc-geodetic set being the entire set of vertices, is NP-hard. We also show that the problem of finding a monitoring arc-geodetic set of size at most $k$ is $NP$-complete when restricted to oriented graphs with maximum degree $4$.

Colloidal matter undergoing Brownian motion serves as a model system to study various physical phenomena. Understanding the effect of external perturbation on the assembly and dynamics of Brownian colloids has emerged as a relevant research issue in soft matter and biological physics. Optical perturbation in the form of photonic forces and torques has added impetus to this exploration. In recent years, optothermal effects arising due to optical excitation of mesoscale matter have expanded the toolbox of light-colloidal matter interactions. In this perspective, we present an experimental viewpoint on some of the developments related to the assembly and dynamics of Brownian colloids driven by the optothermal field. Furthermore, we discuss some interesting prospects on driven colloidal matter that can have implications on soft matter physics and soft photonics., Comment: Invited perspective article. Submitted to Applied Physics Letters. Comments welcome

Autism spectrum disorder (ASD) is characterized by significant challenges in social interaction and comprehending communication signals. Recently, therapeutic interventions for ASD have increasingly utilized Deep learning powered-computer vision techniques to monitor individual progress over time. These models are trained on private, non-public datasets from the autism community, creating challenges in comparing results across different models due to privacy-preserving data-sharing issues. This work introduces MMASD+, an enhanced version of the novel open-source dataset called Multimodal ASD (MMASD). MMASD+ consists of diverse data modalities, including 3D-Skeleton, 3D Body Mesh, and Optical Flow data. It integrates the capabilities of Yolov8 and Deep SORT algorithms to distinguish between the therapist and children, addressing a significant barrier in the original dataset. Additionally, a Multimodal Transformer framework is proposed to predict 11 action types and the presence of ASD. This framework achieves an accuracy of 95.03% for predicting action types and 96.42% for predicting ASD presence, demonstrating over a 10% improvement compared to models trained on single data modalities. These findings highlight the advantages of integrating multiple data modalities within the Multimodal Transformer framework.

With the second quantum revolution underway, quantum-enhanced sensors are moving from laboratory demonstrations to field deployments, providing enhanced and even new capabilities. Signal processing and operational software is becoming integral parts of these emerging sensing systems to reap the benefits of this progress. This paper looks into widefield Nitrogen Vacancy Center-based magnetometry and focuses on estimating the magnetic field from the Optically Detected Magnetic Resonances (ODMR) signal, a crucial output for various applications. Mapping the shifts of ODMR signals to phase estimation, a computationally efficient approaches are proposed. Involving Fourier Transform and Filtering as pre-processing steps, the suggested approaches involve linear curve fit or complex frequency estimation based on well-known super-resolution technique Estimation of Signal Parameters via Rotational Invariant Techniques (ESPRIT). The existing methods in the quantum sensing literature take different routes based on Lorentzian fitting for determining magnetic field maps. To showcase the functionality and effectiveness of the suggested techniques, relevant results, based on experimental data are provided, which shows a significant reduction in computational time with the proposed method over existing methods, Comment: 4 pages, 3 figures, typos corrected

We investigate anisotropic equation of state parameterization of dark energy within the framework of an axisymmetric (planar) Bianchi-I universe. In addition to constraining the equation of state for anisotropic dark energy and other standard cosmological model parameters, we also constrain any underlying anisotropic axis using the latest Pantheon+ Type Ia Supernovae data set augmented by SH0ES Cepheid distance calibrators. The mean anisotropic dark energy equation of state and corresponding difference in the equation of states in and normal to the plane of our axisymmetric Bianchi-I space-time are found to be $\bar{w}=-0.90^{+0.16}_{-0.12}$ and $\delta_w=-0.140^{+0.11}_{-0.082}$ respectively. We also find an axis of anisotropy in this planar Bianchi-I model with anisotropic dark energy to be $\approx(279^{\circ} ,12^{\circ})$ in galactic coordinates. Our analysis of different cosmological models suggests that while a Bianchi-I universe with anisotropic dark energy (the $w_b$CDM model) shows some preference over other anisotropic models, it is still less likely than the standard $\Lambda$CDM model or a model with a constant dark energy equation of state ($w$CDM). Overall, the $\Lambda$CDM model remains the most probable model based on the Akaike Information Criterion., Comment: 12 pages, 6 figures, 2 tables; Comments are welcome

