December 2024 arXiv papers — page 135

Bao Wang

We introduce a family of generalizations of the pentagram maps related to $Q$-nets. A specific example is considered, and we find the map can be treated as a refactorization mapping in the Poisson-Lie group of pseudo-difference operators. This method was firstly proposed by Izosimov, and we generalize it to fit our needs. Using this description, we obtain th

Yuxi Li, Zhibo Zhang, Kailong Wang, Ling Shi

Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly jailbreak attacks. Current jailbreak techniques, while effective, often depend on input modifications, making them detectable and limiting their stealth and scalability. This paper p

Gopi Raju Matta, Rahul Siddartha, Rongali Simhachala Venkata Girish, Sumit Sharma

Flare, an optical phenomenon resulting from unwanted scattering and reflections within a lens system, presents a significant challenge in imaging. The diverse patterns of flares, such as halos, streaks, color bleeding, and haze, complicate the flare removal process. Existing traditional and learning-based methods have exhibited limited efficacy due to their

Alexander Mikhalychev, Saif Almazrouei, Svetlana Mikhalycheva, Abdellatif Bouchalkha

Advanced super-resolution imaging techniques require specific approaches for accurate and consistent estimation of the achievable spatial resolution. Fisher information supplied to Cramer-Rao bound (CRB) has proved to be a powerful and efficient tool for resolution analysis and optical setups optimization. However, the standard CRB is not applicable to const

Wenxuan Sun, Zixuan Yang, Yunli Wang, Zhen Zhang

Advertising systems often face the multi-domain challenge, where data distributions vary significantly across scenarios. Existing domain adaptation methods primarily focus on building domain-adaptive neural networks but often rely on hand-crafted domain information, e.g., advertising placement, which may be sub-optimal. We think that fine-grained "domain" pa

Myung-Joon Kwon, Wonjun Lee, Seung-Hun Nam, Minji Son

Most techniques approach the problem of image forgery localization as a binary segmentation task, training neural networks to label original areas as 0 and forged areas as 1. In contrast, we tackle this issue from a more fundamental perspective by partitioning images according to their originating sources. To this end, we propose Segment Any Forged Image Reg

Phan Phuong Mai Chau, Souhail Bakkali, Antoine Doucet

Abstractive summarization has made significant strides in condensing and rephrasing large volumes of text into coherent summaries. However, summarizing administrative documents presents unique challenges due to domain-specific terminology, OCR-generated errors, and the scarcity of annotated datasets for model fine-tuning. Existing models often struggle to ad

Zitong Chen, Chao Sun, Shida Nie, Chen Min

Off-road environments remain significant challenges for autonomous ground vehicles, due to the lack of structured roads and the presence of complex obstacles, such as uneven terrain, vegetation, and occlusions. Traditional perception algorithms, primarily designed for structured environments, often fail in unstructured scenarios. In this paper, traversable a

Yurong Liu, Eduardo Pena, Aecio Santos, Eden Wu

Recent advances in language models opened new opportunities to address complex schema matching tasks. Schema matching approaches have been proposed that demonstrate the usefulness of language models, but they have also uncovered important limitations: Small language models (SLMs) require training data (which can be both expensive and challenging to obtain),

Xuanze Chen, Jiajun Zhou, Shanqing Yu, Qi Xuan

Graph neural networks excel at graph representation learning but struggle with heterophilous data and long-range dependencies. And graph transformers address these issues through self-attention, yet face scalability and noise challenges on large-scale graphs. To overcome these limitations, we propose GNNMoE, a universal model architecture for node classifica

Maysam Yousefian, Mehrdad Farhoudi

First, we explain some ambiguities of spacetime and metric field as fundamental concepts. Then, from the Unruh effect point of view and using the Gelfand-Naimark-Segal construction, we construct an operator as a quanta of acceleration that we call quantum acceleration operator (QAO). Thereupon, we investigate the relation between the vacuum of two different

Sofia Kankkunen, Merja Tornikoski, Talvikki Hovatta

In this study, we demonstrate some of the caveats in common statistical methods used for analysing astronomical variability timescales. We consider these issues specifically in the context of active galactic nuclei (AGNs) and use a more practical approach compared to mathematics literature, where the number of formulae may sometimes be overwhelming. We condu

