Search

In this paper we construct high order numerical methods for solving third and fourth orders nonlinear functional differential equations (FDE). They are based on the discretization of iterative methods on continuous level with the use of the trapezoidal quadrature formulas with corrections. Depending on the number of terms in the corrections we obtain methods of $O(h^4)$ and $O(h^6)$ accuracy. Some numerical experiments demonstrate the validity of the obtained theoretical results. The approach used here for the third and fourth orders nonlinear functional differential equations can be applied to functional differential equations of any orders., Comment: 25 pages

The cognitive faculty of visual reasoning necessitates the integration of multimodal perceptual processing and commonsense and external knowledge of the world. In recent years, a plethora of large vision-language models (LVLMs) have been proposed, demonstrating outstanding power and exceptional proficiency in commonsense reasoning across diverse domains and tasks. Nevertheless, training such LVLMs requires a lot of costly resources. Recent approaches, instead of training LVLMs from scratch on various large datasets, focus on exploring ways to take advantage of the capabilities of many different LVLMs, such as ensemble methods. In this work, we propose self-ensemble, a novel method that improves the generalization and visual reasoning of the model without updating any parameters, a training-free method. Our key insight is that we realized that LVLM itself can ensemble without the need for any other LVLMs, which helps to unlock their internal capabilities. Extensive experiments on various benchmarks demonstrate the effectiveness of our method in achieving state-of-the-art (SOTA) performance on SketchyVQA, Outside Knowledge VQA, and out-of-distribution VQA tasks.

Let $E$ be a subset in $\mathbb{F}_p^2$ and $S$ be a subset in the special linear group $SL_2(\mathbb{F}_p)$ or the $1$-dimensional Heisenberg linear group $\mathbb{H}_1(\mathbb{F}_p)$. We define $S(E):= \bigcup_{\theta \in S} \theta (E)$. In this paper, we provide optimal conditions on $S$ and $E$ such that the set $S(E)$ covers a positive proportion of all elements in the plane $\mathbb{F}_p$. When the sizes of $S$ and $E$ are small, we prove structural theorems that guarantee that $|S(E)|\gg |E|^{1+\epsilon}$ for some $\epsilon>0$. The main ingredients in our proofs are novel results on algebraic incidence-type structures associated with the groups, in which energy estimates play a crucial role. The higher-dimensional version will also be discussed in this paper., Comment: 34 pages

Depth information plays a crucial role in autonomous systems for environmental perception and robot state estimation. With the rapid development of deep neural network technology, depth estimation has been extensively studied and shown potential for practical applications. However, in particularly challenging environments such as low-light and noisy underwater conditions, direct application of machine learning models may not yield the desired results. Therefore, in this paper, we present an approach to enhance underwater image quality to improve depth estimation effectiveness. First, underwater images are processed through methods such as color compensation, brightness equalization, and enhancement of contrast and sharpness of objects in the image. Next, we perform depth estimation using the Udepth model on the enhanced images. Finally, the results are evaluated and presented to verify the effectiveness and accuracy of the enhanced depth image quality approach for underwater robots., Comment: In The 26th National Conference on Electronics, Communications and Information Technology (REV-ECIT 2023), Hanoi, Vietnam, in Vietnamese language

Image registration techniques usually assume that the images to be registered are of a certain type (e.g. single- vs. multi-modal, 2D vs. 3D, rigid vs. deformable) and there lacks a general method that can work for data under all conditions. We propose a registration method that utilizes neural networks for image representation. Our method uses untrained networks with limited representation capacity as an implicit prior to guide for a good registration. Unlike previous approaches that are specialized for specific data types, our method handles both rigid and non-rigid, as well as single- and multi-modal registration, without requiring changes to the model or objective function. We have performed a comprehensive evaluation study using a variety of datasets and demonstrated promising performance.

