Search

This article presents the Labeled Random Finite Set (LRFS) framework for multi-object systems-systems in which the number of objects and their states are unknown and vary randomly with time. In particular, we focus on state and trajectory estimation via a multi-object State Space Model (SSM) that admits principled tractable multi-object tracking filters/smoothers. Unlike the single-object counterpart, a time sequence of states does not necessarily represent the trajectory of a multi-object system. The LRFS formulation enables a time sequence of multi-object states to represent the multi-object trajectory that accommodates trajectory crossings and fragmentations. We present the basics of LRFS, covering a suite of commonly used models and mathematical apparatus (including the latest results not published elsewhere). Building on this, we outline the fundamentals of multi-object state space modeling and estimation using LRFS, which formally address object identities/trajectories, ancestries for spawning objects, and characterization of the uncertainty on the ensemble of objects (and their trajectories). Numerical solutions to multi-object SSM problems are inherently far more challenging than those in standard SSM. To bridge the gap between theory and practice, we discuss state-of-the-art implementations that address key computational bottlenecks in the number of objects, measurements, sensors, and scans., Comment: To appear in IEEE Transactions on Signal Processing

Haptic feedback is essential for dexterous telemanipulation that enables operators to control robotic hands remotely with high skill and precision, mimicking a human hand's natural movement and sensation. However, current haptic methods for dexterous telemanipulation cannot support torque feedback, resulting in object rotation and rolling mismatches. The operator must make tedious adjustments in these tasks, leading to delays, reduced situational awareness, and suboptimal task performance. This work presents a Bi-directional Momentum-based Haptic Feedback and Control (Bi-Hap) system for real-time dexterous telemanipulation. Bi-Hap integrates multi-modal sensors to extract human interactive information with the object and share it with the robot's learning-based controller. A Field-Oriented Control (FOC) algorithm is developed to enable the integrated brushless active momentum wheel to generate precise torque and vibrative feedback, bridging the gap between human intent and robotic actions. Different feedback strategies are designed for varying error states to align with the operator's intuition. Extensive experiments with human subjects using a virtual Shadow Dexterous Hand demonstrate the effectiveness of Bi-Hap in enhancing task performance and user confidence. Bi-Hap achieved real-time feedback capability with low command following latency (delay<0.025s) and highly accurate torque feedback (RMSE<0.010 Nm)., Comment: 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

In the modern era of rapidly increasing data volumes, accurately retrieving and recommending relevant documents has become crucial in enhancing the reliability of Question Answering (QA) systems. Recently, Retrieval Augmented Generation (RAG) has gained significant recognition for enhancing the capabilities of large language models (LLMs) by mitigating hallucination issues in QA systems, which is particularly beneficial in the legal domain. Various methods, such as semantic search using dense vector embeddings or a combination of multiple techniques to improve results before feeding them to LLMs, have been proposed. However, these methods often fall short when applied to the Vietnamese language due to several challenges, namely inefficient Vietnamese data processing leading to excessive token length or overly simplistic ensemble techniques that lead to instability and limited improvement. Moreover, a critical issue often overlooked is the ordering of final relevant documents which are used as reference to ensure the accuracy of the answers provided by LLMs. In this report, we introduce our three main modifications taken to address these challenges. First, we explore various practical approaches to data processing to overcome the limitations of the embedding model. Additionally, we enhance Reciprocal Rank Fusion by normalizing order to combine results from keyword and vector searches effectively. We also meticulously re-rank the source pieces of information used by LLMs with Active Retrieval to improve user experience when refining the information generated. In our opinion, this technique can also be considered as a new re-ranking method that might be used in place of the traditional cross encoder. Finally, we integrate these techniques into a comprehensive QA system, significantly improving its performance and reliability, Comment: 7 pages

Modern web services adopt cloud-native principles to leverage the advantages of microservices. To consistently guarantee high Quality of Service (QoS) according to Service Level Agreements (SLAs), ensure satisfactory user experiences, and minimize operational costs, each microservice must be provisioned with the right amount of resources. However, accurately provisioning microservices with adequate resources is complex and depends on many factors, including workload intensity and the complex interconnections between microservices. To address this challenge, we develop a model that captures the relationship between an end-to-end latency, requests at the front-end level, and resource utilization. We then use the developed model to predict the end-to-end latency. Our solution leverages the Temporal Fusion Transformer (TFT), an attention-based architecture equipped with interpretability features. When the prediction results indicate SLA non-compliance, we use the feature importance provided by the TFT as covariates in Kernel Ridge Regression (KRR), with the response variable being the desired latency, to learn the parameters associated with the feature importance. These learned parameters reflect the adjustments required to the features to ensure SLA compliance. We demonstrate the merit of our approach with a microservice-based application and provide a roadmap to deployment., Comment: 14 pages, 5 figures

