Search

Oblivious RAM (ORAM) hides the memory access patterns, enhancing data privacy by preventing attackers from discovering sensitive information based on the sequence of memory accesses. The performance of ORAM is often limited by its inherent trade-off between security and efficiency, as concealing memory access patterns imposes significant computational and memory overhead. While prior works focus on improving the ORAM performance by prefetching and eliminating ORAM requests, we find that their performance is very sensitive to workload locality behavior and incurs additional management overhead caused by the ORAM stash pressure. This paper presents Palermo: a protocol-hardware co-design to improve ORAM performance. The key observation in Palermo is that classical ORAM protocols enforce restrictive dependencies between memory operations that result in low memory bandwidth utilization. Palermo introduces a new protocol that overlaps large portions of memory operations, within a single and between multiple ORAM requests, without breaking correctness and security guarantees. Subsequently, we propose an ORAM controller architecture that executes the proposed protocol to service ORAM requests. The hardware is responsible for concurrently issuing memory requests as well as imposing the necessary dependencies to ensure a consistent view of the ORAM tree across requests. Using a rich workload mix, we demonstrate that Palermo outperforms the RingORAM baseline by 2.8x, on average, incurring a negligible area overhead of 5.78mm^2 (less than 2% in 12th generation Intel CPU after technology scaling) and 2.14W without sacrificing security. We further show that Palermo also outperforms the state-of-the-art works PageORAM, PrORAM, and IR-ORAM., Comment: To appear in HPCA'25

This paper presents a novel reinforcement learning framework for trajectory tracking of unmanned aerial vehicles in cluttered environments using a dual-agent architecture. Traditional optimization methods for trajectory tracking face significant computational challenges and lack robustness in dynamic environments. Our approach employs deep reinforcement learning (RL) to overcome these limitations, leveraging 3D pointcloud data to perceive the environment without relying on memory-intensive obstacle representations like occupancy grids. The proposed system features two RL agents: one for predicting UAV velocities to follow a reference trajectory and another for managing collision avoidance in the presence of obstacles. This architecture ensures real-time performance and adaptability to uncertainties. We demonstrate the efficacy of our approach through simulated and real-world experiments, highlighting improvements over state-of-the-art RL and optimization-based methods. Additionally, a curriculum learning paradigm is employed to scale the algorithms to more complex environments, ensuring robust trajectory tracking and obstacle avoidance in both static and dynamic scenarios.

In the current era of social media and generative AI, an ability to automatically assess the credibility of online social media content is of tremendous importance. Credibility assessment is fundamentally based on aggregating credibility signals, which refer to small units of information, such as content factuality, bias, or a presence of persuasion techniques, into an overall credibility score. Credibility signals provide a more granular, more easily explainable and widely utilizable information in contrast to currently predominant fake news detection, which utilizes various (mostly latent) features. A growing body of research on automatic credibility assessment and detection of credibility signals can be characterized as highly fragmented and lacking mutual interconnections. This issue is even more prominent due to a lack of an up-to-date overview of research works on automatic credibility assessment. In this survey, we provide such systematic and comprehensive literature review of 175 research papers while focusing on textual credibility signals and Natural Language Processing (NLP), which undergoes a significant advancement due to Large Language Models (LLMs). While positioning the NLP research into the context of other multidisciplinary research works, we tackle with approaches for credibility assessment as well as with 9 categories of credibility signals (we provide a thorough analysis for 3 of them, namely: 1) factuality, subjectivity and bias, 2) persuasion techniques and logical fallacies, and 3) claims and veracity). Following the description of the existing methods, datasets and tools, we identify future challenges and opportunities, while paying a specific attention to recent rapid development of generative AI.

In this study, we investigate the effect of SSL objective modifications within the SPR framework, focusing on specific adjustments such as terminal state masking and prioritized replay weighting, which were not explicitly addressed in the original design. While these modifications are specific to RL, they are not universally applicable across all RL algorithms. Therefore, we aim to assess their impact on performance and explore other SSL objectives that do not accommodate these adjustments like Barlow Twins and VICReg. We evaluate six SPR variants on the Atari 100k benchmark, including versions both with and without these modifications. Additionally, we test the performance of these objectives on the DeepMind Control Suite, where such modifications are absent. Our findings reveal that incorporating specific SSL modifications within SPR significantly enhances performance, and this influence extends to subsequent frameworks like SR-SPR and BBF, highlighting the critical importance of SSL objective selection and related adaptations in achieving data efficiency in self-predictive reinforcement learning., Comment: Under Review AISTATS 2025,accepted to Neurips 2024 SSL Workshop

We study a federated version of multi-objective optimization (MOO), where a single model is trained to optimize multiple objective functions. MOO has been extensively studied in the centralized setting but is less explored in federated or distributed settings. We propose FedCMOO, a novel communication-efficient federated multi-objective optimization (FMOO) algorithm that improves the error convergence performance of the model compared to existing approaches. Unlike prior works, the communication cost of FedCMOO does not scale with the number of objectives, as each client sends a single aggregated gradient, obtained using randomized SVD (singular value decomposition), to the central server. We provide a convergence analysis of the proposed method for smooth non-convex objective functions under milder assumptions than in prior work. In addition, we introduce a variant of FedCMOO that allows users to specify a preference over the objectives in terms of a desired ratio of the final objective values. Through extensive experiments, we demonstrate the superiority of our proposed method over baseline approaches.