Mixture of Experts (MoEs) plays an important role in the development of more efficient and effective large language models (LLMs). Due to the enormous resource requirements, studying large scale MoE algorithms remain in-accessible to many researchers. This work develops \emph{LibMoE}, a comprehensive and modular framework to streamline the research, training, and evaluation of MoE algorithms. Built upon three core principles: (i) modular design, (ii) efficient training; (iii) comprehensive evaluation, LibMoE brings MoE in LLMs more accessible to a wide range of researchers by standardizing the training and evaluation pipelines. Using LibMoE, we extensively benchmarked five state-of-the-art MoE algorithms over three different LLMs and 11 datasets under the zero-shot setting. The results show that despite the unique characteristics, all MoE algorithms perform roughly similar when averaged across a wide range of tasks. With the modular design and extensive evaluation, we believe LibMoE will be invaluable for researchers to make meaningful progress towards the next generation of MoE and LLMs. Project page: \url{https://fsoft-aic.github.io/fsoft-LibMoE.github.io}., Comment: 15 pages, 9 figures

Endovascular surgical tool reconstruction represents an important factor in advancing endovascular tool navigation, which is an important step in endovascular surgery. However, the lack of publicly available datasets significantly restricts the development and validation of novel machine learning approaches. Moreover, due to the need for specialized equipment such as biplanar scanners, most of the previous research employs monoplanar fluoroscopic technologies, hence only capturing the data from a single view and significantly limiting the reconstruction accuracy. To bridge this gap, we introduce Guide3D, a bi-planar X-ray dataset for 3D reconstruction. The dataset represents a collection of high resolution bi-planar, manually annotated fluoroscopic videos, captured in real-world settings. Validating our dataset within a simulated environment reflective of clinical settings confirms its applicability for real-world applications. Furthermore, we propose a new benchmark for guidewrite shape prediction, serving as a strong baseline for future work. Guide3D not only addresses an essential need by offering a platform for advancing segmentation and 3D reconstruction techniques but also aids the development of more accurate and efficient endovascular surgery interventions. Our project is available at https://airvlab.github.io/guide3d/., Comment: Accepted to ACCV 2024

High performance, reliability and safety are crucial properties of any Software-Defined-Networking (SDN) system. Although the use of Deep Reinforcement Learning (DRL) algorithms has been widely studied to improve performance, their practical applications are still limited as they fail to ensure safe operations in exploration and decision-making. To fill this gap, we explore the design of a Control Barrier Function (CBF) on top of Deep Reinforcement Learning (DRL) algorithms for load-balancing. We show that our DRL-CBF approach is capable of meeting safety requirements during training and testing while achieving near-optimal performance in testing. We provide results using two simulators: a flow-based simulator, which is used for proof-of-concept and benchmarking, and a packet-based simulator that implements real protocols and scheduling. Thanks to the flow-based simulator, we compared the performance against the optimal policy, solving a Non Linear Programming (NLP) problem with the SCIP solver. Furthermore, we showed that pre-trained models in the flow-based simulator, which is faster, can be transferred to the packet simulator, which is slower but more accurate, with some fine-tuning. Overall, the results suggest that near-optimal Quality-of-Service (QoS) performance in terms of end-to-end delay can be achieved while safety requirements related to link capacity constraints are guaranteed. In the packet-based simulator, we also show that our DRL-CBF algorithms outperform non-RL baseline algorithms. When the models are fine-tuned over a few episodes, we achieved smoother QoS and safety in training, and similar performance in testing compared to the case where models have been trained from scratch., Comment: Accepted to Computer Communications 2024. arXiv admin note: text overlap with arXiv:2401.05525

Retrieval-augmented generation (RAG) methods are viable solutions for addressing the static memory limits of pre-trained language models. Nevertheless, encountering conflicting sources of information within the retrieval context is an inevitable practical challenge. In such situations, the language models are recommended to transparently inform users about the conflicts rather than autonomously deciding what to present based on their inherent biases. To analyze how current large language models (LLMs) align with our recommendation, we introduce WhoQA, a public benchmark dataset to examine model's behavior in knowledge conflict situations. We induce conflicts by asking about a common property among entities having the same name, resulting in questions with up to 8 distinctive answers. WhoQA evaluation set includes 5K questions across 13 Wikidata property types and 150K Wikipedia entities. Our experiments show that despite the simplicity of WhoQA questions, knowledge conflicts significantly degrades LLMs' performance in RAG settings., Comment: Accepted to EMNLP 2024 Findings