The rapid development and dynamic nature of large language models (LLMs) make it difficult for conventional quantitative benchmarks to accurately assess their capabilities. We propose report cards, which are human-interpretable, natural language summaries of model behavior for specific skills or topics. We develop a framework to evaluate report cards based on three criteria: specificity (ability to distinguish between models), faithfulness (accurate representation of model capabilities), and interpretability (clarity and relevance to humans). We also propose an iterative algorithm for generating report cards without human supervision and explore its efficacy by ablating various design choices. Through experimentation with popular LLMs, we demonstrate that report cards provide insights beyond traditional benchmarks and can help address the need for a more interpretable and holistic evaluation of LLMs., Comment: 11 pages, 8 figures

We conduct a numerical investigation into wave propagation and localization in one-dimensional lattices subject to nonlinear disorder, focusing on cases with fixed input conditions. Utilizing a discrete nonlinear Schr\"odinger equation with Kerr-type nonlinearity and a random coefficient, we compute the averages and variances of the transmittance, $T$, and its logarithm, as functions of the system size $L$, while maintaining constant intensity for the incident wave. In cases of purely nonlinear disorder, we observe power-law localization characterized by $\langle T \rangle \propto L^{-\gamma_a}$ and $\langle \ln T \rangle \approx -\gamma_g \ln L$ for sufficiently large $L$. At low input intensities, a transition from exponential to power-law decay in $\langle T \rangle$ occurs as $L$ increases. The exponents $\gamma_a$ and $\gamma_g$ are nearly identical, converging to approximately 0.5 as the strength of the nonlinear disorder, $\beta$, increases. Additionally, the variance of $T$ decays according to a power law with an exponent close to 1, and the variance of $\ln T$ approaches a small constant as $L$ increases. These findings are consistent with an underlying log-normal distribution of $T$ and suggest that wave propagation behavior becomes nearly deterministic as the system size increases. When both linear and nonlinear disorders are present, we observe a transition from power-law to exponential decay in transmittance with increasing $L$ when the strength of linear disorder, $V$, is less than $\beta$. As $V$ increases, the region exhibiting power-law localization diminishes and eventually disappears when $V$ exceeds $\beta$, leading to standard Anderson localization., Comment: 8 pages, 7 figures

The paper provides a thorough comparison between R-continuity and other fundamental tools in optimization such as metric regularity, metric subregularity and calmness. We show that R-continuity has some advantages in the convergence rate analysis of algorithms solving optimization problems. We also present some properties of R-continuity and study the explicit convergence rate of the Proximal Point Algorithm (PPA) under the R-continuity.

In database systems, a query plan is a series of concrete internal steps to execute a query. Multiple testing approaches utilize query plans for finding bugs. However, query plans are represented in a database-specific manner, so implementing these testing approaches requires a non-trivial effort, hindering their adoption. We envision that a unified query plan representation can facilitate the implementation of these approaches. In this paper, we present an exploratory case study to investigate query plan representations in nine widely-used database systems. Our study shows that query plan representations consist of three conceptual components: operations, properties, and formats, which enable us to design a unified query plan representation. Based on it, existing testing methods can be efficiently adopted, finding 17 previously unknown and unique bugs. Additionally, the unified query plan representation can facilitate other applications. Existing visualization tools can support multiple database systems based on the unified query plan representation with moderate implementation effort, and comparing unified query plans across database systems provides actionable insights to improve their performance. We expect that the unified query plan representation will enable the exploration of additional application scenarios.

