February 2024 arXiv papers — page 37

Mengen Luo, Chi Xu, Ercan Engin Kuruoglu

Performance degradation owing to data heterogeneity and low output interpretability are the most significant challenges faced by federated learning in practical applications. Personalized federated learning diverges from traditional approaches, as it no longer seeks to train a single model, but instead tailors a unique personalized model for each client. How

Ding-Bang Zhou, Kuang-Hong Gao, Meng-Fan Zhao, Zhi-Yan Jia

Layered transition metal chalcogenides have stimulated a wide research interest due to their many exotic physical properties. In this paper, we studied the magnetotransport properties of the exfoliated TaNiTe5, a recently discovered Dirac nodal-line semimetal. A giant positive magnetoresistance (MR) is observed when the current is parallel to the crystallogr

Natalija Mitic, Apostolos Pyrgelis, Sinem Sav

In this paper, we address the problem of privacy-preserving hyperparameter (HP) tuning for cross-silo federated learning (FL). We first perform a comprehensive measurement study that benchmarks various HP strategies suitable for FL. Our benchmarks show that the optimal parameters of the FL server, e.g., the learning rate, can be accurately and efficiently tu

Feng Lu, Shuting Dong, Lijun Zhang, Bingxi Liu

Visual place recognition (VPR) is a fundamental task for many applications such as robot localization and augmented reality. Recently, the hierarchical VPR methods have received considerable attention due to the trade-off between accuracy and efficiency. They usually first use global features to retrieve the candidate images, then verify the spatial consiste

Saswata Jana, Giuseppe F. Italiano, Manas Jyoti Kashyop, Athanasios L. Konstantinidis

Delivering a parcel from the distribution hub to the customer's doorstep is called the \textit{last-mile delivery} step in delivery logistics. In this paper, we study a hybrid {\it truck-drones} model for the last-mile delivery step, in which a truck moves on a predefined path carrying parcels and drones deliver the parcels. We define the \textsc{online dron

Hanna Abi Akl

We present a neuro-symbolic (NeSy) workflow combining a symbolic-based learning technique with a large language model (LLM) agent to generate synthetic data for code comment classification in the C programming language. We also show how generating controlled synthetic data using this workflow fixes some of the notable weaknesses of LLM-based generation and i

İhsan Ozan Yıldırım, Ege Keskin, Yağmur Kocaman, Murat Kuşcu

Selecting appropriate sensors and actuators is a pivotal aspect of design and engineering, particularly in projects involving interactive systems. This article introduces the Design Thinking Based Iterative Sensor and Actuator Selection Flow, a structured decision-making approach aimed at streamlining this essential, yet often complex task. Created to accomm

Quan-feng Wu, Xun-Jie Xu

The Primakoff process plays a crucial role in axion production in astrophysical environments and laboratories. Given the rising interest in axion physics and many on-going experimental activities, we conduct a comprehensive calculation of this process and carefully examine several aspects that have been neglected in the literature. In particular, our calcula

Yang Xu, Qiucan Huang, Shaojie Shen, Huan Yin

Radar SLAM is robust in challenging conditions, such as fog, dust, and smoke, but suffers from the sparsity and noisiness of radar sensing, including speckle noise and multipath effects. This study provides a performance-enhanced radar SLAM system by incorporating point uncertainty. The basic system is a radar-inertial odometry system that leverages velocity

Yang Li, Ya-Feng Liu

This paper studies the quality-of-service (QoS) constrained multi-group multicast beamforming design problem, where each multicast group is composed of a number of users requiring the same content. Due to the nonconvex QoS constraints, this problem is nonconvex and NP-hard. While existing optimization-based iterative algorithms can obtain a suboptimal soluti

Jipei Chen, Victor M. Calo, Quanling Deng

The recently proposed soft finite element method (SoftFEM) reduces the stiffness (condition numbers), consequently improving the overall approximation accuracy. The method subtracts a least-square term that penalizes the gradient jumps across mesh interfaces from the FEM stiffness bilinear form while maintaining the system's coercivity. Herein, we present tw

Yuta Nozaki, Tamás Kálmán, Masakazu Teragaito, Yuya Koda

We give a homotopy classification of the global defects in ordered media, and explain it via the example of biaxial nematic liquid crystals, i.e., systems where the order parameter space is the quotient of the $3$-sphere $S^3$ by the quaternion group $Q$. As our mathematical model we consider continuous maps from complements of spatial graphs to the space $S