Nucleic acids such as mRNA have emerged as a promising therapeutic modality with the capability of addressing a wide range of diseases. Lipid nanoparticles (LNPs) as a delivery platform for nucleic acids were used in the COVID-19 vaccines and have received much attention. While modern manufacturing processes which involve rapidly mixing an organic stream containing the lipids with an aqueous stream containing the nucleic acids are conceptually straightforward, detailed understanding of LNP formation and structure is still limited and scale-up can be challenging. Mathematical and computational methods are a promising avenue for deepening scientific understanding of the LNP formation process and facilitating improved process development and control. This article describes strategies for the mechanistic modeling of LNP formation, starting with strategies to estimate and predict important physicochemical properties of the various species such as diffusivities and solubilities. Subsequently, a framework is outlined for constructing mechanistic models of reactor- and particle-scale processes. Insights gained from the various models are mapped back to product quality attributes and process insights. Lastly, the use of the models to guide development of advanced process control and optimization strategies is discussed., Comment: 67 pages, 10 figures

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

To address the data scarcity associated with 3D assets, 2D-lifting techniques such as Score Distillation Sampling (SDS) have become a widely adopted practice in text-to-3D generation pipelines. However, the diffusion models used in these techniques are prone to viewpoint bias and thus lead to geometric inconsistencies such as the Janus problem. To counter this, we introduce MT3D, a text-to-3D generative model that leverages a high-fidelity 3D object to overcome viewpoint bias and explicitly infuse geometric understanding into the generation pipeline. Firstly, we employ depth maps derived from a high-quality 3D model as control signals to guarantee that the generated 2D images preserve the fundamental shape and structure, thereby reducing the inherent viewpoint bias. Next, we utilize deep geometric moments to ensure geometric consistency in the 3D representation explicitly. By incorporating geometric details from a 3D asset, MT3D enables the creation of diverse and geometrically consistent objects, thereby improving the quality and usability of our 3D representations., Comment: 9 pages, 8 figures

The projected sensitivity of the effective electron neutrino-mass measurement with the KATRIN experiment is below 0.3 eV (90 % CL) after five years of data acquisition. The sensitivity is affected by the increased rate of the background electrons from KATRIN's main spectrometer. A special shifted-analysing-plane (SAP) configuration was developed to reduce this background by a factor of two. The complex layout of electromagnetic fields in the SAP configuration requires a robust method of estimating these fields. We present in this paper a dedicated calibration measurement of the fields using conversion electrons of gaseous $^\mathrm{83m}$Kr, which enables the neutrino-mass measurements in the SAP configuration., Comment: 19 pages, 11 figures

Submodular optimization finds applications in machine learning and data mining. In this paper, we study the problem of maximizing functions of the form $h = f-c$, where $f$ is a monotone, non-negative, weakly submodular set function and $c$ is a modular function. We design a deterministic approximation algorithm that runs with ${{O}}(\frac{n}{\epsilon}\log \frac{n}{\gamma \epsilon})$ oracle calls to function $h$, and outputs a set ${S}$ such that $h({S}) \geq \gamma(1-\epsilon)f(OPT)-c(OPT)-\frac{c(OPT)}{\gamma(1-\epsilon)}\log\frac{f(OPT)}{c(OPT)}$, where $\gamma$ is the submodularity ratio of $f$. Existing algorithms for this problem either admit a worse approximation ratio or have quadratic runtime. We also present an approximation ratio of our algorithm for this problem with an approximate oracle of $f$. We validate our theoretical results through extensive empirical evaluations on real-world applications, including vertex cover and influence diffusion problems for submodular utility function $f$, and Bayesian A-Optimal design for weakly submodular $f$. Our experimental results demonstrate that our algorithms efficiently achieve high-quality solutions., Comment: To appear in CIKM'24. Full paper including omitted proofs