REST (Representational State Transfer) APIs have become integral for data communication and exchange due to their simplicity, scalability, and compatibility with web standards. However, ensuring REST APIs' reliability through rigorous testing poses significant challenges, given the complexities of operations, parameters, inputs, dependencies, and call sequences. In this paper, we introduce MUCOREST, a novel Reinforcement Learning (RL)-based API testing approach that leverages Q-learning to maximize code coverage and output coverage, thereby improving bug discovery. By focusing on these proximate objectives rather than the abstract goal of maximizing failures, MUCOREST effectively discovers critical code areas and diverse API behaviors. The experimental results on a benchmark of 10 services show that MUCOREST significantly outperforms state-of-the-art API testing approaches by 11.6-261.1% in the number of discovered API bugs. MUCOREST can generate much fewer API calls to discover the same number of bugs compared to the other approaches. Furthermore, 12.17%-64.09% of the bugs discovered by the other techniques can also be found by MUCOREST., Comment: Accepted by KSE'24

Assessing cognitive workload is crucial for human performance as it affects information processing, decision making, and task execution. Pupil size is a valuable indicator of cognitive workload, reflecting changes in attention and arousal governed by the autonomic nervous system. Cognitive events are closely linked to cognitive workload as they activate mental processes and trigger cognitive responses. This study explores the potential of using machine learning to automatically detect cognitive events experienced using individuals. We framed the problem as a binary classification task, focusing on detecting stimulus onset across four cognitive tasks using CNN models and 1-second pupillary data. The results, measured by Matthew's correlation coefficient, ranged from 0.47 to 0.80, depending on the cognitive task. This paper discusses the trade-offs between generalization and specialization, model behavior when encountering unseen stimulus onset times, structural variances among cognitive tasks, factors influencing model predictions, and real-time simulation. These findings highlight the potential of machine learning techniques in detecting cognitive events based on pupil and eye movement responses, contributing to advancements in personalized learning and optimizing neurocognitive workload management., Comment: 10 pages, 7 figures

In this paper, cyber-attack prevention for the prosumer-based electric vehicle (EV) charging stations (EVCSs) is investigated, which covers two aspects: 1) cyber-attack detection on prosumers' network traffic (NT) data, and 2) cyber-attack intervention. To establish an effective prevention mechanism, several challenges need to be tackled, for instance, the NT data per prosumer may be non-independent and identically distributed (non-IID), and the boundary between benign and malicious traffic becomes blurred. To this end, we propose an edge-assisted federated prototype knowledge distillation (E-FPKD) approach, where each client is deployed on a dedicated local edge server (DLES) and can report its availability for joining the federated learning (FL) process. Prior to the E-FPKD approach, to enhance accuracy, the Pearson Correlation Coefficient is adopted for feature selection. Regarding the proposed E-FPKD approach, we integrate the knowledge distillation and prototype aggregation technique into FL to deal with the non-IID challenge. To address the boundary issue, instead of directly calculating the distance between benign and malicious traffic, we consider maximizing the overall detection correctness of all prosumers (ODC), which can mitigate the computational cost compared with the former way. After detection, a rule-based method will be triggered at each DLES for cyber-attack intervention. Experimental analysis demonstrates that the proposed E-FPKD can achieve the largest ODC on NSL-KDD, UNSW-NB15, and IoTID20 datasets in both binary and multi-class classification, compared with baselines. For instance, the ODC for IoTID20 obtained via the proposed method is separately 0.3782% and 4.4471% greater than FedProto and FedAU in multi-class classification., Comment: 27 pages, 12 figures

We extend Tsuji's iterative construction of a K\"ahler--Einstein metric with negative scalar curvature to (non-compact) K\"ahler manifolds with bounded geometry, using Berndtsson's method for the compact setting. Consequently, given a holomorphic surjective map $p:X \to Y$, where $X$ is a weakly pseudoconvex K\"ahler manifold and $Y$ is a complex manifold, whose smooth fibers admit K\"ahler--Einstein metrics with negative scalar curvature and bounded geometry, we show that the fiberwise K\"ahler--Einstein metric induces a semi-positively curved metric on the relative canonical bundle $K_{X/Y}$ of $p$. Moreover, our approach can be applied to obtain the plurisubharmonic variation of cusp K\"ahler--Einstein metrics., Comment: 23 pages, v.2 references updated