Anson Bastos, Kuldeep Singh, Abhishek Nadgeri, Manish Singh

We present the Evolving Graph Fourier Transform (EFT), the first invertible spectral transform that captures evolving representations on temporal graphs. We motivate our work by the inadequacy of existing methods for capturing the evolving graph spectra, which are also computationally expensive due to the temporal aspect along with the graph vertex domain. W

Ruizhe Zhang, Qingyao Ai, Yiqun Liu, Yueyue Wu

In the last decade, legal case search has become an important part of a legal practitioner's work. During legal case search, search engines retrieval a number of relevant cases from huge amounts of data and serve them to users. However, it is uncertain whether these cases are gender-biased and whether such bias has impact on user perceptions. We designed a n

Nadav Dym, Hannah Lawrence, Jonathan W. Siegel

Canonicalization provides an architecture-agnostic method for enforcing equivariance, with generalizations such as frame-averaging recently gaining prominence as a lightweight and flexible alternative to equivariant architectures. Recent works have found an empirical benefit to using probabilistic frames instead, which learn weighted distributions over group

Zhonghang Li, Lianghao Xia, Jiabin Tang, Yong Xu

Spatio-temporal prediction aims to forecast and gain insights into the ever-changing dynamics of urban environments across both time and space. Its purpose is to anticipate future patterns, trends, and events in diverse facets of urban life, including transportation, population movement, and crime rates. Although numerous efforts have been dedicated to devel

Jiehua Mai, Enhui Shi, Kesong Yan, Fanping Zeng

For a disk $D$ in the plane $\mathbb R^2$ and a plane map $f$, we give several conditions on the restriction of $f$ to the boundary $\partial D$ of $D$ which imply the existence of a fixed point of $f$ in some specified domain in $D$. These conditions are similar to those appeared in the intermediate value theorem for maps on the real line. As an application

Kaiqi Chen, Eugene Lim, Kelvin Lin, Yiyang Chen

Imitation learning empowers artificial agents to mimic behavior by learning from demonstrations. Recently, diffusion models, which have the ability to model high-dimensional and multimodal distributions, have shown impressive performance on imitation learning tasks. These models learn to shape a policy by diffusing actions (or states) from standard Gaussian

Semeon Arthamonov, Leonid Chekhov, Philippe Di Francesco, Rinat Kedem

We construct an embedding of the Arthamonov-Shakirov algebra of genus 2 knot operators into the quantized coordinate ring of the cluster Poisson variety of exceptional finite mutation type $X_7$. The embedding is equivariant with respect to the action of the mapping class group of the closed surface of genus 2. The cluster realization of the mapping class gr

Kianoosh Kazemi, Iina Ryhtä, Iman Azimi, Hannakaisa Niela-Vilen

The concept of Quality of Life (QoL) refers to a holistic measurement of an individual's well-being, incorporating psychological and social aspects. Pregnant women, especially those with obesity and stress, often experience lower QoL. Physical activity (PA) has shown the potential to enhance the QoL. However, pregnant women who are overweight and obese rarel

Binyam Gebre, Karoliina Ranta, Stef van den Elzen, Ernst Kuiper

In personalized recommender systems, embeddings are often used to encode customer actions and items, and retrieval is then performed in the embedding space using approximate nearest neighbor search. However, this approach can lead to two challenges: 1) user embeddings can restrict the diversity of interests captured and 2) the need to keep them up-to-date re

Wenhui Cao, Erkun Yang, Jinjin Li, Guanhua She

This article demonstrates a new kind of programmable logic for the representation of an integer that can be used for the programmable Josephson voltage standard. It can enable the numbers of junctions in most bits to be variable integer values, which is different from normal binary logic or ternary logic. Consequently, missing junctions due to superconductin

A. C. Aguilar, M. N. Ferreira, J. Papavassiliou, L. R. Santos

To date, the four-gluon vertex is the least explored component of the QCD Lagrangian, mainly due to the vast proliferation of Lorentz and color structures required for its description. In this work we present a nonperturbative study of this vertex, based on the one-loop dressed Schwinger-Dyson equation obtained from the 4PI effective action. A vast simplific

Cheng-Lin Deng, Yu Liu, Yu-Ran Zhang, Xue-Gang Li

High-order topological phases of matter refer to the systems of $n$-dimensional bulk with the topology of $m$-th order, exhibiting $(n-m)$-dimensional boundary modes and can be characterized by topological pumping. Here, we experimentally demonstrate two types of second-order topological pumps, forming four 0-dimensional corner localized states on a 4$\times