Sofia Kankkunen, Merja Tornikoski, Talvikki Hovatta, Anne Lähteenmäki

We present the results of analysing the long-term radio variability of active galactic nuclei at 37 GHz using data of 123 sources observed in the Aalto University Mets\"ahovi Radio Observatory. Our aim was to constrain the characteristic timescales of the studied sources and to analyse whether up to 42 years of monitoring was enough to describe their variabi

M. Lemoine-Goumard, F. Acero, J. Ballet, M. Miceli

The supernova remnant SN 1006 is a source of high-energy particles detected at radio, X-rays, and tera-electronvolt gamma rays. It was also announced as a source of gamma rays by Fermi-LAT but only the north-east (NE) limb was detected at more than $5\sigma$ significance level. Using 15 years of Fermi-LAT observation and a thorough morphological analysis abo

Xin Chen, Liujuan Cao, Shengchuan Zhang, Xiewu Zheng

Due to the scarcity and unpredictable nature of defect samples, industrial anomaly detection (IAD) predominantly employs unsupervised learning. However, all unsupervised IAD methods face a common challenge: the inherent bias in normal samples, which causes models to focus on variable regions while overlooking potential defects in invariant areas. To effectiv

Kaiwei Zhang, Dandan Zhu, Xiongkuo Min, Guangtao Zhai

Textured meshes significantly enhance the realism and detail of objects by mapping intricate texture details onto the geometric structure of 3D models. This advancement is valuable across various applications, including entertainment, education, and industry. While traditional mesh saliency studies focus on non-textured meshes, our work explores the complexi

Thibault Prouteau, Nicolas Dugué, Simon Guillot

Modelling information from complex systems such as humans social interaction or words co-occurrences in our languages can help to understand how these systems are organized and function. Such systems can be modelled by networks, and network theory provides a useful set of methods to analyze them. Among these methods, graph embedding is a powerful tool to sum

Dinesh Parthasarathy, Tommaso Bevilacqua, Martin Lanser, Axel Klawonn

Multigrid methods are asymptotically optimal algorithms ideal for large-scale simulations. But, they require making numerous algorithmic choices that significantly influence their efficiency. Unlike recent approaches that learn optimal multigrid components using machine learning techniques, we adopt a complementary strategy here, employing evolutionary algor

Houjiang Liu, Jacek Gwizdka, Matthew Lease

Given the volume of potentially false claims online, claim prioritization is essential in allocating limited human resources available for fact-checking. In this study, we perceive claim prioritization as an information retrieval (IR) task: just as multidimensional IR relevance, with many factors influencing which search results a user deems relevant, checkw

Xiang-Qiong Liu

In the SU(3) Nambu-Jona-Lasinio (NJL) model of a thermally magnetized medium, the regularization methods adopted for the thermodynamic potential and the mass gap equation are utilized to calculate the relevant thermodynamic quantities in thermomagnetic quark matter. When dealing with the thermodynamic quantities and the gap equation, three schemes can be cho

Jiawei Zhang, Weipeng Zhang, Tengji Xu, Lei Xu

CMOS-compatible photonic integrated circuits (PICs) are emerging as a promising platform in artificial intelligence (AI) computing. Owing to the compact footprint of microring resonators (MRRs) and the enhanced interconnect efficiency enabled by wavelength division multiplexing (WDM), MRR-based photonic neural networks (PNNs) are particularly promising for l

Masashi Kawahira, Tomohiro Shigemura

In field theory, one can consider a variety of states. Within the framework of factorization algebras, one typically works with the natural augmentation state $\langle-\rangle_{\rm aug}$. In physics, however, other states arise naturally, such as the compactification state $\langle-\rangle_{\rm cptf}$ or the Schwartz state $\langle-\rangle_{\rm Sch}$, define

Cecilia Pagliantini

We consider the vorticity formulation of the Euler equations describing the flow of a two-dimensional incompressible ideal fluid on the sphere. Zeitlin's model provides a finite-dimensional approximation of the vorticity formulation that preserves the underlying geometric structure: it consists of an isospectral Lie--Poisson flow on the Lie algebra of skew-H