Despite recent progress, Multi-Object Tracking (MOT) continues to face significant challenges, particularly its dependence on prior knowledge and predefined categories, complicating the tracking of unfamiliar objects. Generic Multiple Object Tracking (GMOT) emerges as a promising solution, requiring less prior information. Nevertheless, existing GMOT methods, primarily designed as OneShot-GMOT, rely heavily on initial bounding boxes and often struggle with variations in viewpoint, lighting, occlusion, and scale. To overcome the limitations inherent in both MOT and GMOT when it comes to tracking objects with specific generic attributes, we introduce Grounded-GMOT, an innovative tracking paradigm that enables users to track multiple generic objects in videos through natural language descriptors. Our contributions begin with the introduction of the G2MOT dataset, which includes a collection of videos featuring a wide variety of generic objects, each accompanied by detailed textual descriptions of their attributes. Following this, we propose a novel tracking method, KAM-SORT, which not only effectively integrates visual appearance with motion cues but also enhances the Kalman filter. KAM-SORT proves particularly advantageous when dealing with objects of high visual similarity from the same generic category in GMOT scenarios. Through comprehensive experiments, we demonstrate that Grounded-GMOT outperforms existing OneShot-GMOT approaches. Additionally, our extensive comparisons between various trackers highlight KAM-SORT's efficacy in GMOT, further establishing its significance in the field. Project page: https://UARK-AICV.github.io/G2MOT. The source code and dataset will be made publicly available., Comment: ACCV 2024, main track, oral presentation

In this paper, we address the identification and estimation of insurance models where insurees have private information about their risk and risk aversion. The model includes random damages and allows for several claims, while insurers choose from a finite number of coverages. We show that the joint distribution of risk and risk aversion is nonparametrically identified despite bunching due to multidimensional types and a finite number of coverages. Our identification strategy exploits the observed number of claims as well as an exclusion restriction, and a full support assumption. Furthermore, our results apply to any form of competition. We propose a novel estimation procedure combining nonparametric estimators and GMM estimation that we illustrate in a Monte Carlo study.

This paper introduces a novel lossless compression method for compressing geometric attributes of point cloud data with bits-back coding. Our method specializes in using a deep learning-based probabilistic model to estimate the Shannon's entropy of the point cloud information, i.e., geometric attributes of the 3D floating points. Once the entropy of the point cloud dataset is estimated with a convolutional variational autoencoder (CVAE), we use the learned CVAE model to compress the geometric attributes of the point clouds with the bits-back coding technique. The novelty of our method with bits-back coding specializes in utilizing the learned latent variable model of the CVAE to compress the point cloud data. By using bits-back coding, we can capture the potential correlation between the data points, such as similar spatial features like shapes and scattering regions, into the lower-dimensional latent space to further reduce the compression ratio. The main insight of our method is that we can achieve a competitive compression ratio as conventional deep learning-based approaches, while significantly reducing the overhead cost of storage and/or communicating the compression codec, making our approach more applicable in practical scenarios. Throughout comprehensive evaluations, we found that the cost for the overhead is significantly small, compared to the reduction of the compression ratio when compressing large point cloud datasets. Experiment results show that our proposed approach can achieve a compression ratio of 1.56 bit-per-point on average, which is significantly lower than the baseline approach such as Google's Draco with a compression ratio of 1.83 bit-per-point., Comment: This paper is under reviewed in IEEE Robotics and Automation Letters

Reputation is not just a simple opinion that an individual has about another but a social construct that emerges through communication. Despite the huge importance in coordinating human behavior, such a communicative aspect has remained relatively unexplored in the field of indirect reciprocity. In this work, we bridge the gap between private assessment and public reputation: We begin by clarifying what we mean by reputation and argue that the formation of reputation can be modeled by a bi-stochastic matrix, provided that both assessment and behavior are regarded as continuous variables. By choosing bi-stochastic matrices that represent averaging processes, we show that only four norms among the leading eight, which judge a good person's cooperation toward a bad one as good, will keep cooperation asymptotically or neutrally stable against assessment error in a homogeneous society where every member has adopted the same norm. However, when one of those four norms is used by the resident population, the opinion averaging process allows neutral invasion of mutant norms with small differences in the assessment rule. Our approach provides a theoretical framework for describing the formation of reputation in mathematical terms.