Peter J. Forrester, Santosh Kumar

We consider the problem of the exact computation of the marginal eigenvalue distributions in the Laguerre and Jacobi $\beta$ ensembles. In the case $\beta=1$ this is a question of long standing in the mathematical statistics literature. A recursive procedure to accomplish this task is given for $\beta$ a positive integer, and the parameter $\lambda_1$ a non-

Luca Castri, Gloria Beraldo, Sariah Mghames, Marc Hanheide

Deploying robots in human-shared spaces requires understanding interactions among nearby agents and objects. Modelling cause-and-effect relations through causal inference aids in predicting human behaviours and anticipating robot interventions. However, a critical challenge arises as existing causal discovery methods currently lack an implementation inside t

Fumio Hiai

We are concerned with log-majorization for matrices in connection with the multivariate Golden--Thompson trace inequality and the Karcher mean (i.e., a multivariate extension of the weighted geometric mean). We show an extension of Araki's log-majorization and apply it to the $\alpha$-$z$-R\'enyi divergence in quantum information. We discuss the equality cas

Feng Liu, Leilei Zhang

The interaction between local traits and global frameworks of mathematical objects has long endured as a central theme in various mathematical domains. A graph \(G\) is referred to as locally linear provided that the subgraph induced by the neighborhood of each vertex is a path. Likewise, $G$ is said to be locally hamiltonian (or locally traceable) when ever

Aviad Rom, Kfir Bar

We train a bilingual Arabic-Hebrew language model using a transliterated version of Arabic texts in Hebrew, to ensure both languages are represented in the same script. Given the morphological, structural similarities, and the extensive number of cognates shared among Arabic and Hebrew, we assess the performance of a language model that employs a unified scr

Andrzej Krawiecki, Tomasz Gradowski

Approximate master equations are derived for the two-state $q$-voter model with independence on signed random graphs, with negative and positive weights of links corresponding to antagonistic and reinforcing interactions, respectively. Depending on the mean degree of nodes, the size of the $q$-neighborhood, and the fraction of the antagonistic links, with de

Weitao Li, Junkai Li, Weizhi Ma, Yang Liu

Large language models (LLMs) exhibit powerful general intelligence across diverse scenarios, including their integration into chatbots. However, a vital challenge of LLM-based chatbots is that they may produce hallucinated content in responses, which significantly limits their applicability. Various efforts have been made to alleviate hallucination, such as

Xuming Hu, Xiaochuan Li, Junzhe Chen, Yinghui Li

Generative search engines have the potential to transform how people seek information online, but generated responses from existing large language models (LLMs)-backed generative search engines may not always be accurate. Nonetheless, retrieval-augmented generation exacerbates safety concerns, since adversaries may successfully evade the entire system by sub

David Kalaj

Let $\alpha>-1$ and assume that $f$ is $\alpha-$harmonic mapping defined in the unit disk that belongs to the Hardy class $h^p$ with $p\ge 1$. We obtain some sharp estimates of the type $|f(z)|\le g(|r|) \|f^\ast\|_p$ and $|Df(z)|\le h(|r|)\|f^\ast\|_p$. We also prove a Schwarz type lemma for the class of $\alpha-$harmonic mappings of the unit disk onto itse

Tianjie Ju, Weiwei Sun, Wei Du, Xinwei Yuan

Previous work has showcased the intriguing capability of large language models (LLMs) in retrieving facts and processing context knowledge. However, only limited research exists on the layer-wise capability of LLMs to encode knowledge, which challenges our understanding of their internal mechanisms. In this paper, we devote the first attempt to investigate t

Tamali Mukherjee, V Satya Narayana Murthy

Skyrmions, which are topologically stable magnetic structures, have manifested promising features to be used as an information carrier in new-age, non-volatile data storage devices. In this article, Co/Pt square nano-structure with Co-free layer thickness in the range of 1 nm to 5 nm is taken to study the controlled creation of skyrmions. The magnetization d

Viv Bone, Chris van der Heide, Kieran Mackle, Ingo H. J. Jahn

Multifidelity models integrate data from multiple sources to produce a single approximator for the underlying process. Dense low-fidelity samples are used to reduce interpolation error, while sparse high-fidelity samples are used to compensate for bias or noise in the low-fidelity samples. Deep Gaussian processes (GPs) are attractive for multifidelity modell