Jakub Lukeš, Věra Hájková, Martina Hlubučková, Vít Kanclíř

Optical coating, an integral part of many optical systems, is prone to damage from environmental exposure and laser irradiation. This underscores the need for reliable and sensitive coating diagnostics. We introduce second harmonic generation (SHG) as a method for the sensitive detection of defects and inhomogeneities within optical thin films. We demonstrat

SeungBum Ha, Taehwan Lee, Jiyoun Lim, Sung Whan Yoon

Federated learning (FL) enables decentralized training while preserving data privacy, yet existing FL benchmarks address relatively simple classification tasks, where each sample is annotated with a one-hot label. However, little attention has been paid to demonstrating an FL benchmark that handles complicated semantics, where each sample encompasses diverse

Jia Zhou, Jin Yan

A digraph $D$ is $k$-linked if for every $2k$-tuple $ x_1,\ldots , x_k, y_1, \ldots , y_k$ of distinct vertices in $D$, there exist $k$ pairwise vertex-disjoint paths $P_1,\ldots, P_k$ such that $P_i$ starts at $x_i$ and ends at $y_i$, $i\in [k]$. In 2015, Pokrovskiy conjectured that there exists a function $g(k)$ such that every $2k$-connected tournament wi

Xin Dong, Sen Jia, Ming Rui Wang, Yan Li

Recently, with the emergence of recent Multimodal Large Language Model (MLLM) technology, it has become possible to exploit its video understanding capability on different classification tasks. In practice, we face the difficulty of huge requirements for GPU resource if we need to deploy MLLMs online. In this paper, we propose COEF-VQ, a novel cascaded MLLM

Hai-Thien To, Tien-Cuong Bui, Van-Duc Le

Financial analysis relies heavily on the interpretation of earnings reports to assess company performance and guide decision-making. Traditional methods for generating such analyzes require significant financial expertise and are often time-consuming. With the rapid advancement of Large Language Models (LLMs), domain-specific adaptations have emerged for fin

Sahani Pathiraja, Philipp Wacker

The replicator-mutator equation is a model for populations of individuals carrying different traits, with a fitness function mediating their ability to replicate, and a stochastic model for mutation. We derive analytical solutions for the replicator-mutator equation in continuous time and for continuous traits for a quadratic fitness function. Using these re

Chengze Du, Jibin Shi, Hui Xu, Guangzhen Yao

Network tomography plays a crucial role in network monitoring and management, where network topology serves as the fundamental basis for various tomography tasks including traffic matrix estimation and link performance inference. The topology information, however, can be inferred through end-to-end measurements using various inference algorithms, posing sign

Jingjing Xie, Yuxin Zhang, Jun Peng, Zhaohong Huang

Despite the efficiency of prompt learning in transferring vision-language models (VLMs) to downstream tasks, existing methods mainly learn the prompts in a coarse-grained manner where the learned prompt vectors are shared across all categories. Consequently, the tailored prompts often fail to discern class-specific visual concepts, thereby hindering the tran

Huminhao Zhu, Fangyikang Wang, Tianyu Ding, Qing Qu

Training with synthetic data is becoming increasingly inevitable as synthetic content proliferates across the web, driven by the remarkable performance of recent deep generative models. This reliance on synthetic data can also be intentional, as seen in Rectified Flow models, whose Reflow method iteratively uses self-generated data to straighten the flow and

Zihao Li, Lecheng Zheng, Bowen Jin, Dongqi Fu

While great success has been achieved in building vision models with Contrastive Language-Image Pre-training (CLIP) over internet-scale image-text pairs, building transferable Graph Neural Networks (GNNs) with CLIP pipeline is challenging because of the scarcity of labeled data and text supervision, different levels of downstream tasks, and the conceptual ga

Wenxiu Yang, Laura Wolz, Yichao Li, Wenkai Hu

We present the calibration procedures and validation of source measurement with the data of the Commensal Radio Astronomy FAST Survey (CRAFTS) for \HI intensity mapping by the Five-hundred-meter Aperture Spherical Radio Telescope (FAST). Using 70-hour drift-scan observation with the L-band (1.05-1.45GHz) 19-beam receiver, we obtain the data covering $270\,\r