In this paper, we propose a novel encoder-decoder architecture, named SABER, to learn the 6D pose of the object in the embedding space by learning shape representation at a given pose. This model enables us to learn pose by performing shape representation at a target pose from RGB image input. We perform shape representation as an auxiliary task which helps us in learning rotations space for an object based on 2D images. An image encoder predicts the rotation in the embedding space and the DeepSDF based decoder learns to represent the object's shape at the given pose. As our approach is shape based, the pipeline is suitable for any type of object irrespective of the symmetry. Moreover, we need only a CAD model of the objects to train SABER. Our pipeline is synthetic data based and can also handle symmetric objects without symmetry labels and, thus, no additional labeled training data is needed. The experimental evaluation shows that our method achieves close to benchmark results for both symmetric objects and asymmetric objects on Occlusion-LineMOD, and T-LESS datasets., Comment: ECCV 2024 R6D workshop

Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they potentially are. Recent studies have shown that DMs are prone to a wide range of attacks, including adversarial attacks, membership inference, backdoor injection, and various multi-modal threats. Since numerous pre-trained DMs are published widely on the Internet, potential threats from these attacks are especially detrimental to the society, making DM-related security a worth investigating topic. Therefore, in this paper, we conduct a comprehensive survey on the security aspect of DMs, focusing on various attack and defense methods for DMs. First, we present crucial knowledge of DMs with five main types of DMs, including denoising diffusion probabilistic models, denoising diffusion implicit models, noise conditioned score networks, stochastic differential equations, and multi-modal conditional DMs. We further survey a variety of recent studies investigating different types of attacks that exploit the vulnerabilities of DMs. Then, we thoroughly review potential countermeasures to mitigate each of the presented threats. Finally, we discuss open challenges of DM-related security and envision certain research directions for this topic.

We study the competitive facility location problem, where a firm aims to establish new facilities in a market already occupied by competitors. In this problem, customer behavior is crucial for making optimal location decisions. We explore a general class of customer choice models, known as the cross-nested logit (CNL) model, which is recognized for its flexibility and generality in predicting people's choice behavior. To explore the problem, we first demonstrate that it is NP-hard, even when there is only one customer class. We further show that this hardness result is tight, as the facility location problem under any simpler choice models (such as the logit or nested logit) is polynomial-time solvable when there is one customer class. To tackle the resulting facility location problem, we demonstrate that the objective function under a general cross-nested structure is not concave. Interestingly, we show that by a change of variables, the objective function can be converted to a convex program (i.e., a maximization problem with a concave objective and convex constraints), enabling it to be solved to optimality via an outer-approximation algorithm. Extensive experiments show the efficiency of our approach and provide analyses on the benefits of using the cross-nested model in the facility location context.

Extensive research has revealed that adversarial examples (AE) pose a significant threat to voice-controllable smart devices. Recent studies have proposed black-box adversarial attacks that require only the final transcription from an automatic speech recognition (ASR) system. However, these attacks typically involve many queries to the ASR, resulting in substantial costs. Moreover, AE-based adversarial audio samples are susceptible to ASR updates. In this paper, we identify the root cause of these limitations, namely the inability to construct AE attack samples directly around the decision boundary of deep learning (DL) models. Building on this observation, we propose ALIF, the first black-box adversarial linguistic feature-based attack pipeline. We leverage the reciprocal process of text-to-speech (TTS) and ASR models to generate perturbations in the linguistic embedding space where the decision boundary resides. Based on the ALIF pipeline, we present the ALIF-OTL and ALIF-OTA schemes for launching attacks in both the digital domain and the physical playback environment on four commercial ASRs and voice assistants. Extensive evaluations demonstrate that ALIF-OTL and -OTA significantly improve query efficiency by 97.7% and 73.3%, respectively, while achieving competitive performance compared to existing methods. Notably, ALIF-OTL can generate an attack sample with only one query. Furthermore, our test-of-time experiment validates the robustness of our approach against ASR updates., Comment: Published in the 2024 IEEE Symposium on Security and Privacy (SP)

We propose and evaluate a question-answering system that uses decomposed prompting to classify and answer student questions on a course discussion board. Our system uses a large language model (LLM) to classify questions into one of four types: conceptual, homework, logistics, and not answerable. This enables us to employ a different strategy for answering questions that fall under different types. Using a variant of GPT-3, we achieve $81\%$ classification accuracy. We discuss our system's performance on answering conceptual questions from a machine learning course and various failure modes., Comment: 6 pages. Published at International Conference on Artificial Intelligence in Education 2023. Code repository: https://github.com/brandonjaipersaud/piazza-qabot-gpt