With the continuous development of pre-trained language models, prompt-based training becomes a well-adopted paradigm that drastically improves the exploitation of models for many natural language processing tasks. Prompting also shows great performance compared to traditional fine-tuning when adapted to zero-shot or few-shot scenarios where the number of annotated data is limited. In this framework, the role of verbalizers is essential, as an interpretation from masked word distributions into output predictions. In this work, we propose \acrshort{mave}, an approach for verbalizer construction by enrichment of class labels using neighborhood relation in the embedding space of words for the text classification task. In addition, we elaborate a benchmarking procedure to evaluate typical baselines of verbalizers for document classification in few-shot learning contexts. Our model achieves state-of-the-art results while using significantly fewer resources. We show that our approach is particularly effective in cases with extremely limited supervision data.

Recent research has focused on the risks associated with poor sitting posture and the impact of sitting on biological parameters, such as heart rate because prolonged sitting is common across all ages and professions. In this work, we propose a novel approach that can display simultaneously posture and heart rate in real-time. In this device, pressure sensors are embedded into a flexible separate cushion easily put on any chair to provide sitting behaviours and a smartwatch-like PPG module is worn on the user's wrist. Regarding posture classification, pressure figures of ten pressure sensors under the seat bottom are inputs of four machine learning models, giving a high accuracy of 99 per cent. Besides, the Electrocardiography recording module is illustrated with the same results as a commercial device called DFRobot. Another advantage of this smart chair is that it not only simultaneously displays both sitting postures and heart rates on external devices like laptops, mobile phones, or televisions through microcontrollers but also offers the relationship between them to help people adjust their sitting behaviours, avoiding influencing heart rate. The smart chair is expected to be useful equipment for people with a sedentary lifestyle, especially office workers.

Recent advancements in Code Large Language Models (CodeLLMs) have predominantly focused on open-ended code generation tasks, often neglecting the critical aspect of code understanding and comprehension. To bridge this gap, we present CodeMMLU, a comprehensive multiple-choice question-answer benchmark designed to evaluate the depth of software and code understanding in LLMs. CodeMMLU includes over 10,000 questions sourced from diverse domains, encompassing tasks such as code analysis, defect detection, and software engineering principles across multiple programming languages. Unlike traditional benchmarks, CodeMMLU assesses models's ability to reason about code rather than merely generate it, providing deeper insights into their grasp of complex software concepts and systems. Our extensive evaluation reveals that even state-of-the-art models face significant challenges with CodeMMLU, highlighting deficiencies in comprehension beyond code generation. By underscoring the crucial relationship between code understanding and effective generation, CodeMMLU serves as a vital resource for advancing AI-assisted software development, ultimately aiming to create more reliable and capable coding assistants.

Automatic polyp segmentation is crucial for effective diagnosis and treatment in colonoscopy images. Traditional methods encounter significant challenges in accurately delineating polyps due to limitations in feature representation and the handling of variability in polyp appearance. Deep learning techniques, including CNN and Transformer-based methods, have been explored to improve polyp segmentation accuracy. However, existing approaches often neglect additional semantics, restricting their ability to acquire adequate contexts of polyps in colonoscopy images. In this paper, we propose an innovative method named ``Automatic Polyp Segmentation with Self-Enriched Semantic Model'' to address these limitations. First, we extract a sequence of features from an input image and decode high-level features to generate an initial segmentation mask. Using the proposed self-enriched semantic module, we query potential semantics and augment deep features with additional semantics, thereby aiding the model in understanding context more effectively. Extensive experiments show superior segmentation performance of the proposed method against state-of-the-art polyp segmentation baselines across five polyp benchmarks in both superior learning and generalization capabilities., Comment: Asian Conference on Computer Vision 2024