Yuanyuan Zhang, Han Xue, Kachong Lao, Chonkit Chan

This work investigates the exponential stability of neural networks (NNs) systems with time delays. By considering orthogonal polynomials with weighted terms, a new weighted integral inequality is presented. This inequality extend several recently established results. Additionally, based on the reciprocally convex inequality, this study focuses on analyzing

Xin-Cheng Wen, Jiaxin Ye, Cuiyun Gao, Lianwei Wu

Software Vulnerability (SV) assessment is a crucial process of determining different aspects of SVs (e.g., attack vectors and scope) for developers to effectively prioritize efforts in vulnerability mitigation. It presents a challenging and laborious process due to the complexity of SVs and the scarcity of labeled data. To mitigate the above challenges, we i

Sandeep K. Rout, Teo Munoz-Darias, Jeroen Homan, Montserrat Armas Padilla

Low-mass X-ray binaries with a neutron star as the primary object show a complex array of phenomenology during outbursts. The observed variability in X-ray emission primarily arises from changes in the innermost regions of the accretion disk, neutron star surface, and corona. In this work, we present the results of a comprehensive X-ray spectral and timing a

Sihan Chen, Zhuangzhuang Qian, Wingchun Siu, Xingcan Hu

Outlier detection (OD), also known as anomaly detection, is a critical machine learning (ML) task with applications in fraud detection, network intrusion detection, clickstream analysis, recommendation systems, and social network moderation. Among open-source libraries for outlier detection, the Python Outlier Detection (PyOD) library is the most widely adop

Shuting Gu, Ming Xiao, Rui Chen

The Cahn-Hilliard equation is a fundamental model that describes phase separation processes of two-phase flows or binary mixtures. In recent years, the dynamic boundary conditions for the Cahn-Hilliard equation have been proposed and analyzed. Our first goal in this article is to present a projection method to locate the steady state of the CH equation with

Mohammadmostafa Rostamkhani, Baktash Ansari, Hoorieh Sabzevari, Farzan Rahmani

In recent years, Visual Question Answering (VQA) has made significant strides, particularly with the advent of multimodal models that integrate vision and language understanding. However, existing VQA datasets often overlook the complexities introduced by image illusions, which pose unique challenges for both human perception and model interpretation. In thi

M. Ghasemkhani, G. Soleimani, A. Soto, R. Bufalo

This work examines the dynamical mass generation for the photon in Rarita-Schwinger QED. We focus our attention on the cases of $\omega=2,3$ dimensional spacetime. In these frameworks, it is well known that in the usual QED, the photon field (dynamically) acquires a gauge invariant mass (the Schwinger and Chern-Simons mass, respectively). We wish to scrutini

Zhenpeng Chen, Xinyue Li, Jie M. Zhang, Federica Sarro

Intersectional fairness is a critical requirement for Machine Learning (ML) software, demanding fairness across subgroups defined by multiple protected attributes. This paper introduces FairHOME, a novel ensemble approach using higher order mutation of inputs to enhance intersectional fairness of ML software during the inference phase. Inspired by social sci

Dan Dai, Mourad E. H. Ismail, Xiang-Sheng Wang

In this paper, we study a class of orthogonal polynomials defined by a three-term recurrence relation with periodic coefficients. We derive explicit formulas for the generating function, the associated continued fraction, the orthogonality measure of these polynomials, as well as the spectral measure for the associated doubly infinite tridiagonal Jacobi matr

Kevin Buchin, Antonia Kalb, Anil Maheshwari, Saeed Odak

Given a point set $P$ in a metric space and a real number $t \geq 1$, an \emph{oriented $t$-spanner} is an oriented graph $\overrightarrow{G}=(P,\overrightarrow{E})$, where for every pair of distinct points $p$ and $q$ in $P$, the shortest oriented closed walk in $\overrightarrow{G}$ that contains $p$ and $q$ is at most a factor $t$ longer than the perimeter