Recently, advanced Large Language Models (LLMs) such as GPT-4 have been integrated into many real-world applications like Code Copilot. These applications have significantly expanded the attack surface of LLMs, exposing them to a variety of threats. Among them, jailbreak attacks that induce toxic responses through jailbreak prompts have raised critical safety concerns. To identify these threats, a growing number of red teaming approaches simulate potential adversarial scenarios by crafting jailbreak prompts to test the target LLM. However, existing red teaming methods do not consider the unique vulnerabilities of LLM in different scenarios, making it difficult to adjust the jailbreak prompts to find context-specific vulnerabilities. Meanwhile, these methods are limited to refining jailbreak templates using a few mutation operations, lacking the automation and scalability to adapt to different scenarios. To enable context-aware and efficient red teaming, we abstract and model existing attacks into a coherent concept called "jailbreak strategy" and propose a multi-agent LLM system named RedAgent that leverages these strategies to generate context-aware jailbreak prompts. By self-reflecting on contextual feedback in an additional memory buffer, RedAgent continuously learns how to leverage these strategies to achieve effective jailbreaks in specific contexts. Extensive experiments demonstrate that our system can jailbreak most black-box LLMs in just five queries, improving the efficiency of existing red teaming methods by two times. Additionally, RedAgent can jailbreak customized LLM applications more efficiently. By generating context-aware jailbreak prompts towards applications on GPTs, we discover 60 severe vulnerabilities of these real-world applications with only two queries per vulnerability. We have reported all found issues and communicated with OpenAI and Meta for bug fixes.

In object detection, unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, UDA's reliance on labeled source data restricts its adaptability in privacy-related scenarios. This study focuses on source-free object detection (SFOD), which adapts a source-trained detector to an unlabeled target domain without using labeled source data. Recent advancements in self-training, particularly with the Mean Teacher (MT) framework, show promise for SFOD deployment. However, the absence of source supervision significantly compromises the stability of these approaches. We identify two primary issues, (1) uncontrollable degradation of the teacher model due to inopportune updates from the student model, and (2) the student model's tendency to replicate errors from incorrect pseudo labels, leading to it being trapped in a local optimum. Both factors contribute to a detrimental circular dependency, resulting in rapid performance degradation in recent self-training frameworks. To tackle these challenges, we propose the Dynamic Retraining-Updating (DRU) mechanism, which actively manages the student training and teacher updating processes to achieve co-evolutionary training. Additionally, we introduce Historical Student Loss to mitigate the influence of incorrect pseudo labels. Our method achieves state-of-the-art performance in the SFOD setting on multiple domain adaptation benchmarks, comparable to or even surpassing advanced UDA methods. The code will be released at https://github.com/lbktrinh/DRU, Comment: ECCV 2024

Vision-language models have been extensively explored across a wide range of tasks, achieving satisfactory performance; however, their application in medical imaging remains underexplored. In this work, we propose a unified framework - LiteGPT - for the medical imaging. We leverage multiple pre-trained visual encoders to enrich information and enhance the performance of vision-language models. To the best of our knowledge, this is the first study to utilize vision-language models for the novel task of joint localization and classification in medical images. Besides, we are pioneers in providing baselines for disease localization in chest X-rays. Finally, we set new state-of-the-art performance in the image classification task on the well-benchmarked VinDr-CXR dataset. All code and models are publicly available online: https://github.com/leduckhai/LiteGPT, Comment: Preprint, 19 pages

In the dynamic landscape of the Web, we are witnessing the emergence of the Web3 paradigm, which dictates that platforms should rely on blockchain technology and cryptocurrencies to sustain themselves and their profitability. Cryptocurrencies are characterised by high market volatility and susceptibility to substantial crashes, issues that require temporal analysis methodologies able to tackle the high temporal resolution, heterogeneity and scale of blockchain data. While existing research attempts to analyse crash events, fundamental questions persist regarding the optimal time scale for analysis, differentiation between long-term and short-term trends, and the identification and characterisation of shock events within these decentralised systems. This paper addresses these issues by examining cryptocurrencies traded on the Ethereum blockchain, with a spotlight on the crash of the stablecoin TerraUSD and the currency LUNA designed to stabilise it. Utilising complex network analysis and a multi-layer temporal graph allows the study of the correlations between the layers representing the currencies and system evolution across diverse time scales. The investigation sheds light on the strong interconnections among stablecoins pre-crash and the significant post-crash transformations. We identify anomalous signals before, during, and after the collapse, emphasising their impact on graph structure metrics and user movement across layers. This paper pioneers temporal, cross-chain graph analysis to explore a cryptocurrency collapse. It emphasises the importance of temporal analysis for studies on web-derived data and how graph-based analysis can enhance traditional econometric results. Overall, this research carries implications beyond its field, for example for regulatory agencies aiming to safeguard users from shocks and monitor investment risks for citizens and clients.