In the domain of black-box model extraction, conventional methods reliant on soft labels or surrogate datasets struggle with scaling to high-dimensional input spaces and managing the complexity of an extensive array of interrelated classes. In this work, we present a novel approach that utilizes SHAP (SHapley Additive exPlanations) to enhance synthetic data generation. SHAP quantifies the individual contributions of each input feature towards the victim model's output, facilitating the optimization of an energy-based GAN towards a desirable output. This method significantly boosts performance, achieving a 16.45% increase in the accuracy of image classification models and extending to video classification models with an average improvement of 26.11% and a maximum of 33.36% on challenging datasets such as UCF11, UCF101, Kinetics 400, Kinetics 600, and Something-Something V2. We further demonstrate the effectiveness and practical utility of our method under various scenarios, including the availability of top-k prediction probabilities, top-k prediction labels, and top-1 labels.

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

Vehicular Ad-Hoc Networks (VANETs) hold immense potential for improving traffic safety and efficiency. However, traditional centralized approaches for machine learning in VANETs raise concerns about data privacy and security. Federated Learning (FL) offers a solution that enables collaborative model training without sharing raw data. This paper proposes FL-DECO-BC as a novel privacy-preserving, provably secure, and provenance-preserving federated learning framework specifically designed for VANETs. FL-DECO-BC leverages decentralized oracles on blockchain to securely access external data sources while ensuring data privacy through advanced techniques. The framework guarantees provable security through cryptographic primitives and formal verification methods. Furthermore, FL-DECO-BC incorporates a provenance-preserving design to track data origin and history, fostering trust and accountability. This combination of features empowers VANETs with secure and privacy-conscious machine-learning capabilities, paving the way for advanced traffic management and safety applications.

Next-generation wireless networks aim to deliver data speeds much faster than 5G. This requires base stations with lots of antennas and a large operating bandwidth. These advanced base stations are expected to serve several multiantenna user-equipment (UEs) simultaneously on the same time-frequency resources on both the uplink and the downlink. The UE data rates are affected by the following three main factors: UE rank, which refers to the number of data layers used by each UE, UE frequency allocation, which refers to the assignment of slices of the overall frequency band to use for each UE in an orthogonal frequency-division multiplexing (OFDM) system, and UE power allocation/control, which refers to the allocation of power by the base station for data transmission to each UE on the downlink or the power used by each UE to send data on the uplink. Since multiple UEs are to be simultaneously served, the type of precoder used for downlink transmission and the type of receiver used for uplink reception predominantly influence these three aforementioned factors and the resulting overall UE throughput. This paper addresses the problem of jointly selecting these three parameters specifically when zero-forcing (ZF) precoders are used for downlink transmission and linear minimum mean square error (LMMSE) receivers are employed for uplink reception., Comment: 12 pages in double column format, 9 figures, 1 table. 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

Improving the reliability and spectral efficiency of wireless systems is a key goal in wireless systems. However, most efforts have been devoted to improving data channel capacity, whereas control-plane capacity bottlenecks are often neglected. In this paper, we propose a means of improving the control-plane capacity and reliability by shrinking the bit size of a key signaling message - the 5G Downlink Control Information (DCI). In particular, a transformer model is studied as a probability distribution estimator for Arithmetic coding to achieve lossless compression. Feature engineering, neural model design, and training technique are comprehensively discussed in this paper. Both temporal and spatial correlations among DCI messages are explored by the transformer model to achieve reasonable lossless compression performance. Numerical results show that the proposed method achieves 21.7% higher compression ratio than Huffman coding in DCI compression for a single-cell scheduling scenario.