Microscopic examination of slides prepared from tissue samples is the primary tool for detecting and classifying cancerous lesions, a process that is time-consuming and requires the expertise of experienced pathologists. Recent advances in deep learning methods hold significant potential to enhance medical diagnostics and treatment planning by improving accuracy, reproducibility, and speed, thereby reducing clinicians' workloads and turnaround times. However, the necessity for vast amounts of labeled data to train these models remains a major obstacle to the development of effective clinical decision support systems. In this paper, we propose the integration of topological deep learning methods to enhance the accuracy and robustness of existing histopathological image analysis models. Topological data analysis (TDA) offers a unique approach by extracting essential information through the evaluation of topological patterns across different color channels. While deep learning methods capture local information from images, TDA features provide complementary global features. Our experiments on publicly available histopathological datasets demonstrate that the inclusion of topological features significantly improves the differentiation of tumor types in ovarian and breast cancers.

Graph embeddings play a critical role in graph representation learning, allowing machine learning models to explore and interpret graph-structured data. However, existing methods often rely on opaque, high-dimensional embeddings, limiting interpretability and practical visualization. In this work, we introduce Topological Evolution Rate (TopER), a novel, low-dimensional embedding approach grounded in topological data analysis. TopER simplifies a key topological approach, Persistent Homology, by calculating the evolution rate of graph substructures, resulting in intuitive and interpretable visualizations of graph data. This approach not only enhances the exploration of graph datasets but also delivers competitive performance in graph clustering and classification tasks. Our TopER-based models achieve or surpass state-of-the-art results across molecular, biological, and social network datasets in tasks such as classification, clustering, and visualization., Comment: 17 pages, 7 figures

Graph Neural Networks (GNNs) have revolutionized the domain of graph representation learning by utilizing neighborhood aggregation schemes in many popular architectures, such as message passing graph neural networks (MPGNNs). This scheme involves iteratively calculating a node's representation vector by aggregating and transforming the representation vectors of its adjacent nodes. Despite their effectiveness, MPGNNs face significant issues, such as oversquashing, oversmoothing, and underreaching, which hamper their effectiveness. Additionally, the reliance of MPGNNs on the homophily assumption, where edges typically connect nodes with similar labels and features, limits their performance in heterophilic contexts, where connected nodes often have significant differences. This necessitates the development of models that can operate effectively in both homophilic and heterophilic settings. In this paper, we propose a novel approach, ClassContrast, grounded in Energy Landscape Theory from Chemical Physics, to overcome these limitations. ClassContrast combines spatial and contextual information, leveraging a physics-inspired energy landscape to model node embeddings that are both discriminative and robust across homophilic and heterophilic settings. Our approach introduces contrast-based homophily matrices to enhance the understanding of class interactions and tendencies. Through extensive experiments, we demonstrate that ClassContrast outperforms traditional GNNs in node classification and link prediction tasks, proving its effectiveness and versatility in diverse real-world scenarios., Comment: 16 pages, 5 figures

Over the past decade, Graph Neural Networks (GNNs) have transformed graph representation learning. In the widely adopted message-passing GNN framework, nodes refine their representations by aggregating information from neighboring nodes iteratively. While GNNs excel in various domains, recent theoretical studies have raised concerns about their capabilities. GNNs aim to address various graph-related tasks by utilizing such node representations, however, this one-size-fits-all approach proves suboptimal for diverse tasks. Motivated by these observations, we conduct empirical tests to compare the performance of current GNN models with more conventional and direct methods in link prediction tasks. Introducing our model, PROXI, which leverages proximity information of node pairs in both graph and attribute spaces, we find that standard machine learning (ML) models perform competitively, even outperforming cutting-edge GNN models when applied to these proximity metrics derived from node neighborhoods and attributes. This holds true across both homophilic and heterophilic networks, as well as small and large benchmark datasets, including those from the Open Graph Benchmark (OGB). Moreover, we show that augmenting traditional GNNs with PROXI significantly boosts their link prediction performance. Our empirical findings corroborate the previously mentioned theoretical observations and imply that there exists ample room for enhancement in current GNN models to reach their potential.

The growth and ordering of molecules on surfaces is an intriguing research topic as insights gained here can be of significant relevance for organic electronic devices. While often simple, rigid molecules are employed as model systems, we show results for a highly dipolar merocyanine which is studied on top of Au(100), Ag(100) and Cu(100) metal single crystals. Film thicknesses ranging from submonolayer to multilayer regimes are analyzed using UV (UPS) and X ray photoelectron spectroscopy (XPS). For the monolayer regime, there is strong indication of face on orientation, with both of the molecules sulfur atoms bonding to the metal surfaces. Here, on Ag and Au(100) the sulfur atoms lose some or all of their intrinsic charges due to a charge transfer with the substrate, while on Cu(100) a strong metal sulfur bond forms. The interaction between the substrate and the molecules can also be seen in the intensity and width of the highest occupied molecular orbital features in UPS. Upon multilayer deposition, a gradual lowering in ionization energy is observed, likely due to the formation of antiparallel dimers followed by an increased charge carrier delocalization due to the formation of an extended molecular aggregate for thicker layers. Interestingly, on Cu(100) the aggregated phase is already observed for much lower deposition, showing the importance of substrate-molecule interaction on the subsequent film growth. Therefore, this study offers a detailed understanding of the interface formation and electronic structure evolution for merocyanine films on different metal surfaces.

This work presents a novel rehabilitation framework designed for a therapist, wearing an inertial measurement unit (IMU) suit, to virtually interact with a lower-limb exoskeleton worn by a patient with motor impairments. This framework aims to harmonize the skills and knowledge of the therapist with the capabilities of the exoskeleton. The therapist can guide the patient's movements by moving their own joints and making real-time adjustments to meet the patient's needs, while reducing the physical effort of the therapist. This eliminates the need for a predefined trajectory for the patient to follow, as in conventional robotic gait training. For the virtual interaction medium between the therapist and patient, we propose an impedance profile that is stiff at low frequencies and less stiff at high frequencies, that can be tailored to individual patient needs and different stages of rehabilitation. The desired interaction torque from this medium is commanded to a whole-exoskeleton closed-loop compensation controller. The proposed virtual interaction framework was evaluated with a pair of unimpaired individuals in different teacher-student gait training exercises. Results show the proposed interaction control effectively transmits haptic cues, informing future applications in rehabilitation scenarios.