In this study, based on the quantum kinetic equation approach, we systematically present the radio-electric effect in asymmetric semi-parabolic quantum wells under the influence of a laser radiation field taking into account the electron-longitudinal optical phonon scattering mechanism. The numerical results show that the blue-shift of the maximum peaks in the photon energy range is less than 60 meV. The height of maximum peaks increases according to an exponential rule, depending nonlinearly on the structural parameters of the asymmetric semi-parabolic quantum wells. In the photon energy range greater than 100 meV, the saturated radio-electric field increases with temperature and geometric parameters of the quantum well. Temperature also strongly affects full-width at half-maximum with rules consistent with previous theoretical calculations and experimental observations. The results show the differences between symmetric and asymmetric semi-parabolic quantum wells, highlighting the influence of asymmetric structures on radio-electric effects in two-dimensional quantum well systems., Comment: The manuscript was rejected by the journal

Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains. However, this utility comes with increasing concerns about privacy, as the training data may include sensitive information. To address these concerns, machine unlearning has been proposed to erase specific data samples from models. While some unlearning techniques efficiently remove data at low costs, recent research highlights vulnerabilities where malicious users could request unlearning on manipulated data to compromise the model. Despite these attacks' effectiveness, perturbed data differs from original training data, failing hash verification. Existing attacks on machine unlearning also suffer from practical limitations and require substantial additional knowledge and resources. To fill the gaps in current unlearning attacks, we introduce the Unlearning Usability Attack. This model-agnostic, unlearning-agnostic, and budget-friendly attack distills data distribution information into a small set of benign data. These data are identified as benign by automatic poisoning detection tools due to their positive impact on model training. While benign for machine learning, unlearning these data significantly degrades model information. Our evaluation demonstrates that unlearning this benign data, comprising no more than 1% of the total training data, can reduce model accuracy by up to 50%. Furthermore, our findings show that well-prepared benign data poses challenges for recent unlearning techniques, as erasing these synthetic instances demands higher resources than regular data. These insights underscore the need for future research to reconsider "data poisoning" in the context of machine unlearning.

Human motion copy is an intriguing yet challenging task in artificial intelligence and computer vision, which strives to generate a fake video of a target person performing the motion of a source person. The problem is inherently challenging due to the subtle human-body texture details to be generated and the temporal consistency to be considered. Existing approaches typically adopt a conventional GAN with an L1 or L2 loss to produce the target fake video, which intrinsically necessitates a large number of training samples that are challenging to acquire. Meanwhile, current methods still have difficulties in attaining realistic image details and temporal consistency, which unfortunately can be easily perceived by human observers. Motivated by this, we try to tackle the issues from three aspects: (1) We constrain pose-to-appearance generation with a perceptual loss and a theoretically motivated Gromov-Wasserstein loss to bridge the gap between pose and appearance. (2) We present an episodic memory module in the pose-to-appearance generation to propel continuous learning that helps the model learn from its past poor generations. We also utilize geometrical cues of the face to optimize facial details and refine each key body part with a dedicated local GAN. (3) We advocate generating the foreground in a sequence-to-sequence manner rather than a single-frame manner, explicitly enforcing temporal inconsistency. Empirical results on five datasets, iPER, ComplexMotion, SoloDance, Fish, and Mouse datasets, demonstrate that our method is capable of generating realistic target videos while precisely copying motion from a source video. Our method significantly outperforms state-of-the-art approaches and gains 7.2% and 12.4% improvements in PSNR and FID respectively.

Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions. Inspired by the success of generative diffusion models, we propose a novel approach coupling data augmentation, in the form of image noising and blurring, with label smoothing to align predicted label confidences with image degradation. The method is simple to implement, introduces negligible overheads, and can be combined with existing augmentations. We demonstrate improved robustness and uncertainty quantification on the corrupted image benchmarks of the CIFAR and TinyImageNet datasets., Comment: Under review