Xinze Li, Zhenghao Liu, Chenyan Xiong, Shi Yu

Large language models (LLMs) require lengthy prompts as the input context to produce output aligned with user intentions, a process that incurs extra costs during inference. In this paper, we propose the Gist COnditioned deCOding (Gist-COCO) model, introducing a novel method for compressing prompts which also can assist the prompt interpretation and engineer

Jiaxin Huang, Jian Shen, Yilin Zheng, Zhigong Song

Although the multi-jointed underactuated manipulator is highly dexterous, its grasping capacity does not match that of the parallel jaw gripper. This work introduces a fractal gripper to enhance the grasping capacity of multi-joint underactuated manipulators, preserving their passive clamping features. We describe in detail the working principle and manufact

Ludovica Donati, Francesco Saverio Cataliotti, Stefano Gherardini

In a multi-level quantum system Fano coherences stand for the formation of quantum coherences due to the interaction with the continuum of modes characterizing an incoherent process. When the incoherent source vanishes, Fano coherences tend to disappear. In this paper we propose a V-type three-level quantum system on which we certify the presence of genuinel

Sebastiaan Selvi, Oliver Porth, Bart Ripperda, Lorenzo Sironi

We study the magnetospheric evolution of a non-accreting spinning black hole (BH) with an initially inclined split monopole magnetic field by means of three-dimensional general relativistic magnetohydrodynamics simulations. This serves as a model for a neutron star (NS) collapse or a BH-NS merger remnant after the inherited magnetosphere has settled into a s

Konrad Marosek, Adam Balcerzak

In this paper, we explore the conformal structure of singularities arising from varying fundamental constants using the method of Penrose diagrams. We employ a specific type of bimetric model featuring two different metrics. One metric describes the causal structure for matter, while the other characterizes the causal structure for gravitational interactions

Kai Xu, Yeqing Zhou, Liping Zhu, Runze Li

Testing for independence between two random vectors is a fundamental problem in statistics. It is observed from empirical studies that many existing omnibus consistent tests may not work well for some strongly nonmonotonic and nonlinear relationships. To explore the reasons behind this issue, we novelly transform the multivariate independence testing problem

Abdenacer Naouri, Huansheng Ning, Nabil Abdelkader Nouri, Amar Khelloufi

In disaster scenarios and high-stakes rescue operations, integrating Unmanned Aerial Vehicles (UAVs) as fog nodes has become crucial. This integration ensures a smooth connection between affected populations and essential health monitoring devices, supported by the Internet of Things (IoT). Integrating UAVs in such environments is inherently challenging, whe

Ying Zhang, Guangzhao He, Quanxing Ye, Da-Cheng Yan

The structure of light diquarks plays a crucial role in the formation of exotic hadrons beyond the conventional quark model, especially in their line shapes of bottomed hadron decays. We study the two-body hadronic weak decays of bottomed baryons and bottomed mesons to probe the light diquark structure and pin down the quark-quark correlations in the diquark

Yuxuan Wang, Yueqian Wang, Pengfei Wu, Jianxin Liang

Despite progress in multimodal large language models (MLLMs), the challenge of interpreting long-form videos in response to linguistic queries persists, largely due to the inefficiency in temporal grounding and limited pre-trained context window size. In this work, we introduce Temporal Grounding Bridge (TGB), a novel framework that bootstraps MLLMs with adv

Jun Lu, Wan-Yuan Xu

In this paper, we prove a conjecture of Schnell in the surface case.

Guangsheng Bao, Hongbo Zhang, Cunxiang Wang, Linyi Yang

Chain-of-thought emerges as a promising technique for eliciting reasoning capabilities from Large Language Models (LLMs). However, it does not always improve task performance or accurately represent reasoning processes, leaving unresolved questions about its usage. In this paper, we diagnose the underlying mechanism by comparing the reasoning process of LLMs

Prajnanaswaroopa S

In this paper, we try to determine exact or bounds on the choosability, or list chromatic numbers of some Cayley graphs, typically some Unitary Cayley graphs and Cayley graphs on Dihedral groups.