Medical imaging analysis faces challenges such as data scarcity, high annotation costs, and privacy concerns. This paper introduces the Medical AI for Synthetic Imaging (MAISI), an innovative approach using the diffusion model to generate synthetic 3D computed tomography (CT) images to address those challenges. MAISI leverages the foundation volume compression network and the latent diffusion model to produce high-resolution CT images (up to a landmark volume dimension of 512 x 512 x 768 ) with flexible volume dimensions and voxel spacing. By incorporating ControlNet, MAISI can process organ segmentation, including 127 anatomical structures, as additional conditions and enables the generation of accurately annotated synthetic images that can be used for various downstream tasks. Our experiment results show that MAISI's capabilities in generating realistic, anatomically accurate images for diverse regions and conditions reveal its promising potential to mitigate challenges using synthetic data., Comment: WACV25 accepted. https://monai.io/research/maisi

This paper proposes an observer-based formation tracking control approach for multi-vehicle systems with second-order motion dynamics, assuming that vehicles' relative or global position and velocity measurements are unavailable. It is assumed that all vehicles are equipped with sensors capable of sensing the bearings relative to neighboring vehicles and only one leader vehicle has access to its global position. Each vehicle estimates its absolute position and velocity using relative bearing measurements and the estimates of neighboring vehicles received over a communication network. A distributed observer-based controller is designed, relying only on bearing and acceleration measurements. This work further explores the concept of the \textit{Bearing Persistently Exciting} (BPE) formation by proposing new algorithms for bearing-based localization and state estimation of second-order systems in centralized and decentralized manners. It also examines conditions on the desired formation to guarantee the exponential stability of distributed observer-based formation tracking controllers. In support of our theoretical results, some simulation results are presented to illustrate the performance of the proposed observers as well as the observer-based tracking controllers.

In this paper, we investigate the problem of decomposing 2D environments for robot coverage planning. Coverage path planning (CPP) involves computing a cost-minimizing path for a robot equipped with a coverage or sensing tool so that the tool visits all points in the environment. CPP is an NP-Hard problem, so existing approaches simplify the problem by decomposing the environment into the minimum number of sectors. Sectors are sub-regions of the environment that can each be covered using a lawnmower path (i.e., along parallel straight-line paths) oriented at an angle. However, traditional methods either limit the coverage orientations to be axis-parallel (horizontal/vertical) or provide no guarantees on the number of sectors in the decomposition. We introduce an approach to decompose the environment into possibly overlapping rectangular sectors. We provide an approximation guarantee on the number of sectors computed using our approach for a given environment. We do this by leveraging the submodular property of the sector coverage function, which enables us to formulate the decomposition problem as a submodular set cover (SSC) problem with well-known approximation guarantees for the greedy algorithm. Our approach improves upon existing coverage planning methods, as demonstrated through an evaluation using maps of complex real-world environments., Comment: Extended version of the 2024 IEEE CDC paper, 8 pages, 3 figures

Topological Machine Learning (TML) is an emerging field that leverages techniques from algebraic topology to analyze complex data structures in ways that traditional machine learning methods may not capture. This tutorial provides a comprehensive introduction to two key TML techniques, persistent homology and the Mapper algorithm, with an emphasis on practical applications. Persistent homology captures multi-scale topological features such as clusters, loops, and voids, while the Mapper algorithm creates an interpretable graph summarizing high-dimensional data. To enhance accessibility, we adopt a data-centric approach, enabling readers to gain hands-on experience applying these techniques to relevant tasks. We provide step-by-step explanations, implementations, hands-on examples, and case studies to demonstrate how these tools can be applied to real-world problems. The goal is to equip researchers and practitioners with the knowledge and resources to incorporate TML into their work, revealing insights often hidden from conventional machine learning methods. The tutorial code is available at https://github.com/cakcora/TopologyForML, Comment: 54 pages, 35 figures

Air components, including UAVs, planes, balloons, and satellites have been widely utilized since the fixed capacity of ground infrastructure cannot meet the dynamic load of the users. However, since those air components should be coordinated in order to achieve the desired quality of service, several next-generation paradigms have been defined including air computing. Nevertheless, even though many studies and open research issues exist for air computing, there are limited test environments that cannot satisfy the performance evaluation requirements of the dynamic environment. Therefore, in this study, we introduce our discrete event simulator, AirCompSim, which fulfills an air computing environment considering dynamically changing requirements, loads, and capacities through its modular structure. To show its capabilities, a dynamic capacity enhancement scenario is used for investigating the effect of the number of users, UAVs, and requirements of different application types on the average task success rate, service time, and server utilization. The results demonstrate that AirCompSim can be used for experiments in air computing., Comment: 6 pages, 8 figures, 2 tables

Assessing seismic hazards and thereby designing earthquake-resilient structures or evaluating structural damage that has been incurred after an earthquake are important objectives in earthquake engineering. Both tasks require critical evaluation of strong ground motion records, and the knowledge of site conditions at the earthquake stations plays a major role in achieving the aforementioned objectives. Site conditions are generally represented by the time-averaged shear wave velocity in the upper 30 meters of the geological materials (Vs30). Several strong motion stations lack Vs30 measurements resulting in potentially inaccurate assessment of seismic hazards and evaluation of ground motion records. In this study, we present a deep learning-based approach for predicting Vs30 at strong motion station locations using three-channel earthquake records. For this purpose, Convolutional Neural Networks (CNNs) with dilated and causal convolutional layers are used to extract deep features from accelerometer records collected from over 700 stations located in Turkey. In order to overcome the limited availability of labeled data, we propose a two-phase training approach. In the first phase, a CNN is trained to estimate the epicenters, for which ground truth is available for all records. After the CNN is trained, the pre-trained encoder is fine-tuned based on the Vs30 ground truth. The performance of the proposed method is compared with machine learning models that utilize hand-crafted features. The results demonstrate that the deep convolutional encoder based Vs30 prediction model outperforms the machine learning models that rely on hand-crafted features., Comment: 12 pages, 14 figures, Accepted by 18th World Conference on Earthquake Engineering WCEE2024