The analogy between electromagnetism and gravitation was achieved by linearizing the tensorial gravitational equations of general relativity and converting them into a vector form corresponding to Maxwell's electromagnetic equations. On this basis, we use the equivalence with viscoelasticity (SH waves) and propose a theory of gravitational waves. We add a damping term to the differential equations, which is equivalent to Ohm's law in electromagnetism and Maxwell's viscosity in viscoelasticity, to describe the attenuation of the waves. A plane-wave analysis gives the phase velocity, the energy velocity, the quality factor and the attenuation factor of the field as well as the energy balance. To obtain these properties, we use the analogy with viscoelasticity; the properties of electromagnetic and gravitational waves are similar to those of shear waves. The presence of attenuation means that the transient field is generally a composition of inhomogeneous (non-uniform) plane waves, where the propagation and attenuation vectors do not point in the same direction and the phase velocity vector and the energy flux (energy velocity) are not collinear. The polarization of cross-plane field is linear and perpendicular to the propagation-attenuation plane, while the polarization of the field within the plane is elliptical. Transient wave fields in the space-time domain are analyzed with the Green function (in homogeneous media) and with a grid method (in heterogeneous media) based on the Fourier method for calculating the spatial derivatives and a Runge-Kutta scheme of order 4 for the time stepping. In the examples, wave propagation at the Sun-Earth and Earth-Moon distances using quadrupole sources is considered in comparison to viscoelastic waves. Finally, an example of propagation in heterogeneous media is presented., Comment: 11 figures

We propose a 3D multi-object tracking (MOT) solution using only 2D detections from monocular cameras, which automatically initiates/terminates tracks as well as resolves track appearance-reappearance and occlusions. Moreover, this approach does not require detector retraining when cameras are reconfigured but only the camera matrices of reconfigured cameras need to be updated. Our approach is based on a Bayesian multi-object formulation that integrates track initiation/termination, re-identification, occlusion handling, and data association into a single Bayes filtering recursion. However, the exact filter that utilizes all these functionalities is numerically intractable due to the exponentially growing number of terms in the (multi-object) filtering density, while existing approximations trade-off some of these functionalities for speed. To this end, we develop a more efficient approximation suitable for online MOT by incorporating object features and kinematics into the measurement model, which improves data association and subsequently reduces the number of terms. Specifically, we exploit the 2D detections and extracted features from multiple cameras to provide a better approximation of the multi-object filtering density to realize the track initiation/termination and re-identification functionalities. Further, incorporating a tractable geometric occlusion model based on 2D projections of 3D objects on the camera planes realizes the occlusion handling functionality of the filter. Evaluation of the proposed solution on challenging datasets demonstrates significant improvements and robustness when camera configurations change on-the-fly, compared to existing multi-view MOT solutions. The source code is publicly available at https://github.com/linh-gist/mv-glmb-ab.

We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tackle the problem through a multi-sensor fusion approach, where we take as input an additional synchronized sparse point cloud (i.e., from a LiDAR) projected onto the image plane as a sparse depth map, along with a camera image. The crux of our method lies in the use of the abundantly available synthetic data to first approximate the 3D scene structure by learning a mapping from sparse to (coarse) dense depth maps along with their predictive uncertainty - we term this, SpaDe. In poorly illuminated regions where photometric intensities do not afford the inference of local shape, the coarse approximation of scene depth serves as a prior; the uncertainty map is then used with the image to guide refinement through an uncertainty-driven residual learning (URL) scheme. The resulting depth completion network leverages complementary strengths from both modalities - depth is sparse but insensitive to illumination and in metric scale, and image is dense but sensitive with scale ambiguity. SpaDe can be used in a plug-and-play fashion, which allows for 25% improvement when augmented onto existing methods to preprocess sparse depth. We demonstrate URL on the nuScenes dataset where we improve over all baselines by an average 11.65% in all-day scenarios, 11.23% when tested specifically for daytime, and 13.12% for nighttime scenes., Comment: 8 pages, 4 figures

Deep learning is computationally intensive, with significant efforts focused on reducing arithmetic complexity, particularly regarding energy consumption dominated by data movement. While existing literature emphasizes inference, training is considerably more resource-intensive. This paper proposes a novel mathematical principle by introducing the notion of Boolean variation such that neurons made of Boolean weights and inputs can be trained -- for the first time -- efficiently in Boolean domain using Boolean logic instead of gradient descent and real arithmetic. We explore its convergence, conduct extensively experimental benchmarking, and provide consistent complexity evaluation by considering chip architecture, memory hierarchy, dataflow, and arithmetic precision. Our approach achieves baseline full-precision accuracy in ImageNet classification and surpasses state-of-the-art results in semantic segmentation, with notable performance in image super-resolution, and natural language understanding with transformer-based models. Moreover, it significantly reduces energy consumption during both training and inference., Comment: Under review

We generalize the problem of recovering a lost/erased symbol in a Reed-Solomon code to the scenario in which some side information about the lost symbol is known. The side information is represented as a set $S$ of linearly independent combinations of the sub-symbols of the lost symbol. When $S = \varnothing$, this reduces to the standard problem of repairing a single codeword symbol. When $S$ is a set of sub-symbols of the erased one, this becomes the repair problem with partially lost/erased symbol. We first establish that the minimum repair bandwidth depends on $|S|$ and not the content of $S$ and construct a lower bound on the repair bandwidth of a linear repair scheme with side information $S$. We then consider the well-known subspace-polynomial repair schemes and show that their repair bandwidths can be optimized by choosing the right subspaces. Finally, we demonstrate several parameter regimes where the optimal bandwidths can be achieved for full-length Reed-Solomon codes.