Tiny Machine Learning (TinyML) is a branch of Machine Learning (ML) that constitutes a bridge between the ML world and the embedded system ecosystem (i.e., Internet of Things devices, embedded devices, and edge computing units), enabling the execution of ML algorithms on devices constrained in terms of memory, computational capabilities, and power consumption. Video Streaming Analysis (VSA), one of the most interesting tasks of TinyML, consists in scanning a sequence of frames in a streaming manner, with the goal of identifying interesting patterns. Given the strict constraints of these tiny devices, all the current solutions rely on performing a frame-by-frame analysis, hence not exploiting the temporal component in the stream of data. In this paper, we present StreamTinyNet, the first TinyML architecture to perform multiple-frame VSA, enabling a variety of use cases that requires spatial-temporal analysis that were previously impossible to be carried out at a TinyML level. Experimental results on public-available datasets show the effectiveness and efficiency of the proposed solution. Finally, StreamTinyNet has been ported and tested on the Arduino Nicla Vision, showing the feasibility of what proposed., Comment: this paper has been accepted and presented at the WCCI24 conference

We compare two-moment based \emph{energy-dependent} and 3 variants of \emph{energy-integrated} neutrino transport general-relativistic magnetohydrodynamics simulations of hypermassive neutron star. To study the impacts due to the choice of the neutrino transport schemes, we perform simulations with the same setups and input neutrino microphysics. We show that the main differences between energy-dependent and energy-integrated neutrino transport are found in the disk and ejecta properties, as well as in the neutrino signals. The properties of the disk surrounding the neutron star and the ejecta in energy-dependent transport are very different from the ones obtained using energy-integrated schemes. Specifically, in the energy-dependent case, the disk is more neutron-rich at early times, and becomes geometrically thicker at later times. In addition, the ejecta is more massive, and on average more neutron-rich in the energy-dependent simulations. Moreover, the average neutrino energies and luminosities are about 30\% higher. Energy-dependent neutrino transport is necessary if one wants to better model the neutrino signals and matter outflows from neutron star merger remnants via numerical simulations.

We experimentally investigate the morphology and breakup of a droplet as it descends freely from a height and encounters an airstream. The size distributions of the child droplets are analysed using high-speed shadowgraphy and in-line holography techniques. We found that a droplet falling from various heights exhibits shape oscillations due to the intricate interplay between inertia and surface tension forces, leading to significant variations in the radial deformation of the droplet, influencing the breakup dynamics under an identical airstream condition. Specifically, the droplet undergoes vibrational breakup when introduced at a location slightly above the air nozzle. In contrast, as the release height of the droplet increases, keeping the Weber number defined based on the velocity of the airstream fixed, a dynamic interplay between the inertia of the droplet and the aerodynamic flow field comes into play, resulting in a sequence of breakup modes transitioning from vibrational breakup to retracting bag breakup, bag breakup, bag-stamen, retracting bag-stamen breakup, and eventually returning to vibrational breakup. Our experiments also reveal that the size distribution resulting from retracting bag breakup primarily arises from rim and node fragmentation, leading to a bimodal distribution. In contrast, bag and bag-stamen breakups yield a tri-modal size distribution due to the combined contributions of bag, rim, and node breakup mechanisms. Furthermore, we utilize a theoretical model that incorporates the effective Weber number, considering different release heights. This model accurately predicts the size distribution of the child droplets resulting from the various breakup modes observed in our experiments., Comment: 23 pages, 17 figures

Electric field-induced giant resistive switching triggered by insulator-to-metal transition (IMT) is one of the promising approaches for developing a new class of electronics often referred to as Mottronics. Achieving this resistive switching by minimal external field at room temperature is of paramount research and technological interest. Mott-IMT is often associated with structural modification, which is very important for optoelectronic and actuator applications. Here, we report a giant resistive switching of about 900 % at room temperature in disordered polycrystalline V2O3-Si thin film stabilized at the IMT phase boundary and associated structural transformation under a small electric field. The increase of electron population in the a1g band under the field is responsible for the Mott gap collapse that drives the structural transition. Furthermore, we also fabricated a room temperature Mott-FET with a channel ON/OFF resistive ratio of about 15. This study provides a fundamental mechanism of the Mott-IMT in V2O3 as well as its device applications., Comment: 16 pages, 5 figures