Less than 10 meters deep, shallow landslides are rapidly moving and strongly dangerous slides. In the present work, the probabilistic distribution of the landslide detachment points within a valley is modelled as a spatial Poisson point process, whose intensity depends on geophysical predictors according to a generalized additive model. Modelling the intensity with a generalized additive model jointly allows to obtain good predictive performance and to preserve the interpretability of the effects of the geophysical predictors on the intensity of the process. We propose a novel workflow, based on Random Forests, to select the geophysical predictors entering the model for the intensity. In this context, the statistically significant effects are interpreted as activating or stabilizing factors for landslide detachment. In order to guarantee the transferability of the resulting model, training, validation, and test of the algorithm are performed on mutually disjoint valleys in the Alps of Lombardy (Italy). Finally, the uncertainty around the estimated intensity of the process is quantified via semiparametric bootstrap.

Centralized social networks have experienced a transformative impact on our digital era communication, connection, and information-sharing information. However, it has also raised significant concerns regarding users' privacy and individual rights. In response to these concerns, this paper proposes a novel Decentralized Social Network employing Blockchain technology and Decentralized Storage Networks completed by Access Control Smart Contracts. The initial phase comprises a comprehensive literature review, delving into decentralized social networks, explaining the review methodology, and presenting the resulting findings. Building upon these findings and an analysis of previous research gaps, we propose a novel architecture for decentralized social networks. In conclusion, the principal results highlight the benefit of our decentralized social network to protect user privacy. Moreover, the users have all rights to their posted information following the General Data Protection Regulation (GDPR).

We have conducted Q-band (30 GHz $-$ 50 GHz) line survey observations toward a carbon-chain emission peak in the Serpens South cluster-forming region with the extended Q-band (eQ) receiver installed on the Nobeyama 45 m radio telescope. Approximately 180 lines have been detected including tentative detection, and these lines are attributed to 52 molecules including isotopologues. It has been found that this position is rich in carbon-chain species as much as Cyanopolyyne Peak in Taurus Molecular Cloud-1 (TMC-1 CP), suggesting chemical youth. Not only carbon-chain species, but several complex organic molecules (CH$_3$OH, CH$_3$CHO, HCCCHO, CH$_3$CN, and tentatively C$_2$H$_3$CN) have also been detected, which is similar to the chemical complexity found in evolved prestellar cores. The HDCS/H$_2$CS ratio has been derived to be $11.3 \pm 0.5$ %, and this value is similar to the prestellar core L1544. The chemically young features that are similar to the less-dense starless core TMC-1 CP ($10^4$ cm$^{-3}$ $-$ $10^5$ cm$^{-3}$) and chemically evolved characters which resemble the dense prestellar core L1544 ($\sim 10^6$ cm$^{-3}$) mean that the clump including the observed position is a pre-cluster clump without any current star formation activity., Comment: Accepted for publication in Publications of the Astronomical Society of Japan (PASJ), 32 pages, 9 figures, 6 tables

The recent development of statistical methods that can distinguish between stellar activity and dynamical signals in radial velocity (RV) observations has facilitated the discovery and characterization of planets orbiting young stars. One such technique, Gaussian process (GP) regression, has been regularly employed to improve the detection of a growing number of planets, but the impact of this model for mitigating stellar activity has not been uniformly analyzed for a large sample with real observations. The goal of this study is to investigate how GPs can affect the inferred parameters of RV-detected planets. We homogeneously analyze how two commonly adopted GP frameworks, a GP trained on RVs alone and a GP pretrained on photometry and then applied to RVs, can influence the inferred physical and orbital parameters compared to a traditional Keplerian orbit fit. Our sample comprises 17 short-period giant planets orbiting stars that exhibit a broad range of activity levels. We find that the decision to adopt GPs, as well as the choice of GP framework, can result in variations of inferred parameters such as minimum planet mass and eccentricity by up to 67% and 95%, respectively. This implies that the method for modeling stellar activity in RVs of young planet-hosting stars can have widespread ramifications on the interpretation of planet properties including their masses, densities, circularization timescales, and tidal quality factors. When mitigating stellar activity with GPs, we recommend carrying out comparative tests between different models to assess the sensitivity of planet physical and orbital parameters to these choices., Comment: 37 pages, 23 Figures