Bound states in the continuum (BICs) are an excellent platform enabling highly efficient light-matter interaction in applications for lasing, nonlinear generation, and sensing. However, the current focus in implementing BICs has primarily been on single sharp resonances, limiting the extent of electric field enhancement for multiple resonances. In this study, we conducted experimental demonstrations to showcase how metasurfaces can enable the control of symmetry-broken and Friedrich-Wintgen BICs by leveraging the asymmetry of split resonant rings. This approach allows for the existence of multiple free-control BIC resonances and tailored enhancement of controlling light-matter interactions. We have conducted further experiments to validate the effectiveness and performance of our approach for identification of the distinct fingerprint of {\alpha}-lactose with high sensitivity using only one single metasurface. These findings present a novel and efficient platform for the development of miniaturized and chip-scale photonics devices with intense light-matter interaction.

Morphological classification conveys abundant information on the formation, evolution, and environment of galaxies. In this work, we refine the two-step galaxy morphological classification framework ({\tt\string USmorph}), which employs a combination of unsupervised machine learning (UML) and supervised machine learning (SML) techniques, along with a self-consistent and robust data preprocessing step. The updated method is applied to the galaxies with $I_{\rm mag}<25$ at $0.2

Recent years have seen significant efforts to adopt Artificial Intelligence (AI) in healthcare for various use cases, from computer-aided diagnosis to ICU triage. However, the size of AI models has been rapidly growing due to scaling laws and the success of foundational models, which poses an increasing challenge to leverage advanced models in practical applications. It is thus imperative to develop efficient models, especially for deploying AI solutions under resource-constrains or with time sensitivity. One potential solution is to perform model compression, a set of techniques that remove less important model components or reduce parameter precision, to reduce model computation demand. In this work, we demonstrate that model pruning, as a model compression technique, can effectively reduce inference cost for computational and digital pathology based analysis with a negligible loss of analysis performance. To this end, we develop a methodology for pruning the widely used U-Net-style architectures in biomedical imaging, with which we evaluate multiple pruning heuristics on nuclei instance segmentation and classification, and empirically demonstrate that pruning can compress models by at least 70% with a negligible drop in performance.

As crowdsourcing emerges as an efficient and cost-effective method for obtaining labels for machine learning datasets, it is important to assess the quality of crowd-provided data, so as to improve analysis performance and reduce biases in subsequent machine learning tasks. Given the lack of ground truth in most cases of crowdsourcing, we refer to data quality as annotators' consistency and credibility. Unlike the simple scenarios where Kappa coefficient and intraclass correlation coefficient usually can apply, online crowdsourcing requires dealing with more complex situations. We introduce a systematic method for evaluating data quality and detecting spamming threats via variance decomposition, and we classify spammers into three categories based on their different behavioral patterns. A spammer index is proposed to assess entire data consistency and two metrics are developed to measure crowd worker's credibility by utilizing the Markov chain and generalized random effects models. Furthermore, we showcase the practicality of our techniques and their advantages by applying them on a face verification task with both simulation and real-world data collected from two crowdsourcing platforms., Comment: Preprint paper, under review on Behavior Research Methods. 45 pages, 10 figures

Dimension reduction techniques are among the most essential analytical tools in the analysis of high-dimensional data. Generalized principal component analysis (PCA) is an extension to standard PCA that has been widely used to identify low-dimensional features in high-dimensional discrete data, such as binary, multi-category and count data. For microbiome count data in particular, the multinomial PCA is a natural counterpart of the standard PCA. However, this technique fails to account for the excessive number of zero values, which is frequently observed in microbiome count data. To allow for sparsity, zero-inflated multivariate distributions can be used. We propose a zero-inflated probabilistic PCA model for latent factor analysis. The proposed model is a fully Bayesian factor analysis technique that is appropriate for microbiome count data analysis. In addition, we use the mean-field-type variational family to approximate the marginal likelihood and develop a classification variational approximation algorithm to fit the model. We demonstrate the efficiency of our procedure for predictions based on the latent factors and the model parameters through simulation experiments, showcasing its superiority over competing methods. This efficiency is further illustrated with two real microbiome count datasets. The method is implemented in R., Comment: 2 figures, 3 tables