Short gamma-ray bursts originate when relativistic jets emerge from the remnants of binary neutron star mergers. Both the jet and the remnant are believed to be strongly magnetized, and the presence of magnetic fields is known to influence the jet propagation across the surrounding post-merger environment. In the magnetic interplay between the jet and the environment itself, effects due to a finite plasma conductivity may be important, especially in the first phases of the jet propagation. We aim to investigate such effects, from jet launching to its final breakout from the post-merger environment. 2D axisymmetric and full 3D resistive relativistic MHD simulations, are performed with the PLUTO numerical code. Different models for physical resistivity, which must be small but still above the numerical one (producing unwanted smearing of structures in any ideal MHD code) are considered and compared. All simulations are performed by using an axisymmetric analytical model for the jet propagation environment; we leave the case of jet propagation in a realistic environment (i.e. imported from actual binary neutron star merger simulation) to a later study. Significant differences in the jet structure and induced turbulence are clearly seen in 2D axisymmetric simulations. Regions with a resistive electric field parallel to the magnetic field form and non-thermal particle acceleration may be enhanced there. The level of dissipated Ohmic power is also dependent on the various recipes for resistivity. Most of the differences arise before breakout from the magnetized environment, whereas once the jet enters the external atmosphere these differences are preserved during further propagation despite the lower grid refinement. Finally, we show and discuss the 3D evolution of the jet within the same environment, in order to highlight the emergence of non-axisymmetric features., Comment: 14 pages (+1 appendix), 8 figures (+ 1 appendix), submitted to A&A

Farmers face various challenges when it comes to identifying diseases in rice leaves during their early stages of growth, which is a major reason for poor produce. Therefore, early and accurate disease identification is important in agriculture to avoid crop loss and improve cultivation. In this research, we propose a novel hybrid deep learning (DL) classifier designed by extending the Squeeze-and-Excitation network architecture with a channel attention mechanism and the Swish ReLU activation function. The channel attention mechanism in our proposed model identifies the most important feature channels required for classification during feature extraction and selection. The dying ReLU problem is mitigated by utilizing the Swish ReLU activation function, and the Squeeze-andExcitation blocks improve information propagation and cross-channel interaction. Upon evaluation, our model achieved a high F1-score of 99.76% and an accuracy of 99.74%, surpassing the performance of existing models. These outcomes demonstrate the potential of state-of-the-art DL techniques in agriculture, contributing to the advancement of more efficient and reliable disease detection systems., Comment: 17 pages, 4 tables, 10 figures

The recent strides in artificial intelligence (AI) and machine learning (ML) have propelled the rise of TinyML, a paradigm enabling AI computations at the edge without dependence on cloud connections. While TinyML offers real-time data analysis and swift responses critical for diverse applications, its devices' intrinsic resource limitations expose them to security risks. This research delves into the adversarial vulnerabilities of AI models on resource-constrained embedded hardware, with a focus on Model Extraction and Evasion Attacks. Our findings reveal that adversarial attacks from powerful host machines could be transferred to smaller, less secure devices like ESP32 and Raspberry Pi. This illustrates that adversarial attacks could be extended to tiny devices, underscoring vulnerabilities, and emphasizing the necessity for reinforced security measures in TinyML deployments. This exploration enhances the comprehension of security challenges in TinyML and offers insights for safeguarding sensitive data and ensuring device dependability in AI-powered edge computing settings., Comment: Accepted and presented at tinyML Foundation EMEA Innovation Forum 2024

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

Alzheimer's disease (AD) represents the primary form of neurodegeneration, impacting millions of individuals each year and causing progressive cognitive decline. Accurately diagnosing and classifying AD using neuroimaging data presents ongoing challenges in medicine, necessitating advanced interventions that will enhance treatment measures. In this research, we introduce a dual attention enhanced deep learning (DL) framework for classifying AD from neuroimaging data. Combined spatial and self-attention mechanisms play a vital role in emphasizing focus on neurofibrillary tangles and amyloid plaques from the MRI images, which are difficult to discern with regular imaging techniques. Results demonstrate that our model yielded remarkable performance in comparison to existing state of the art (SOTA) convolutional neural networks (CNNs), with an accuracy of 99.1%. Moreover, it recorded remarkable metrics, with an F1-Score of 99.31%, a precision of 99.24%, and a recall of 99.5%. These results highlight the promise of cutting edge DL methods in medical diagnostics, contributing to highly reliable and more efficient healthcare solutions., Comment: 18 pages, 10 figures, 6 tables