Zebei Zhao, Yinghao Xiang, Ziyu Zhou, Kehan Chong

Traditional Real-Time Operating Systems (RTOS) often suffer from limited parallel performance, whereas thread monitoring in Linux-based systems remains challenging. To overcome these limitations, this paper presents a satellite flight software system design based on the Robot Operating System (ROS), which utilizes its reliable built-in publish-subscribe mess

Anmol Guragain, Nadika Poudel, Rajesh Piryani, Bishesh Khanal

This paper explores hate speech detection in Devanagari-scripted languages, focusing on Hindi and Nepali, for Subtask B of the CHIPSAL@COLING 2025 Shared Task. Using a range of transformer-based models such as XLM-RoBERTa, MURIL, and IndicBERT, we examine their effectiveness in navigating the nuanced boundary between hate speech and free expression. Our best

Alexey Rosaev, Eva Plavalova

In this paper we present our results of numerical integrations of orbits of fictive massless particle in vicinity of resonance. Our goal is to study the dependences of period (frequency) of resonance perturbations and the width of the resonance on mass and orbital eccentricity of perturbing planet and on the initial difference of longitude between test parti

Kexin Li, Zongxin Yang, Yi Yang, Jun Xiao

Audio-visual video segmentation (AVVS) aims to generate pixel-level maps of sound-producing objects that accurately align with the corresponding audio. However, existing methods often face temporal misalignment, where audio cues and segmentation results are not temporally coordinated. Audio provides two critical pieces of information: i) target object-level

Haonan Yuan, Qingyun Sun, Zhaonan Wang, Xingcheng Fu

Dynamic graphs exhibit intertwined spatio-temporal evolutionary patterns, widely existing in the real world. Nevertheless, the structure incompleteness, noise, and redundancy result in poor robustness for Dynamic Graph Neural Networks (DGNNs). Dynamic Graph Structure Learning (DGSL) offers a promising way to optimize graph structures. However, aside from enc

Kevin Miao, Harsh Agrawal, Qihang Zhang, Federico Semeraro

Generating high-quality 3D content requires models capable of learning robust distributions of complex scenes and the real-world objects within them. Recent Gaussian-based 3D reconstruction techniques have achieved impressive results in recovering high-fidelity 3D assets from sparse input images by predicting 3D Gaussians in a feed-forward manner. However, t

Yojiro Harie, Yuto Ogata, Gautam Bishnu Prasad, Katsumi Wasaki

Model checking is a fundamental technique for verifying finite state concurrent systems. Traditionally, model designs were initially created to facilitate the application of model checking. This process, representative of Model Driven Development (MDD), involves generating an equivalent code from a given model which is verified before implementation begins.

Yayun Qi, Hongxi Li, Yiqi Song, Xinxiao Wu

The exploration of various vision-language tasks, such as visual captioning, visual question answering, and visual commonsense reasoning, is an important area in artificial intelligence and continuously attracts the research community's attention. Despite the improvements in overall performance, classic challenges still exist in vision-language tasks and hin

Liang Du, Hua Jiang, Yijia Wu, X. C. Xie

Topological spin superconductors are $p$-wave spin-triplet exciton insulators whose topological edge modes have been shown to obey non-Abelian braiding statistics. Based on a toy model as the spin counterpart of the Kitaev's chain, we study the spin Josephson effect adopting the $S$-matrix as well as the Green's function method. The on-site energies of these

Xin Zhao, Xiaojun Chen, Haoyu Gao

Due to the remarkable generative potential of diffusion-based models, numerous researches have investigated jailbreak attacks targeting these frameworks. A particularly concerning threat within image models is the generation of Not-Safe-for-Work (NSFW) content. Despite the implementation of security filters, numerous efforts continue to explore ways to circu

Akanshu Khandelwal, Dhyey Raval, Narayan Sharma, Yashashri Patil

This work investigates the discharge properties of a cylindrical magnetized capacitive coupled plasma discharge produced between a pair of coaxial cylinders. For the purpose of diagnosing plasma properties and electron energy distribution function (EEDF), an in-house electronic circuit and an RF-compensated Langmuir probe are devised and constructed. The sec

Kaito Kashiwagi, Akira Matsumura

The open dynamics of quantum particles in relativistic scattering is investigated. In particular, we consider the scattering process of quantum particles coupled to an environment initially in a vacuum state. Tracing out the environment and using the unitarity of S-operator, we find the Gorini-Kossakowski-Sudarshan-Lindblad (GKSL) generator describing the ev

Masood Aryapoor

We introduce a new concept of a semiprime submodule. We show that a submodule of a finitely generated module over a commutative ring is semiprime if and only if it is radical, that is, an intersection of prime submodules. Using our notion, we also provide a new characterization of radical submodules of finitely generated modules over commutative rings.