Muhammad Sajjad Ansar, Bilal Farooq

The safe transition from conditional automation to manual driving control is significantly intertwined with the vehicle's lateral and longitudinal dynamics. The transition may occur as a result of a system-initiated mandatory takeover (MTOR) or as a driver-initiated discretionary takeover (DTOR). In either condition, the takeover process entails differing co

Hamidreza Kasaei, Mohammadreza Kasaei

In this work, we delve into the intricate synergy among non-prehensile actions like pushing, and prehensile actions such as grasping and throwing, within the domain of robotic manipulation. We introduce an innovative approach to learning these synergies by leveraging model-free deep reinforcement learning. The robot's workflow involves detecting the pose of

Adnan A. E. Hajomer, Ivan Derkach, Radim Filip, Ulrik L. Andersen

Building scalable and secure quantum networks with many users has a high application potential but also holds many practical challenges. A significant stride in this pursuit involves extending quantum key distribution, an information-theoretically secure method for establishing cryptographic keys between two distant users, from a point-to-point protocol impl

Jiahui Xiang, Lirong Fu, Tong Ye, Peiyu Liu

The diversity of web configuration interfaces for IoT devices has exacerbated issues such as inadequate permission controls and insecure interfaces, resulting in various vulnerabilities. Owing to the varying interface configurations across various devices, the existing methods are inadequate for identifying these vulnerabilities precisely and comprehensively

Abdelkader Hidki, Abderrahim Lakhfif, Mostafa Nassik, Rizwan Ahmed

In the two microwave (MW) cross-shaped cavity magnon system, we describe a method to produce multipartite entanglement and quantum steering. To achieve squeezed states of the magnons, a Josephson parametric amplifier (JPA) creates a squeezed vacuum field that drives the two cavities. We theoretically demonstrate that the cavity-cavity entanglement can be gen

Shuhai Zhang, Yiliao Song, Jiahao Yang, Yuanqing Li

Large language models (LLMs) such as ChatGPT have exhibited remarkable performance in generating human-like texts. However, machine-generated texts (MGTs) may carry critical risks, such as plagiarism issues, misleading information, or hallucination issues. Therefore, it is very urgent and important to detect MGTs in many situations. Unfortunately, it is chal

Sunjun Kweon, Jiyoun Kim, Heeyoung Kwak, Dongchul Cha

Discharge summaries in Electronic Health Records (EHRs) are crucial for clinical decision-making, but their length and complexity make information extraction challenging, especially when dealing with accumulated summaries across multiple patient admissions. Large Language Models (LLMs) show promise in addressing this challenge by efficiently analyzing vast a

Bo Liu, Grace Li Zhang, Xunzhao Yin, Ulf Schlichtmann

Deep neural networks (DNNs) have achieved great breakthroughs in many fields such as image classification and natural language processing. However, the execution of DNNs needs to conduct massive numbers of multiply-accumulate (MAC) operations on hardware and thus incurs a large power consumption. To address this challenge, we propose a novel digital MAC desi

Zihan Liu, Han Li, Anfan Chen, Renwen Zhang

Conversational Agents (CAs) have increasingly been integrated into everyday life, sparking significant discussions on social media. While previous research has examined public perceptions of AI in general, there is a notable lack in research focused on CAs, with fewer investigations into cultural variations in CA perceptions. To address this gap, this study

Shuning Huo, Yafei Xiang, Hanyi Yu, Mengran Zhu

In recent years, advancements in natural language processing (NLP) have been fueled by deep learning techniques, particularly through the utilization of powerful computing resources like GPUs and TPUs. Models such as BERT and GPT-3, trained on vast amounts of data, have revolutionized language understanding and generation. These pre-trained models serve as r

Camille L Latune, Cyril Elouard

Considering a general microscopic model for a quantum measuring apparatus comprising a quantum probe coupled to a thermal bath, we analyze the energetic resources necessary for the realization of a quantum measurement, which includes the creation of system-apparatus correlations, the irreversible transition to a statistical mixture of definite outcomes, and

Hanyi Yu, Shuning Huo, Mengran Zhu, Yulu Gong

In recent years, the expansion of internet technology and advancements in automation have brought significant attention to autonomous driving technology. Major automobile manufacturers, including Volvo, Mercedes-Benz, and Tesla, have progressively introduced products ranging from assisted-driving vehicles to semi-autonomous vehicles. However, this period has

Yafei Xiang, Hanyi Yu, Yulu Gong, Shuning Huo

With the rapid development of artificial intelligence technology, Transformer structural pre-training model has become an important tool for large language model (LLM) tasks. In the field of e-commerce, these models are especially widely used, from text understanding to generating recommendation systems, which provide powerful technical support for improving

Siddhanth Bhat

Detecting emotions in limited text datasets from under-resourced languages presents a formidable obstacle, demanding specialized frameworks and computational strategies. This study conducts a thorough examination of deep learning techniques for discerning emotions in short English texts. Deep learning approaches employ transfer learning and word embedding, n