Humans describe complex scenes with compositionality, using simple text descriptions enriched with links and relationships. While vision-language research has aimed to develop models with compositional understanding capabilities, this is not reflected yet in existing datasets which, for the most part, still use plain text to describe images. In this work, we propose a new annotation strategy, graph-based captioning (GBC) that describes an image using a labelled graph structure, with nodes of various types. The nodes in GBC are created using, in a first stage, object detection and dense captioning tools nested recursively to uncover and describe entity nodes, further linked together in a second stage by highlighting, using new types of nodes, compositions and relations among entities. Since all GBC nodes hold plain text descriptions, GBC retains the flexibility found in natural language, but can also encode hierarchical information in its edges. We demonstrate that GBC can be produced automatically, using off-the-shelf multimodal LLMs and open-vocabulary detection models, by building a new dataset, GBC10M, gathering GBC annotations for about 10M images of the CC12M dataset. We use GBC10M to showcase the wealth of node captions uncovered by GBC, as measured with CLIP training. We show that using GBC nodes' annotations -- notably those stored in composition and relation nodes -- results in significant performance boost on downstream models when compared to other dataset formats. To further explore the opportunities provided by GBC, we also propose a new attention mechanism that can leverage the entire GBC graph, with encouraging experimental results that show the extra benefits of incorporating the graph structure. Our datasets are released at \url{https://huggingface.co/graph-based-captions}., Comment: 47 pages, 33 figures

Deep learning has shown its efficacy in extracting useful features to solve various computer vision tasks. However, when the structure of the data is complex and noisy, capturing effective information to improve performance is very difficult. To this end, topological data analysis (TDA) has been utilized to derive useful representations that can contribute to improving performance and robustness against perturbations. Despite its effectiveness, the requirements for large computational resources and significant time consumption in extracting topological features through TDA are critical problems when implementing it on small devices. To address this issue, we propose a framework called Topological Guidance-based Knowledge Distillation (TGD), which uses topological features in knowledge distillation (KD) for image classification tasks. We utilize KD to train a superior lightweight model and provide topological features with multiple teachers simultaneously. We introduce a mechanism for integrating features from different teachers and reducing the knowledge gap between teachers and the student, which aids in improving performance. We demonstrate the effectiveness of our approach through diverse empirical evaluations., Comment: ICML 2024 Workshop on Geometry-grounded Representation Learning and Generative Modeling

Deep learning methods have achieved a lot of success in various applications involving converting wearable sensor data to actionable health insights. A common application areas is activity recognition, where deep-learning methods still suffer from limitations such as sensitivity to signal quality, sensor characteristic variations, and variability between subjects. To mitigate these issues, robust features obtained by topological data analysis (TDA) have been suggested as a potential solution. However, there are two significant obstacles to using topological features in deep learning: (1) large computational load to extract topological features using TDA, and (2) different signal representations obtained from deep learning and TDA which makes fusion difficult. In this paper, to enable integration of the strengths of topological methods in deep-learning for time-series data, we propose to use two teacher networks, one trained on the raw time-series data, and another trained on persistence images generated by TDA methods. The distilled student model utilizes only the raw time-series data at test-time. This approach addresses both issues. The use of KD with multiple teachers utilizes complementary information, and results in a compact model with strong supervisory features and an integrated richer representation. To assimilate desirable information from different modalities, we design new constraints, including orthogonality imposed on feature correlation maps for improving feature expressiveness and allowing the student to easily learn from the teacher. Also, we apply an annealing strategy in KD for fast saturation and better accommodation from different features, while the knowledge gap between the teachers and student is reduced. Finally, a robust student model is distilled, which uses only the time-series data as an input, while implicitly preserving topological features., Comment: Engineering Applications of Artificial Intelligence 130, 107719