The increasing usage of Large Language Models (LLMs) has resulted in a surging demand for planet-scale serving systems, where tens of thousands of GPUs continuously serve hundreds of millions of users. Consequently, throughput (under reasonable latency constraints) has emerged as a key metric that determines serving systems' performance. To boost throughput, various methods of inter-device parallelism (e.g., data, tensor, pipeline) have been explored. However, existing methods do not consider overlapping the utilization of different resources within a single device, leading to underutilization and sub-optimal performance. We propose NanoFlow, a novel serving framework that exploits intra-device parallelism, which overlaps the usage of resources including compute, memory, and network within a single device through operation co-scheduling. To exploit intra-device parallelism, NanoFlow introduces two key innovations: First, NanoFlow splits requests into nano-batches at the granularity of operations, which breaks the dependency of sequential operations in LLM inference and enables overlapping; then, to get benefit from overlapping, NanoFlow uses an operation-level pipeline with execution unit scheduling, which partitions the device's functional units and simultaneously executes different operations in each unit. NanoFlow automates the pipeline setup using a parameter search algorithm, which enables easily porting NanoFlow to different models. We implement NanoFlow on NVIDIA GPUs and evaluate end-to-end serving throughput on several popular models such as LLaMA-2-70B, Mixtral 8x7B, LLaMA-3-8B, etc.. With practical workloads, NanoFlow provides 1.91x throughput boost compared to state-of-the-art serving systems achieving 59% to 72% of optimal throughput across ported models.

By coupling a semiconductor-based planar Josephson junction to a superconducting resonator, we investigate the Andreev bound states in the junction using dispersive readout techniques. Using electrostatic gating to create a narrow constriction in the junction, our measurements unveil a strong coupling interaction between the resonator and the Andreev bound states. This enables the mapping of isolated tunable Andreev bound states, with an observed transparency of up to 99.94\% along with an average induced superconducting gap of $\sim 150 \mu$eV. Exploring the gate parameter space further elucidates a non-monotonic evolution of multiple Andreev bound states with varying gate voltage. Complimentary tight-binding calculations of an Al-InAs planar Josephson junction with strong Rashba spin-orbit coupling provide insight into possible mechanisms responsible for such behavior. Our findings highlight the subtleties of the Andreev spectrum of Josephson junctions fabricated on superconductor-semiconductor heterostructures and offering potential applications in probing topological states in these hybrid platforms.

Exoskeletons can boost human strength and provide assistance to individuals with physical disabilities. However, ensuring safety and optimal performance in their design poses substantial challenges. This study presents the design process for an underactuated hand exoskeleton (U-HEx), first including a single objective (maximizing force transmission), then expanding into multi objective (also minimizing torque variance and actuator displacement). The optimization relies on a Genetic Algorithm, the Big Bang-Big Crunch Algorithm, and their versions for multi-objective optimization. Analyses revealed that using Big Bang-Big Crunch provides high and more consistent results in terms of optimality with lower convergence time. In addition, adding more objectives offers a variety of trade-off solutions to the designers, who might later set priorities for the objectives without repeating the process - at the cost of complicating the optimization algorithm and computational burden. These findings underline the importance of performing proper optimization while designing exoskeletons, as well as providing a significant improvement to this specific robotic design., Comment: 12 pages, 7 figures, 8 talbes, submitted to IEEE Transactions on Robotics

The purpose of this paper is to analyze the degree index and clustering index in random graphs. The degree index in our setup is a certain measure of degree irregularity whose basic properties are well studied in the literature, and the corresponding theoretical analysis in a random graph setup turns out to be tractable. On the other hand, the clustering index, based on a similar reasoning, is first introduced in this manuscript. Computing exact expressions for the expected clustering index turns out to be more challenging even in the case of Erd\H{o}s-R\'enyi graphs, and our results are on obtaining relevant upper bounds. These are also complemented with observations based on Monte Carlo simulations. Besides the Erd\H{o}s-R\'enyi case, we also do simulation-based analysis for random regular graphs, the Barab\'asi-Albert model and the Watts-Strogatz model., Comment: 21 pages, 6 figures

The deployment of unmanned aerial vehicles (UAVs) in many different settings has provided various solutions and strategies for networking paradigms. Therefore, it reduces the complexity of the developments for the existing problems, which otherwise require more sophisticated approaches. One of those existing problems is the unknown user locations in an infrastructure-less environment in which users cannot connect to any communication device or computation-providing server, which is essential to task offloading in order to achieve the required quality of service (QoS). Therefore, in this study, we investigate this problem thoroughly and propose a novel deep reinforcement learning (DRL) based scheme, DeepAir. DeepAir considers all of the necessary steps including sensing, localization, resource allocation, and multi-access edge computing (MEC) to achieve QoS requirements for the offloaded tasks without violating the maximum tolerable delay. To this end, we use two types of UAVs including detector UAVs, and serving UAVs. We utilize detector UAVs as DRL agents which ensure sensing, localization, and resource allocation. On the other hand, we utilize serving UAVs to provide MEC features. Our experiments show that DeepAir provides a high task success rate by deploying fewer detector UAVs in the environment, which includes different numbers of users and user attraction points, compared to benchmark methods., Comment: 12 pages, 8 figures, 5 tables