Baiang Li, Zhao Zhang, Huan Zheng, Xiaogang Xu

Transformer-based Single Image Deraining (SID) methods have achieved remarkable success, primarily attributed to their robust capability in capturing long-range interactions. However, we've noticed that current methods handle rain-affected and unaffected regions concurrently, overlooking the disparities between these areas, resulting in confusion between rai

Laiwen Yu, Yurui Li, Hengtai Xiang, Yuanrong Li

Silicon photonics with the advantages of low power consumption, low cost, and high yield is a crucial technology for facilitating high-capacity optical communications and interconnects. The graphene photodetectors (GPDs) featuring broadband operation, high speed, and low integration cost can be good additions to the conventional SiGe photodetectors, supporti

Liangsheng Li, Maoxin Liu, Wen-Long You, Chengjie Zhang

In this study, we explore an approach aimed at enhancing the transmission or reflection coefficients of absorbing materials through the utilization of joint measurements of entangled photon states. On the one hand, through the implementation of photon catalysis in the reflected channel, we can effectively modify the state of the transmission channel, leading

Xin Mao, Feng-Lin Li, Huimin Xu, Wei Zhang

While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large Language Models (LLMs), recent studies have raised concerns regarding the complexity and instability associated with the Proximal Policy Optimization (PPO) algorithm, proposing a series of order-based calibration methods as viable alternatives. This

Nuo Chen, Yuhan Li, Jianheng Tang, Jia Li

Large language models (LLMs) have achieved impressive success across several fields, but their proficiency in understanding and resolving complex graph problems is less explored. To bridge this gap, we introduce GraphInstruct, a novel and comprehensive instruction-tuning dataset designed to equip language models with the ability to tackle a broad spectrum of

Xinpeng Ling, Jie Fu, Kuncan Wang, Huifa Li

Federated learning (FL) is an emerging machine learning paradigm designed to address the challenge of data silos, attracting considerable attention. However, FL encounters persistent issues related to fairness and data privacy. To tackle these challenges simultaneously, we propose a fairness-aware federated learning algorithm called FedFair. Building on FedF

Yuang Chen, Hancheng Lu, Chenwu Zhang, Yansha Deng

Massive interconnection has sparked people's envisioning for next-generation ultra-reliable and low-latency communications (xURLLC), prompting the design of customized next-generation advanced transceivers (NGAT). Rate-splitting multiple access (RSMA) has emerged as a pivotal technology for NGAT design, given its robustness to imperfect channel state informa

Zhenxing Zhang, Jun Ge, Zheng Wei, Chunjie Zhou

The goal of feature selection is to choose the optimal subset of features for a recognition task by evaluating the importance of each feature, thereby achieving effective dimensionality reduction. Currently, proposed feature selection methods often overlook the discriminative dependencies between features and labels. To address this problem, this paper intro

Yihao Chen, Qilei Yin, Qi Li, Zhuotao Liu

BGP is the de facto inter-domain routing protocol to ensure global connectivity of the Internet. However, various reasons, such as deliberate attacks or misconfigurations, could cause BGP routing anomalies. Traditional methods for BGP routing anomaly detection require significant manual investigation of routes by network operators. Although machine learning

Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi

Heterogeneous graph learning aims to capture complex relationships and diverse relational semantics among entities in a heterogeneous graph to obtain meaningful representations for nodes and edges. Recent advancements in heterogeneous graph neural networks (HGNNs) have achieved state-of-the-art performance by considering relation heterogeneity and using spec

Yonatan Gershuni, Itai Epstein

Polaritons are quasi-particles describing the coupling between a photon and a material excitation, which can carry large momentum and confine electromagnetic fields to small dimensions, enabling strong light-matter interactions. In the visible (VIS) to near-infrared (NIR) spectral ranges, the intraband response of metals gives rise to surface-plasmon-polarit

Xiaohan Lei, Min Wang, Wengang Zhou, Li Li

As a new embodied vision task, Instance ImageGoal Navigation (IIN) aims to navigate to a specified object depicted by a goal image in an unexplored environment. The main challenge of this task lies in identifying the target object from different viewpoints while rejecting similar distractors. Existing ImageGoal Navigation methods usually adopt the simple Exp

Xiangyu Hua, Zimeng Zeng, Fanbao Meng, Hongxu Yao

The intimate connection between magnetism and superconducting pairing routinely plays a central role in determining the occurrence of unconventional superconducting states. In high-transition-temperature (high-Tc) stripe-ordered cuprate superconductors and a magnetically ordered iron-based superconductor, the coupling between magnetism and superconductivity