Pain is a more intuitive and user-friendly way of communicating problems, making it especially useful in rehabilitation nurse training robots. While most previous methods have focused on classifying or recognizing pain expressions, these approaches often result in unnatural, jiggling robot faces. We introduce PainDiffusion, a model that generates facial expressions in response to pain stimuli, with controllable pain expressiveness and emotion status. PainDiffusion leverages diffusion forcing to roll out predictions over arbitrary lengths using a conditioned temporal U-Net. It operates as a latent diffusion model within EMOCA's facial expression latent space, ensuring a compact data representation and quick rendering time. For training data, we process the BioVid Heatpain Database, extracting expression codes and subject identity configurations. We also propose a novel set of metrics to evaluate pain expressions, focusing on expressiveness, diversity, and the appropriateness of model-generated outputs. Finally, we demonstrate that PainDiffusion outperforms the autoregressive method, both qualitatively and quantitatively. Code, videos, and further analysis are available at: \href{https://damtien444.github.io/paindf/}{https://damtien444.github.io/paindf/}., Comment: Under reviewing

The integration of power electronics building blocks in modern MVDC 12kV Naval ship systems enhances energy management and functionality but also introduces complex fault detection and control challenges. These challenges strain traditional fault diagnostic methods, making it difficult to detect and manage faults across multiple locations while maintaining system stability and performance. This paper proposes a temporal recurrent graph transformer network for fault diagnosis in naval MVDC 12kV shipboard systems. The deep graph neural network uses gated recurrent units to capture temporal features and a multi-head attention mechanism to extract spatial features, enhancing diagnostic accuracy. The approach effectively identifies and evaluates successive multiple faults with high precision. The method is implemented and validated on the MVDC 12kV shipboard system designed by the ESDRC team, incorporating all key components. Results show significant improvements in fault localization accuracy, with a 1-4% increase in performance metrics compared to other machine learning methods., Comment: 10 pages

We completely determine the asymptotic depth, equivalently, the asymptotic projective dimension of a chain of edge ideals that is invariant under the action of the monoid Inc of increasing functions on the positive integers. Our results and their proofs also reveal surprising combinatorial and topological properties of corresponding graphs and their independence complexes. In particular, we are able to determine the asymptotic behavior of all reduced homology groups of these independence complexes., Comment: 33 pages

The Von Neumann bottleneck, a fundamental challenge in conventional computer architecture, arises from the inability to execute fetch and data operations simultaneously due to a shared bus linking processing and memory units. This bottleneck significantly limits system performance, increases energy consumption, and exacerbates computational complexity. Emerging technologies such as Resistive Random Access Memories (RRAMs), leveraging crossbar arrays, offer promising alternatives for addressing the demands of data-intensive computational tasks through in-memory computing of analog vector-matrix multiplication (VMM) operations. However, the propagation of errors due to device and circuit-level imperfections remains a significant challenge. In this study, we introduce MELISO (In-Memory Linear Solver), a comprehensive end-to-end VMM benchmarking framework tailored for RRAM-based systems. MELISO evaluates the error propagation in VMM operations, analyzing the impact of RRAM device metrics on error magnitude and distribution. This paper introduces the MELISO framework and demonstrates its utility in characterizing and mitigating VMM error propagation using state-of-the-art RRAM device metrics., Comment: ICONS 2024.Copyright 2024 IEEE.Personal use of this material is permitted.Permission from IEEE must be obtained for all other uses,in any current or future media,including reprinting/republishing this material for advertising or promotional purposes,creating new collective works,for resale or redistribution to servers or lists or reuse of any copyrighted component of this work in other works