Placenta volume measured from 3D ultrasound (3DUS) images is an important tool for tracking the growth trajectory and is associated with pregnancy outcomes. Manual segmentation is the gold standard, but it is time-consuming and subjective. Although fully automated deep learning algorithms perform well, they do not always yield high-quality results for each case. Interactive segmentation models could address this issue. However, there is limited work on interactive segmentation models for the placenta. Despite their segmentation accuracy, these methods may not be feasible for clinical use as they require relatively large computational power which may be especially prohibitive in low-resource environments, or on mobile devices. In this paper, we propose a lightweight interactive segmentation model aiming for clinical use to interactively segment the placenta from 3DUS images in real-time. The proposed model adopts the segmentation from our fully automated model for initialization and is designed in a human-in-the-loop manner to achieve iterative improvements. The Dice score and normalized surface Dice are used as evaluation metrics. The results show that our model can achieve superior performance in segmentation compared to state-of-the-art models while using significantly fewer parameters. Additionally, the proposed model is much faster for inference and robust to poor initial masks. The code is available at https://github.com/MedICL-VU/PRISM-placenta.

Planar Josephson junctions provide a platform to host topological superconductivity which, through manipulating Majorana bound states (MBS), could enable fault-tolerant quantum computing. However, what constitutes experimental signatures of topological superconductivity and how MBS can be detected remains strongly debated. In addition to spurious effects that mimic MBS, there is a challenge to discern the inherent topological signals in realistic systems with many topologically-trivial Andreev bound states, determining the transport properties of Josephson junctions. Guided by the advances in microwave spectroscopy, we theoretically study Al/InAs-based planar Josephson junction embedded into a radio-frequency superconducting quantum interference device to identify microwave signatures of topological superconductivity. Remarkably, by exploring the closing and reopening of a topological gap, we show that even in a wide planar Josephson junction with many Andreev bound states, such a topological signature is distinguishable in the resonance frequency shift of a microwave drive and the ``half-slope'' feature of the microwave absorption spectrum. Our findings provide an important step towards experimental detection of non-Abelian statistics and implementing scalable topological quantum computing.

Ranking-based loss functions, such as Average Precision Loss and Rank&Sort Loss, outperform widely used score-based losses in object detection. These loss functions better align with the evaluation criteria, have fewer hyperparameters, and offer robustness against the imbalance between positive and negative classes. However, they require pairwise comparisons among $P$ positive and $N$ negative predictions, introducing a time complexity of $\mathcal{O}(PN)$, which is prohibitive since $N$ is often large (e.g., $10^8$ in ATSS). Despite their advantages, the widespread adoption of ranking-based losses has been hindered by their high time and space complexities. In this paper, we focus on improving the efficiency of ranking-based loss functions. To this end, we propose Bucketed Ranking-based Losses which group negative predictions into $B$ buckets ($B \ll N$) in order to reduce the number of pairwise comparisons so that time complexity can be reduced. Our method enhances the time complexity, reducing it to $\mathcal{O}(\max (N \log(N), P^2))$. To validate our method and show its generality, we conducted experiments on 2 different tasks, 3 different datasets, 7 different detectors. We show that Bucketed Ranking-based (BR) Losses yield the same accuracy with the unbucketed versions and provide $2\times$ faster training on average. We also train, for the first time, transformer-based object detectors using ranking-based losses, thanks to the efficiency of our BR. When we train CoDETR, a state-of-the-art transformer-based object detector, using our BR Loss, we consistently outperform its original results over several different backbones. Code is available at https://github.com/blisgard/BucketedRankingBasedLosses, Comment: to appear in ECCV 2024

In this paper we introduce Sampling with a Black Box, a generic technique for the design of parameterized approximation algorithms for vertex deletion problems (e.g., Vertex Cover, Feedback Vertex Set, etc.). The technique relies on two components: $\bullet$ A Sampling Step. A polynomial time randomized algorithm which given a graph $G$ returns a random vertex $v$ such that the optimum of $G\setminus \{v\}$ is smaller by $1$ than the optimum of $G$ with some prescribed probability $q$. We show such algorithms exists for multiple vertex deletion problems. $\bullet$ A Black Box algorithm which is either an exact parameterized algorithm or a polynomial time approximation algorithm. Our technique combines these two components together. The sampling step is applied iteratively to remove vertices from the input graph, and then the solution is extended using the black box algorithm. The process is repeated sufficiently many times so that the target approximation ratio is attained with a constant probability. The main novelty of our work lies in the analysis of the framework and the optimization of the parameters it uses. We use the technique to derive parameterized approximation algorithm for several vertex deletion problems, including Feedback Vertex Set, $d$-Hitting Set and $\ell$-Path Vertex Cover. In particular, for every approximation ratio $1<\beta<2$, we attain a parameterized $\beta$-approximation for Feedback Vertex Set which is faster than the parameterized $\beta$-approximation of [Jana, Lokshtanov, Mandal, Rai and Saurabh, MFCS 23']. Furthermore, our algorithms are always faster than the algorithms attained using Fidelity Preserving Transformations [Fellows, Kulik, Rosamond, and Shachnai, JCSS 18'].