Minsu Kim, Jee-weon Jung, Hyeongseop Rha, Soumi Maiti

The capability to jointly process multi-modal information is becoming an essential task. However, the limited number of paired multi-modal data and the large computational requirements in multi-modal learning hinder the development. We propose a novel Tri-Modal Translation (TMT) model that translates between arbitrary modalities spanning speech, image, and t

Yu-Hsueh Fang, He-Zhe Lin, Jie-Jyun Liu, Chih-Jen Lin

Automatic differentiation is a key component in deep learning. This topic is well studied and excellent surveys such as Baydin et al. (2018) have been available to clearly describe the basic concepts. Further, sophisticated implementations of automatic differentiation are now an important part of popular deep learning frameworks. However, it is difficult, if

Yujie Feng, Huizi Liu, Yingge Huang, Fuchang Gu

Background: The understanding of the impact of initial deformation and collision orientation on quasi-fission and fusion-fission reactions remains incomplete. Purpose: This article aims to explore how the orientation of deformed nuclei influences quasi-fission and fusion-fission around 1.2 VB, employing a micro dynamical method in systems with diverse shapes

Keyu Xing, Weikai Zong, Roberto Silvotti, Jian-Ning Fu

Stellar flares are critical phenomena on stellar surfaces, which are closely tied to stellar magnetism. While extensively studied in main-sequence (MS) stars, their occurrence in evolved compact stars, specifically hot subdwarfs and white dwarfs (WDs), remains scarcely explored. Based on Cycles 1-5 of TESS photometry, we conducted a pioneering survey of flar

Ali Ebrahimpour Boroojeny, Matus Telgarsky, Hari Sundaram

We show the effectiveness of automatic differentiation in efficiently and correctly computing and controlling the spectrum of implicitly linear operators, a rich family of layer types including all standard convolutional and dense layers. We provide the first clipping method which is correct for general convolution layers, and illuminate the representational

Robert Bredereck, Junjie Luo

Judgment aggregation is a framework to aggregate individual opinions on multiple, logically connected issues into a collective outcome. These opinions are cast by judges, which can be for example referees, experts, advisors or jurors, depending on the application and context. It is open to manipulative attacks such as \textsc{Manipulation} where judges cast

Frank Barrows, Forrest C. Sheldon, Francesco Caravelli

Networks with memristive devices are a potential basis for the next generation of computing devices. They are also an important model system for basic science, from modeling nanoscale conductivity to providing insight into the information-processing of neurons. The resistance in a memristive device depends on the history of the applied bias and thus displays

Tianyu Chen, Haoyi Zhou, Ying Li, Hao Wang

Foundation models have revolutionized language modeling, while whether this success is replicated in scientific computing remains unexplored. We present OmniArch, the first prototype aiming at solving multi-scale and multi-physics scientific computing problems with physical alignment. We addressed all three challenges with one unified architecture. Its pre-t

Sahal Shaji Mullappilly, Abhishek Singh Gehlot, Rao Muhammad Anwer, Fahad Shahbaz Khan

Conventional open-world object detection (OWOD) problem setting first distinguishes known and unknown classes and then later incrementally learns the unknown objects when introduced with labels in the subsequent tasks. However, the current OWOD formulation heavily relies on the external human oracle for knowledge input during the incremental learning stages.

Sheng Wang, Liheng Chen, Jiyue Jiang, Boyang Xue

With the remarkable capabilities, large language models (LLMs) have emerged as essential elements in numerous NLP applications, while parameter-efficient finetuning, especially LoRA, has gained popularity as a lightweight approach for model customization. Meanwhile, various dropout methods, initially designed for full finetuning with all the parameters updat

Mulin Chen, Bocheng Wang, Xuelong Li

Graph Convolutional Network (GCN) has exhibited remarkable potential in improving graph-based clustering. To handle the general clustering scenario without a prior graph, these models estimate an initial graph beforehand to apply GCN. Throughout the literature, we have witnessed that 1) most models focus on the initial graph while neglecting the original fea

Mingyang Xu, Hanzhong Wu, Jiawen Zhi, Yang Liu

Laser frequency combs, which are composed of a series of equally-spaced coherent frequency components, have triggered revolutionary progress for precision spectroscopy and optical metrology. Length/distance is of fundamental importance in both science and technology. In this work, we describe a ranging scheme based on chirped pulse interferometry. In contras