Yian Zhao, Wanshi Xu, Yang Wu, Weiheng Huang

3D editing plays a crucial role in editing and reusing existing 3D assets, thereby enhancing productivity. Recently, 3DGS-based methods have gained increasing attention due to their efficient rendering and flexibility. However, achieving desired 3D editing results often requires multiple adjustments in an iterative loop, resulting in tens of minutes of train

Junsup Shim, Teppei Okumura, Atsushi Taruya

The intrinsic alignment (IA) of galaxy shapes probes the underlying gravitational tidal field, thus offering cosmological information complementary to galaxy clustering. In this paper, we perform a Fisher forecast to assess the benefit of IA in improving cosmological parameter constraints, for the first time, leveraging the full-shape (FS) information of IA

Junsup Shim, Teppei Okumura, Atsushi Taruya

Recent $2-4\sigma$ deviations from the Cosmological Constant $\Lambda$ suggest that dark energy (DE) may be dynamical, based on baryon acoustic oscillations and full-shape galaxy clustering (FS GC) analyses. This calls for even tighter DE constraints to narrow down its true nature. In this Letter, we explore how galaxy intrinsic alignments (IA) can enhance t

Zihao Han, Baoquan Zhang, Lisai Zhang, Shanshan Feng

Image inpainting is an important image generation task, which aims to restore corrupted image from partial visible area. Recently, diffusion Schr\"odinger bridge methods effectively tackle this task by modeling the translation between corrupted and target images as a diffusion Schr\"odinger bridge process along a noising schedule path. Although these methods

Guiran Liu, Binrong Zhu

This paper provides a comprehensive review of mechanical equipment fault diagnosis methods, focusing on the advancements brought by Transformer-based models. It details the structure, working principles, and benefits of Transformers, particularly their self-attention mechanism and parallel computation capabilities, which have propelled their widespread appli

Hajime Kubota

The Upsilon invariant is a concordance invariant in knot Floer homology. F\"{o}ldv\'{a}ri reconstructed the Upsilon invariant using grid homology. We prove that the Upsilon invariant in knot Floer homology and one in grid homology are equivalent. Furthermore, we show some properties of the Upsilon invariant in the framework of grid homology.

Yang Li, Xinyu Zhou, Yitong Wang, Liangxin Qian

Transformer models have revolutionized AI, enabling applications like content generation and sentiment analysis. However, their use in Machine Learning as a Service (MLaaS) raises significant privacy concerns, as centralized servers process sensitive user data. Private Transformer Inference (PTI) addresses these issues using cryptographic techniques such as

Weigang Lu, Ziyu Guan, Wei Zhao, Yaming Yang

Mixup is a data augmentation technique that enhances model generalization by interpolating between data points using a mixing ratio $\lambda$ in the image domain. Recently, the concept of mixup has been adapted to the graph domain through node-centric interpolations. However, these approaches often fail to address the complexity of interconnected relationshi

Michael A. J. Mitchell, Teresa Del Aguila Ferrandis, Stefano Sanvito

Orbital-free density functional theory promises to deliver linear-scaling electronic structure calculations. This requires the knowledge of the non-interacting kinetic-energy density functional (KEDF), which should be accurate and must admit accurate functional derivatives, so that a minimization procedure can be designed. In this work, symbolic regression i

Yamato Honda, Soma Onoda, Hiroshi Suzuki

We investigate the non-invertible symmetry associated with chiral symmetry in axion quantum electrodynamics (QED) using the modified Villain formulation. In axion QED, it is known that naive magnetic objects such as 't Hooft loops and axion strings lose their gauge invariance due to the violation of the Bianchi identity for the field strength of the photon o