This paper presents the proof-of-concept of the first automatic voice assistant ever built in Wolof language, the main vehicular language spoken in Senegal. This voicebot is the result of a collaborative research project between Orange Innovation in France, Orange Senegal (aka Sonatel) and ADNCorp, a small IT company based in Dakar, Senegal. The purpose of the voicebot is to provide information to Orange customers about the Sargal loyalty program of Orange Senegal by using the most natural mean to communicate: speech. The voicebot receives in input the customer's oral request that is then processed by a SLU system to reply to the customer's request using audio recordings. The first results of this proof-of-concept are encouraging as we achieved 22\% of WER for the ASR task and 78\% of F1-score on the NLU task., Comment: in French language

Most domain adaptation (DA) methods are based on either a convolutional neural networks (CNNs) or a vision transformers (ViTs). They align the distribution differences between domains as encoders without considering their unique characteristics. For instance, ViT excels in accuracy due to its superior ability to capture global representations, while CNN has an advantage in capturing local representations. This fact has led us to design a hybrid method to fully take advantage of both ViT and CNN, called Explicitly Class-specific Boundaries (ECB). ECB learns CNN on ViT to combine their distinct strengths. In particular, we leverage ViT's properties to explicitly find class-specific decision boundaries by maximizing the discrepancy between the outputs of the two classifiers to detect target samples far from the source support. In contrast, the CNN encoder clusters target features based on the previously defined class-specific boundaries by minimizing the discrepancy between the probabilities of the two classifiers. Finally, ViT and CNN mutually exchange knowledge to improve the quality of pseudo labels and reduce the knowledge discrepancies of these models. Compared to conventional DA methods, our ECB achieves superior performance, which verifies its effectiveness in this hybrid model. The project website can be found https://dotrannhattuong.github.io/ECB/website., Comment: Project page: https://dotrannhattuong.github.io/ECB/website, Accepted to CVPR 2024

Granular metals offer tailorable electronic properties and play crucial roles in device and sensor applications. We have fabricated a series of nonmagnetic granular CoSi2 thin films and studied the Hall effect and transport properties. We observed a two orders of magnitude enhancement in the Hall coefficient in films fall slightly above the metal-insulator transition. This giant Hall effect (GHE) is ascribed to the local quantum-interference effect induced reduction of the charge carriers. Transmission electron microscopy images and transport properties indicate that our films form two dimensional granular arrays. The GHE may provide useful and sensitive applications., Comment: 5 pages, 4 figures

This paper proposed a novel and temporal phase-shift digital shearography system for simultaneous measurement of first order displacement derivative in orthogonal shear directions. Dual lasers with wavelengths of 532nm and 637nm, three splitter prism structure, two dichroic mirrors with different response wavelength, and the color CMOS are used in the system. Two dichroic mirrors can be used as shear mirrors to realize shear in orthogonal directions at the same time. The system realizes the measurement of the first-order displacement derivative information in the orthogonal direction of the round metal aluminum plate of diameter 250mm. The experimental results show that the overall displacement integral PV error in the x and y directions is 2.7%-14.8%, which verified the reliability of the system.

High-dimensional real-world systems can often be well characterized by a small number of simultaneous low-complexity interactions. The analysis of variance (ANOVA) decomposition and the anchored decomposition are typical techniques to find sparse additive decompositions of functions. In this paper, we are interested in a setting, where these decompositions are not directly spare, but become so after an appropriate basis transform. Noting that the sparsity of those additive function decompositions is equivalent to the fact that most of its mixed partial derivatives vanish, we can exploit a connection to the underlying function graphs to determine an orthogonal transform that realizes the appropriate basis change. This is done in three steps: we apply singular value decomposition to minimize the number of vertices of the function graph, and joint block diagonalization techniques of families of matrices followed by sparse minimization based on relaxations of the zero ''norm'' for minimizing the number of edges. For the latter one, we propose and analyze minimization techniques over the manifold of special orthogonal matrices. Various numerical examples illustrate the reliability of our approach for functions having, after a basis transform, a sparse additive decomposition into summands with at most two variables., Comment: 46 pages, 10 figures, 8 tables