Placenta volume measurement from 3D ultrasound images is critical for predicting pregnancy outcomes, and manual annotation is the gold standard. However, such manual annotation is expensive and time-consuming. Automated segmentation algorithms can often successfully segment the placenta, but these methods may not consistently produce robust segmentations suitable for practical use. Recently, inspired by the Segment Anything Model (SAM), deep learning-based interactive segmentation models have been widely applied in the medical imaging domain. These models produce a segmentation from visual prompts provided to indicate the target region, which may offer a feasible solution for practical use. However, none of these models are specifically designed for interactively segmenting 3D ultrasound images, which remain challenging due to the inherent noise of this modality. In this paper, we evaluate publicly available state-of-the-art 3D interactive segmentation models in contrast to a human-in-the-loop approach for the placenta segmentation task. The Dice score, normalized surface Dice, averaged symmetric surface distance, and 95-percent Hausdorff distance are used as evaluation metrics. We consider a Dice score of 0.95 a successful segmentation. Our results indicate that the human-in-the-loop segmentation model reaches this standard. Moreover, we assess the efficiency of the human-in-the-loop model as a function of the amount of prompts. Our results demonstrate that the human-in-the-loop model is both effective and efficient for interactive placenta segmentation. The code is available at \url{https://github.com/MedICL-VU/PRISM-placenta}.

Sensor network localization (SNL) is a challenging problem due to its inherent non-convexity and the effects of noise in inter-node ranging measurements and anchor node position. We formulate a non-convex SNL problem as a multi-player non-convex potential game and investigate the existence and uniqueness of a Nash equilibrium (NE) in both the ideal setting without measurement noise and the practical setting with measurement noise. We first show that the NE exists and is unique in the noiseless case, and corresponds to the precise network localization. Then, we study the SNL for the case with errors affecting the anchor node position and the inter-node distance measurements. Specifically, we establish that in case these errors are sufficiently small, the NE exists and is unique. It is shown that the NE is an approximate solution to the SNL problem, and that the position errors can be quantified accordingly. Based on these findings, we apply the results to case studies involving only inter-node distance measurement errors and only anchor position information inaccuracies., Comment: arXiv admin note: text overlap with arXiv:2311.03326, arXiv:2401.02471

Open-loop control of laser powder bed fusion (LPBF) additive manufacturing (AM) has enabled the production of complex, high-criticality parts for various industries. This method relies on static parameter sets from extensive experimentation and simulations, hoping they remain stable and defect-free in production. Closed-loop control of LPBF can further enhance process stability and reduce defects despite complex thermal histories, process noise, hardware drift, and unexpected perturbations. Controller performance depends on parameter tuning, traditionally a manual, expertise-driven process with no guarantee of optimal performance and limited transferability between systems. This study proposes Bayesian Optimization (BO) to automate in-layer controller tuning by leveraging LPBF's layer-to-layer repetitive nature. Two approaches are introduced: online tuning, adjusting parameters iteratively during the process, and offline tuning, conducted in a setup such as laser exposures on a bare metal plate. These methods are experimentally implemented on an in-layer PI controller, and the performance is investigated on two wedge geometries prone to overheating. Results show that BO effectively tunes controllers using either method, significantly reducing overheating in controlled wedge specimens compared to uncontrolled ones. This study presents the first printed parts controlled by an in-layer controller subjected to microstructural analysis. Findings reveal partial presence of lack-of-fusion porosities due to insufficient laser power assigned by the controller, highlighting a significant challenge for utilizing laser power controllers. In summary, BO presents a promising method for automatic in-layer controller tuning in LPBF, enhancing control precision and mitigating overheating in production parts.

This paper presents a review of the NTIRE 2024 challenge on night photography rendering. The goal of the challenge was to find solutions that process raw camera images taken in nighttime conditions, and thereby produce a photo-quality output images in the standard RGB (sRGB) space. Unlike the previous year's competition, the challenge images were collected with a mobile phone and the speed of algorithms was also measured alongside the quality of their output. To evaluate the results, a sufficient number of viewers were asked to assess the visual quality of the proposed solutions, considering the subjective nature of the task. There were 2 nominations: quality and efficiency. Top 5 solutions in terms of output quality were sorted by evaluation time (see Fig. 1). The top ranking participants' solutions effectively represent the state-of-the-art in nighttime photography rendering. More results can be found at https://nightimaging.org., Comment: 10 pages, 10 figures

Prostate cancer is one of the most prevalent malignancies in the world. While deep learning has potential to further improve computer-aided prostate cancer detection on MRI, its efficacy hinges on the exhaustive curation of manually annotated images. We propose a novel methodology of semisupervised learning (SSL) guided by automatically extracted clinical information, specifically the lesion locations in radiology reports, allowing for use of unannotated images to reduce the annotation burden. By leveraging lesion locations, we refined pseudo labels, which were then used to train our location-based SSL model. We show that our SSL method can improve prostate lesion detection by utilizing unannotated images, with more substantial impacts being observed when larger proportions of unannotated images are used., Comment: 4 page paper accepted to IEEE International Symposium on Biomedical Imaging (ISBI 2024)

As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed decreases significantly as the sequence length grows. This slowdown is primarily caused by loading a large KV cache during self-attention. Previous works have shown that a small portion of critical tokens will dominate the attention outcomes. However, we observe the criticality of a token highly depends on the query. To this end, we propose Quest, a query-aware KV cache selection algorithm. Quest keeps track of the minimal and maximal Key values in KV cache pages and estimates the criticality of a given page using Query vectors. By only loading the Top-K critical KV cache pages for attention, Quest significantly speeds up self-attention without sacrificing accuracy. We show that Quest can achieve up to 2.23x self-attention speedup, which reduces inference latency by 7.03x while performing well on tasks with long dependencies with negligible accuracy loss. Code is available at http://github.com/mit-han-lab/Quest ., Comment: ICML 2024