Data augmentation is a widely used technique for creating training data for tasks that require labeled data, such as semantic segmentation. This method benefits pixel-wise annotation tasks requiring much effort and intensive labor. Traditional data augmentation methods involve simple transformations like rotations and flips to create new images from existing ones. However, these new images may lack diversity along the main semantic axes in the data and not change high-level semantic properties. To address this issue, generative models have emerged as an effective solution for augmenting data by generating synthetic images. Controllable generative models offer a way to augment data for semantic segmentation tasks using a prompt and visual reference from the original image. However, using these models directly presents challenges, such as creating an effective prompt and visual reference to generate a synthetic image that accurately reflects the content and structure of the original. In this work, we introduce an effective data augmentation method for semantic segmentation using the Controllable Diffusion Model. Our proposed method includes efficient prompt generation using Class-Prompt Appending and Visual Prior Combination to enhance attention to labeled classes in real images. These techniques allow us to generate images that accurately depict segmented classes in the real image. In addition, we employ the class balancing algorithm to ensure efficiency when merging the synthetic and original images to generate balanced data for the training dataset. We evaluated our method on the PASCAL VOC datasets and found it highly effective for synthesizing images in semantic segmentation.

Audio-driven talking face generation is a widely researched topic due to its high applicability. Reconstructing a talking face using audio significantly contributes to fields such as education, healthcare, online conversations, virtual assistants, and virtual reality. Early studies often focused solely on changing the mouth movements, which resulted in outcomes with limited practical applications. Recently, researchers have proposed a new approach of constructing the entire face, including face pose, neck, and shoulders. To achieve this, they need to generate through landmarks. However, creating stable landmarks that align well with the audio is a challenge. In this paper, we propose the KFusion of Dual-Domain model, a robust model that generates landmarks from audio. We separate the audio into two distinct domains to learn emotional information and facial context, then use a fusion mechanism based on the KAN model. Our model demonstrates high efficiency compared to recent models. This will lay the groundwork for the development of the audio-driven talking face generation problem in the future.

Force and torque sensing is crucial in robotic manipulation across both collaborative and industrial settings. Traditional methods for dynamics identification enable the detection and control of external forces and torques without the need for costly sensors. However, these approaches show limitations in scenarios where robot dynamics, particularly the end-effector payload, are subject to changes. Moreover, existing calibration techniques face trade-offs between efficiency and accuracy due to concerns over joint space coverage. In this paper, we introduce a calibration scheme that leverages pre-trained Neural Network models to learn calibrated dynamics across a wide range of joint space in advance. This offline learning strategy significantly reduces the need for online data collection, whether for selection of the optimal model or identification of payload features, necessitating merely a 4-second trajectory for online calibration. This method is particularly effective in tasks that require frequent dynamics recalibration for precise contact estimation. We further demonstrate the efficacy of this approach through applications in sensorless joint and task compliance, accounting for payload variability., Comment: Accepted to Robotics and Automation Letters (RA-L), 8 pages

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

Recent millimeter and submillimeter observations have unveiled elongated and asymmetric structures around protostars. These structures, referred to as streamers, often exhibit coherent velocity gradients, seemingly indicating a directed gas flow towards the protostars. However, their origin and role in star formation remain uncertain. A protostellar core Per-emb-2, located in Barnard 1, has a relatively large streamer with $10^4$ au, which is more prominent in emission from carbon chain molecules. We aim to unveil the formation mechanism of this streamer. We conducted mapping observations towards Per-emb-2 using the NRO 45-m telescope. We targeted carbon chain molecular lines such as CCS, HC$_3$N, and HC$_5$N. Using astrodendro, we identified one protostellar and four starless cores, including three new detections, on the Herschel map. The starless and protostellar cores are more or less gravitationally bound. We discovered strong CCS and HC$_3$N emissions extending from the north to the south, appearing to bridge the gap between the protostellar core and the starless core north of it. This bridge spans $3\times 10^4$ au with the velocities from 6.5 to 7.0 km s$^{-1}$. The bridge has the velocity gradient opposite to the streamer. Thus, the streamer is unlikely to be connected to this bridge, suggesting that the streamer does not have an accretion origin. We propose that a collision between a spherical core and the filament has shaped the density structure in this region, consequently triggering star formation within the head-tail-shaped core. In this core-filament collision (CFC) scenario, the collision appears to have fragmented the filament into two structures. The streamer is a bow structure, while the bridge is a remnant of the shock-compressed filament. Thus, we conclude that the Per-emb-2 streamer does not significantly contribute to the mass accumulation towards the protostar., Comment: accepted by Astronomy and Astrophysics Letters