Y. -M. Robin Hu, Elena A. Ostrovskaya, Eliezer Estrecho

The quantum geometric tensor (QGT) characterizes the local geometry of quantum states, and its components directly account for the dynamical effects observed, e.g., in condensed matter systems. In this work, we address the problem of extending the QGT formalism to non-Hermitian systems with gain and loss. In particular, we investigate a wave-packet dynamics

Swathi Krishna

We prove that for a finitely generated group G with a free factor system and an injective endomorphism that preserves the free factor system, the ascending HNN extension of G is hyperbolic relative to a collection of maximal parabolic subgroups. As a corollary, we see that if an injective endomorphism of a finite rank free group F is exponentially growing, t

Jiaming Lv, Haoyuan Yang, Peihua Li

Since pioneering work of Hinton et al., knowledge distillation based on Kullback-Leibler Divergence (KL-Div) has been predominant, and recently its variants have achieved compelling performance. However, KL-Div only compares probabilities of the corresponding category between the teacher and student while lacking a mechanism for cross-category comparison. Be

Yuchang Sun, Xinran Li, Tao Lin, Jun Zhang

Federated learning (FL) enables collaborative learning among decentralized clients while safeguarding the privacy of their local data. Existing studies on FL typically assume offline labeled data available at each client when the training starts. Nevertheless, the training data in practice often arrive at clients in a streaming fashion without ground-truth l

Zhaoying Li, Pranav Dangi, Chenyang Yin, Thilini Kaushalya Bandara

Coarse-grained Reconfigurable Arrays (CGRAs) are domain-agnostic accelerators that enhance the energy efficiency of resource-constrained edge devices. The CGRA landscape is diverse, exhibiting trade-offs between performance, efficiency, and architectural specialization. However, CGRAs often overprovision communication resources relative to their modest compu

Shigeo S. Kimura, Kengo Tomida, Masato I. N. Kobayashi, Koki Kin

The origin of PeV cosmic rays is a long-standing mystery, and ultrahigh-energy gamma-ray observations would play a crucial role in identifying it. Recently, LHAASO reported the discovery of ``dark'' gamma-ray sources that were detected above 100 TeV without any GeV--TeV gamma-ray counterparts. The origins of these dark gamma-ray sources are unknown. We propo

Venkatraman Manikandan, Suresh Neethirajan

Deciphering the acoustic language of chickens offers new opportunities in animal welfare and ecological informatics. Their subtle vocal signals encode health conditions, emotional states, and dynamic interactions within ecosystems. Understanding the semantics of these calls provides a valuable tool for interpreting their functional vocabulary and clarifying

Zewen Xu, Yijia He, Hao Wei, Yihong Wu

Most existing visual-inertial odometry (VIO) initialization methods rely on accurate pre-calibrated extrinsic parameters. However, during long-term use, irreversible structural deformation caused by temperature changes, mechanical squeezing, etc. will cause changes in extrinsic parameters, especially in the rotational part. Existing initialization methods th

Ayse Asu Guvenli, Bora Isildak

Identifying jets originating from bottom quarks is vital in collider experiments for new physics searches. This paper proposes a novel approach based on Retentive Networks (RetNet) for b-jet tagging using low-level features of jet constituents along with high-level jet features. A simulated \ttbar dataset provided by CERN CMS Open Data Portal was used, where

Vikas Vyas, Sneha Sudhir Shetiya

Electric Power Steering (EPS) systems utilize electric motors to aid users in steering their vehicles, which provide additional precise control and reduced energy consumption compared to traditional hydraulic systems. EPS technology provides safety,control and efficiency.. This paper explains the integration of Artificial Intelligence (AI) into Electric Powe

Qiang Zhao, Zhengxue Ren, Pengwei Zhao, Kenichi Yoshida

The exact-exchange relativistic density functional theory (Ex-RDFT) of atomic nuclei has been solved in three-dimensional lattice space for the first time. The exchange energy is treated within the framework of the orbital-dependent relativistic Kohn-Sham density functional theory, wherein the local Lorentz scalar and vector potentials are derived using the