The field of temporal graph learning aims to learn from evolving network data to forecast future interactions. Given a collection of observed temporal graphs, is it possible to predict the evolution of an unseen network from the same domain? To answer this question, we first present the Temporal Graph Scaling (TGS) dataset, a large collection of temporal graphs consisting of eighty-four ERC20 token transaction networks collected from 2017 to 2023. Next, we evaluate the transferability of Temporal Graph Neural Networks (TGNNs) for the temporal graph property prediction task by pre-training on a collection of up to sixty-four token transaction networks and then evaluating the downstream performance on twenty unseen token networks. We find that the neural scaling law observed in NLP and Computer Vision also applies in temporal graph learning, where pre-training on greater number of networks leads to improved downstream performance. To the best of our knowledge, this is the first empirical demonstration of the transferability of temporal graphs learning. On downstream token networks, the largest pre-trained model outperforms single model TGNNs on thirteen unseen test networks. Therefore, we believe that this is a promising first step towards building foundation models for temporal graphs., Comment: 17 pages, 15 figures, preprint version

A planar Josephson junction is a versatile platform to realize topological superconductivity over a large parameter space and host Majorana bound states. With a change in Zeeman field, this system undergoes a transition from trivial to topological superconductivity accompanied by a jump in the superconducting phase difference between the two superconductors. A standard model of these Josephson junctions, which can be fabricated to have a nearly perfect interfacial transparency, predicts a simple universal behavior. In that model, at the same value of Zeeman field for the topological transition, there is a $\pi$ phase jump and a minimum in the critical superconducting current, while applying a controllable phase difference yields a diamond-shaped topological region as a function of that phase difference and a Zeeman field. In contrast, even for a perfect interfacial transparency, we find a much richer and nonuniversal behavior as the width of the superconductor is varied or the Dresselhaus spin-orbit coupling is considered. The Zeeman field for the phase jump, not necessarily $\pi$, is different from the value for the minimum critical current, while there is a strong deviation from the diamond-like topological region. These Josephson junctions show a striking example of a nonreciprocal transport and superconducting diode effect, revealing the importance of our findings not only for topological superconductivity and fault-tolerant quantum computing, but also for superconducting spintronics., Comment: Invited to APL Special Topic Issue: "Josephson Junctions and Related Proximity Effects: From Basic Science to Emerging Applications in Advanced Technologies", accepted version

Medical image segmentation is a core component of precision medicine, and 3D computed tomography (CT) is one of the most important imaging techniques. A highly accurate and clinically applicable segmentation foundation model will greatly facilitate clinicians and researchers using CT images. Although existing foundation models have attracted great interest, none are adequate for 3D CT, either because they lack accurate automatic segmentation for large cohort analysis or the ability to segment novel classes. An ideal segmentation solution should possess two features: accurate out-of-the-box performance covering major organ classes, and effective adaptation or zero-shot ability to novel structures. To achieve this goal, we introduce Versatile Imaging SegmenTation and Annotation model (VISTA3D). VISTA3D is trained systematically on 11454 volumes and provides accurate out-of-the-box segmentation for 127 common types of human anatomical structures and various lesions. Additionally, VISTA3D supports 3D interactive segmentation, allowing convenient editing of automatic results and achieving state-of-the-art annotation results on unseen classes. The novel model design and training recipe represent a promising step toward developing a versatile medical image foundation model and will serve as a valuable foundation for CT image analysis. Code and model weights are available at https://github.com/Project-MONAI/VISTA

Federated Learning (FL) enables edge devices or clients to collaboratively train machine learning (ML) models without sharing their private data. Much of the existing work in FL focuses on efficiently learning a model for a single task. In this paper, we study simultaneous training of multiple FL models using a common set of clients. The few existing simultaneous training methods employ synchronous aggregation of client updates, which can cause significant delays because large models and/or slow clients can bottleneck the aggregation. On the other hand, a naive asynchronous aggregation is adversely affected by stale client updates. We propose FedAST, a buffered asynchronous federated simultaneous training algorithm that overcomes bottlenecks from slow models and adaptively allocates client resources across heterogeneous tasks. We provide theoretical convergence guarantees for FedAST for smooth non-convex objective functions. Extensive experiments over multiple real-world datasets demonstrate that our proposed method outperforms existing simultaneous FL approaches, achieving up to 46.0% reduction in time to train multiple tasks to completion., Comment: Accepted to UAI 2024

This paper explores the application of deep learning (DL) techniques to strong motion records for single-station epicenter localization. Often underutilized in seismology-related studies, strong motion records offer a potential wealth of information about seismic events. We investigate whether DL-based methods can effectively leverage this data for accurate epicenter localization. Our study introduces AFAD-1218, a collection comprising more than 36,000 strong motion records sourced from Turkey. To utilize the strong motion records represented in either the time or the frequency domain, we propose two neural network architectures: deep residual network and temporal convolutional networks. Through extensive experimentation, we demonstrate the efficacy of DL approaches in extracting meaningful insights from these records, showcasing their potential for enhancing seismic event analysis and localization accuracy. Notably, our findings highlight significant reductions in prediction error achieved through the exclusion of low signal-to-noise ratio records, both in nationwide experiments and regional transfer-learning scenarios. Overall, this research underscores the promise of DL techniques in harnessing strong motion records for improved seismic event characterization and localization.