We analyze a one-dimensional two-scalar fields reaction advection diffusion model for the globally subcritical transition to turbulence. In this model, the homogeneous turbulent state is disconnected from the laminar one and disappears in a tipping catastrophe scenario. The model however exhibits a linear instability of the turbulent homogeneous state, mimicking the onset of the laminar-turbulent patterns observed in the transitional regime of wall shear flows. Numerically continuing the solutions obtained at large Reynolds numbers, we construct the Busse balloon associated with the multistability of the nonlinear solutions emerging from the instability. In the core of the balloon, the turbulent fluctuations, encoded into a multiplicative noise, select the pattern wavelength. On the lower Reynolds number side of the balloon, the pattern follows a cascade of destabilizations towards larger and larger, eventually infinite wavelengths. In that limit, the periodic limit cycle associated with the spatial pattern hits the laminar fixed point, resulting in a saddle-loop global bifurcation and the emergence of solitary pulse solutions. This saddle-loop scenario predicts a logarithmic divergence of the wavelength, which captures experimental and numerical data in two representative shear flows., Comment: 5 pages, 6 figures

DLRM is a state-of-the-art recommendation system model that has gained widespread adoption across various industry applications. The large size of DLRM models, however, necessitates the use of multiple devices/GPUs for efficient training. A significant bottleneck in this process is the time-consuming all-to-all communication required to collect embedding data from all devices. To mitigate this, we introduce a method that employs error-bounded lossy compression to reduce the communication data size and accelerate DLRM training. We develop a novel error-bounded lossy compression algorithm, informed by an in-depth analysis of embedding data features, to achieve high compression ratios. Moreover, we introduce a dual-level adaptive strategy for error-bound adjustment, spanning both table-wise and iteration-wise aspects, to balance the compression benefits with the potential impacts on accuracy. We further optimize our compressor for PyTorch tensors on GPUs, minimizing compression overhead. Evaluation shows that our method achieves a 1.38$\times$ training speedup with a minimal accuracy impact., Comment: camera-ready version for SC '24

Breast cancer poses a profound threat to lives globally, claiming numerous lives each year. Therefore, timely detection is crucial for early intervention and improved chances of survival. Accurately diagnosing and classifying breast tumors using ultrasound images is a persistent challenge in medicine, demanding cutting-edge solutions for improved treatment strategies. This research introduces multiattention-enhanced deep learning (DL) frameworks designed for the classification and segmentation of breast cancer tumors from ultrasound images. A spatial channel attention mechanism is proposed for segmenting tumors from ultrasound images, utilizing a novel LinkNet DL framework with an InceptionResNet backbone. Following this, the paper proposes a deep convolutional neural network with an integrated multi-attention framework (DCNNIMAF) to classify the segmented tumor as benign, malignant, or normal. From experimental results, it is observed that the segmentation model has recorded an accuracy of 98.1%, with a minimal loss of 0.6%. It has also achieved high Intersection over Union (IoU) and Dice Coefficient scores of 96.9% and 97.2%, respectively. Similarly, the classification model has attained an accuracy of 99.2%, with a low loss of 0.31%. Furthermore, the classification framework has achieved outstanding F1-Score, precision, and recall values of 99.1%, 99.3%, and 99.1%, respectively. By offering a robust framework for early detection and accurate classification of breast cancer, this proposed work significantly advances the field of medical image analysis, potentially improving diagnostic precision and patient outcomes., Comment: 29 pages, 15 figures, 6 tables

Using results from scaling laws, this theoretical note argues that the following two statements cannot be simultaneously true: 1. Superposition hypothesis where sparse features are linearly represented across a layer is a complete theory of feature representation. 2. Features are universal, meaning two models trained on the same data and achieving equal performance will learn identical features., Comment: 4 pages, 1 figure