Sergey Pankov

Some mechanical systems, that are modeled to have inelastic collisions, nonetheless possess energy-conserving intermittent-contact solutions, known as collisionless solutions. Such a solution, representing a persistent hopping or walking across a level ground, may be important for understanding animal locomotion or for designing efficient walking machines. S

Fanjin Zhang, Kun Cao, Yukuo Cen, Jifan Yu

Tracing the source of research papers is a fundamental yet challenging task for researchers. The billion-scale citation relations between papers hinder researchers from understanding the evolution of science efficiently. To date, there is still a lack of an accurate and scalable dataset constructed by professional researchers to identify the direct source of

Yasmine Mustafa, Tie Luo

The evolution of deep learning and artificial intelligence has significantly reshaped technological landscapes. However, their effective application in crucial sectors such as medicine demands more than just superior performance, but trustworthiness as well. While interpretability plays a pivotal role, existing explainable AI (XAI) approaches often do not re

Ishmael N. Amartey, Andreas A. Linninger, Thomas Ventimiglia

Cerebral blood flow and perfusion can be estimated using tracer dilution experiments. Accurate estimation of blood flow parameters is a crucial part of medical imaging for effective diagnosis and treatment. This study explores two themes: (i) the derivation of the gamma variate function as a response tracer infusion and (ii) the estimation of impulse and res

Hao Wang, Hao Li, Minlie Huang, Lei Sha

The safety defense methods of Large language models(LLMs) stays limited because the dangerous prompts are manually curated to just few known attack types, which fails to keep pace with emerging varieties. Recent studies found that attaching suffixes to harmful instructions can hack the defense of LLMs and lead to dangerous outputs. However, similar to tradit

Xiaohui Chen, Tie Luo

In the field of Medical Imaging, extensive research has been dedicated to leveraging its potential in uncovering critical diagnostic features in patients. Artificial Intelligence (AI)-driven medical diagnosis relies on sophisticated machine learning and deep learning models to analyze, detect, and identify diseases from medical images. Despite the remarkable

Vyacheslav M. Abramov

For a class of irreducible Markov chains with an infinitely countable set of states, we establish a new verifiable necessary and sufficient condition for recurrence and transience. We show that if one of the basic assumptions is not satisfied, then the statement of the theorem becomes invalid.

Chunxi Wang, Maoshen Jia, Meiran Li, Changchun Bao

Dynamic parameterization of acoustic environments has drawn widespread attention in the field of audio processing. Precise representation of local room acoustic characteristics is crucial when designing audio filters for various audio rendering applications. Key parameters in this context include reverberation time (RT60) and geometric room volume. In recent

Lekai Song, Pengyu Liu, Jingfang Pei, Yang Liu

The demand for efficient edge vision has spurred the interest in developing stochastic computing approaches for performing image processing tasks. Memristors with inherent stochasticity readily introduce probability into the computations and thus enable stochastic image processing computations. Here, we present a stochastic computing approach for edge detect

Abel C. H. Chen

In recent years, quantum computers and Shor quantum algorithm have posed a threat to current mainstream asymmetric cryptography methods (e.g. RSA and Elliptic Curve Cryptography (ECC)). Therefore, it is necessary to construct a Post-Quantum Cryptography (PQC) method to resist quantum computing attacks. Therefore, this study proposes a PQC-based neural networ

Huan Ni, Yubin Zhao, Haiyan Guan, Cheng Jiang

Large-scale high-resolution land cover classification is a prerequisite for constructing Earth system models and addressing ecological and resource issues. Advancements in satellite sensor technology have led to an improvement in spatial resolution and wider coverage areas. Nevertheless, the lack of high-resolution labeled data is still a challenge, hinderin

Srinivas Eswar, Vishwas Rao, Arvind K. Saibaba

This paper tackles optimal sensor placement for Bayesian linear inverse problems, a popular version of the more general Optimal Experimental Design (OED) problem, using the D-optimality criterion. This is done by establishing connections between sensor placement and Column Subset Selection Problem (CSSP), which is a well-studied problem in Numerical Linear A

Yining Hu, Xu Wang, Chen Chen, Qingle Zhang

Conventional magnetic domain walls are characterized by reorientation of local spins. However, what occurs at the boundary of itinerant magnets is largely unknown. Here using spin-sensitive scanning tunneling microscopy, we investigated the microscopic domain wall structure of the spin-density-wave (SDW) state in a prototypical itinerant antiferromagnet - ch