Federated learning (FL) aims to collaboratively learn deep learning model parameters from decentralized data archives (i.e., clients) without accessing training data on clients. However, the training data across clients might be not independent and identically distributed (non-IID), which may result in difficulty in achieving optimal model convergence. In this work, we investigate the capability of state-of-the-art transformer architectures (which are MLP-Mixer, ConvMixer, PoolFormer) to address the challenges related to non-IID training data across various clients in the context of FL for multi-label classification (MLC) problems in remote sensing (RS). The considered transformer architectures are compared among themselves and with the ResNet-50 architecture in terms of their: 1) robustness to training data heterogeneity; 2) local training complexity; and 3) aggregation complexity under different non-IID levels. The experimental results obtained on the BigEarthNet-S2 benchmark archive demonstrate that the considered architectures increase the generalization ability with the cost of higher local training and aggregation complexities. On the basis of our analysis, some guidelines are derived for a proper selection of transformer architecture in the context of FL for RS MLC. The code of this work is publicly available at https://git.tu-berlin.de/rsim/FL-Transformer., Comment: Accepted at IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2024. Our code is available at https://git.tu-berlin.de/rsim/FL-Transformer

Automated volumetric segmentation of the pancreas on cross-sectional imaging is needed for diagnosis and follow-up of pancreatic diseases. While CT-based pancreatic segmentation is more established, MRI-based segmentation methods are understudied, largely due to a lack of publicly available datasets, benchmarking research efforts, and domain-specific deep learning methods. In this retrospective study, we collected a large dataset (767 scans from 499 participants) of T1-weighted (T1W) and T2-weighted (T2W) abdominal MRI series from five centers between March 2004 and November 2022. We also collected CT scans of 1,350 patients from publicly available sources for benchmarking purposes. We developed a new pancreas segmentation method, called PanSegNet, combining the strengths of nnUNet and a Transformer network with a new linear attention module enabling volumetric computation. We tested PanSegNet's accuracy in cross-modality (a total of 2,117 scans) and cross-center settings with Dice and Hausdorff distance (HD95) evaluation metrics. We used Cohen's kappa statistics for intra and inter-rater agreement evaluation and paired t-tests for volume and Dice comparisons, respectively. For segmentation accuracy, we achieved Dice coefficients of 88.3% (std: 7.2%, at case level) with CT, 85.0% (std: 7.9%) with T1W MRI, and 86.3% (std: 6.4%) with T2W MRI. There was a high correlation for pancreas volume prediction with R^2 of 0.91, 0.84, and 0.85 for CT, T1W, and T2W, respectively. We found moderate inter-observer (0.624 and 0.638 for T1W and T2W MRI, respectively) and high intra-observer agreement scores. All MRI data is made available at https://osf.io/kysnj/. Our source code is available at https://github.com/NUBagciLab/PaNSegNet., Comment: Peer-reviewer version

The largest direct dark matter search experiments to date employ dual-phase time projection chambers (TPCs) with liquid noble gas targets. These detect both the primary photons generated by particle interactions in the liquid target, as well as proportional secondary scintillation light created by the ionization electrons in a strong electric field in the gas phase between the liquid-gas interface and the anode. In this work, we describe the detection of charge signals in a small-scale single-phase liquid-xenon-only TPC, that features the well-established TPC geometry with light readout above and below a cylindrical target. In the single-phase TPC, the proportional scintillation light (S2) is generated in liquid xenon in close proximity to 10 {\mu}m diameter anode wires. The detector was characterized and the proportional scintillation process was studied using the 32.1 keV and 9.4 keV signals from 83mKr decays. A charge gain factor g2 of up to (1.9 $\pm$ 0.3) PE/electron was reached at an anode voltage 4.4 kV higher than the gate electrode 5 mm below it, corresponding to (29 $\pm$ 6) photons emitted per ionization electron. The duration of S2 signals is dominated by electron diffusion and approaches the xenon de-excitation timescale for very short electron drift times. The electron drift velocity and the longitudinal diffusion constant were measured at a drift field of 470 V/cm. The results agree with the literature and demonstrate that a single-phase TPC can be operated successfully., Comment: 20 pages, 14 figures

Identifying peri-pancreatic edema is a pivotal indicator for identifying disease progression and prognosis, emphasizing the critical need for accurate detection and assessment in pancreatitis diagnosis and management. This study \textit{introduces a novel CT dataset sourced from 255 patients with pancreatic diseases, featuring annotated pancreas segmentation masks and corresponding diagnostic labels for peri-pancreatic edema condition}. With the novel dataset, we first evaluate the efficacy of the \textit{LinTransUNet} model, a linear Transformer based segmentation algorithm, to segment the pancreas accurately from CT imaging data. Then, we use segmented pancreas regions with two distinctive machine learning classifiers to identify existence of peri-pancreatic edema: deep learning-based models and a radiomics-based eXtreme Gradient Boosting (XGBoost). The LinTransUNet achieved promising results, with a dice coefficient of 80.85\%, and mIoU of 68.73\%. Among the nine benchmarked classification models for peri-pancreatic edema detection, \textit{Swin-Tiny} transformer model demonstrated the highest recall of $98.85 \pm 0.42$ and precision of $98.38\pm 0.17$. Comparatively, the radiomics-based XGBoost model achieved an accuracy of $79.61\pm4.04$ and recall of $91.05\pm3.28$, showcasing its potential as a supplementary diagnostic tool given its rapid processing speed and reduced training time. Our code is available \url{https://github.com/NUBagciLab/Peri-Pancreatic-Edema-Detection}.

This study introduces a novel approach to enhance communication networks in the cislunar space by leveraging Reconfigurable Intelligent Surfaces (RIS). Using the ability of RIS to dynamically control electromagnetic waves, this paper tackles the challenges of signal attenuation, directivity, and divergence in cislunar missions, primarily caused by immense distances and that Earth-based station transmitters do not always face the Moon. A new optimization problem is formulated, whose objective is to maximize the received signal-to-noise ratio (SNR) for Earth-to-Moon communications. We derive a closed-form solution to the problem of determining the optimal RIS phase shift configuration based on the effective area of the RIS. Through extensive simulations, this paper demonstrates how optimal adjustments in RIS phase shifts can significantly enhance signal integrity, hinting at the substantial potential of RIS technology to revolutionize long-distance cislunar communication., Comment: The submission includes 6 pages in double-column format, with 6 figures, and has been submitted to the IEEE Globecom 2024 conference