Surface plasmons (SP) and their mediated effects have been widely used to manipulate micro- and nanoscale objects of dielectric and metallic nature. In this work, we show how SP excitation can be used to induce thermofluidic and thermoelectric effects to manipulate colloidal dynamics on a large scale. In an evanescent plasmonic trap, temperature gradients induce fluid flow that can facilitate particle accumulation. However, large out-of-plane flows expel particles from the trap, resulting in a shallow trap potential. Here, we numerically demonstrate how adding thermoelectric fields can overpower the optical and hydrodynamic forces to achieve a stable nanoparticle assembly at low excitation powers. We calculate the corresponding optical, fluidic, and thermoelectric trapping forces and potentials. These potentials can be enabled without resonant SP excitation, which requires careful optical alignment. Thus, we explain the mechanism of how, despite weak optical intensities and forces, sufficient trapping force can be supplied via the evanescent optothermoelectric trap to obtain large-scale reversible nanoparticle assemblies, irrespective of their shape, size, or material., Comment: 21 pages, 4 figures

Large language models (LLMs) have recently shown tremendous promise in serving as the backbone to agentic systems, as demonstrated by their performance in multi-faceted, challenging benchmarks like SWE-Bench and Agent-Bench. However, to realize the true potential of LLMs as autonomous agents, they must learn to identify, call, and interact with external tools and application program interfaces (APIs) to complete complex tasks. These tasks together are termed function calling. Endowing LLMs with function calling abilities leads to a myriad of advantages, such as access to current and domain-specific information in databases and knowledge sources, and the ability to outsource tasks that can be reliably performed by tools, e.g., a Python interpreter or calculator. While there has been significant progress in function calling with LLMs, there is still a dearth of open models that perform on par with proprietary LLMs like GPT, Claude, and Gemini. Therefore, in this work, we introduce the GRANITE-20B-FUNCTIONCALLING model under an Apache 2.0 license. The model is trained using a multi-task training approach on seven fundamental tasks encompassed in function calling, those being Nested Function Calling, Function Chaining, Parallel Functions, Function Name Detection, Parameter-Value Pair Detection, Next-Best Function, and Response Generation. We present a comprehensive evaluation on multiple out-of-domain datasets comparing GRANITE-20B-FUNCTIONCALLING to more than 15 other best proprietary and open models. GRANITE-20B-FUNCTIONCALLING provides the best performance among all open models on the Berkeley Function Calling Leaderboard and fourth overall. As a result of the diverse tasks and datasets used for training our model, we show that GRANITE-20B-FUNCTIONCALLING has better generalizability on multiple tasks in seven different evaluation datasets.

For any positive integer $m$ and an odd prime $p$; let $\mathbb{F}_{q}+u\mathbb{F}_{q}$, where $q=p^{m}$, be a ring extension of the ring $\mathbb{F}_{p}+u\mathbb{F}_{p}.$ In this paper, we construct linear codes over $\mathbb{F}_{p}+u\mathbb{F}_{p}$ by using trace function defined on $\mathbb{F}_{q}+u\mathbb{F}_{q}$ and determine their Hamming weight distributions by employing symplectic-weight distributions of their Gray images.

In this study, linear codes having their Lee-weight distributions over the semi-local ring $\mathbb{F}_{q}+u\mathbb{F}_{q}$ with $u^{2}=1$ are constructed using the defining set and Gauss sums for an odd prime $q $. Moreover, we derive complete Hamming-weight enumerators for the images of the constructed linear codes under the Gray map. We finally show an application to secret sharing schemes.

As a two-sided marketplace, Airbnb brings together hosts who own listings for rent with prospective guests from around the globe. Results from a guest's search for listings are displayed primarily through two interfaces: (1) as a list of rectangular cards that contain on them the listing image, price, rating, and other details, referred to as list-results (2) as oval pins on a map showing the listing price, called map-results. Both these interfaces, since their inception, have used the same ranking algorithm that orders listings by their booking probabilities and selects the top listings for display. But some of the basic assumptions underlying ranking, built for a world where search results are presented as lists, simply break down for maps. This paper describes how we rebuilt ranking for maps by revising the mathematical foundations of how users interact with search results. Our iterative and experiment-driven approach led us through a path full of twists and turns, ending in a unified theory for the two interfaces. Our journey shows how assumptions taken for granted when designing machine learning algorithms may not apply equally across all user interfaces, and how they can be adapted. The net impact was one of the largest improvements in user experience for Airbnb which we discuss as a series of experimental validations.