Haiming Yao, Wei Luo, Ang Gao, Tao Zhou

Raman spectroscopy has attracted significant attention in various biochemical detection fields, especially in the rapid identification of pathogenic bacteria. The integration of this technology with deep learning to facilitate automated bacterial Raman spectroscopy diagnosis has emerged as a key focus in recent research. However, the diagnostic performance o

Liang Guo, Jin Qian, Qin Wang

Let $(X,d)$ be a uniformly locally finite metric space, and $T$ an operator in the uniform Roe algebra $C_u^*(X)$ (or uniform quasi-local algebra $C_{ql}^*(X)$). In this paper, we introduce the concept of limit operators of $T$ on galaxies in the nonstandard extension of $X$, and prove that $T$ is a generalized Fredholm operator with respect to the ghost ide

Junqi You, Xiaosong Jia, Zhiyuan Zhang, Yutao Zhu

For end-to-end autonomous driving (E2E-AD), the evaluation system remains an open problem. Existing closed-loop evaluation protocols usually rely on simulators like CARLA being less realistic; while NAVSIM using real-world vision data, yet is limited to fixed planning trajectories in short horizon and assumes other agents are not reactive. We introduce Bench

V. Arvind Rameshwar, V. Lalitha

In this paper, we revisit the Recursive Projection-Aggregation (RPA) decoder, of Ye and Abbe (2020), for Reed-Muller (RM) codes. Our main contribution is an explicit upper bound on the probability of incorrect decoding, using the RPA decoder, over a binary symmetric channel (BSC). Importantly, we focus on the events where a \emph{single} iteration of the RPA

Yanchen Xu, Siqi Huang, Hongyuan Zhang, Xuelong Li

Graph contrastive learning (GCL) has been widely used as an effective self-supervised learning method for graph representation learning. However, how to apply adequate and stable graph augmentation to generating proper views for contrastive learning remains an essential problem. Dropping edges is a primary augmentation in GCL while adding edges is not a comm

Jiho Choi, Donggyun Kim, Chanhyuk Lee, Seunghoon Hong

Model merging aims to build a multi-task learner by combining the parameters of individually fine-tuned models without additional training. While a straightforward approach is to average model parameters across tasks, this often results in suboptimal performance due to interference among parameters across tasks. In this paper, we present intriguing results t

Kuang-Hua Chou, Alexander Eden, David E. Huber, Sumita Pennathur

We demonstrate electronic sensing of DNA nanostar (NS) condensate. Specifically, we use electrokinetic nanofluidics to observe and interpret how temperature-induced NS condensation affects nanochannel current. The increase in current upon filling a nanochannel with NS condensate indicates that its electrophoretic mobility is about half that of a single NS an

Xuhan Sheng, Runyi Li, Bin Chen, Weiqi Li

Omnidirectional image super-resolution (ODISR) aims to upscale low-resolution (LR) omnidirectional images (ODIs) to high-resolution (HR), catering to the growing demand for detailed visual content across a $ 180^{\circ}\times360^{\circ}$ viewport. Existing ODISR methods are limited by simplified degradation assumptions (e.g., bicubic downsampling), failing t

Nathanaël Carraz Rakotonirina, Corentin Kervadec, Francesca Franzon, Marco Baroni

It has been widely observed that language models (LMs) respond in predictable ways to algorithmically generated prompts that are seemingly unintelligible. This is both a sign that we lack a full understanding of how LMs work, and a practical challenge, because opaqueness can be exploited for harmful uses of LMs, such as jailbreaking. We present the first tho

Yonghyuk Lee, Taehun Lee

Understanding the semiconductor-electrolyte interface in photoelectrochemical (PEC) systems is crucial for optimizing stability and reactivity. Despite the challenges in establishing reliable surface structure models during PEC cycles, this study explores the complex surface reconstructions of BiVO$_{4}$(010) by employing a computational workflow integrated

Quang-Hung Le, Long Hoang Dang, Ngan Le, Truyen Tran

Existing Large Vision-Language Models (LVLMs) excel at matching concepts across multi-modal inputs but struggle with compositional concepts and high-level relationships between entities. This paper introduces Progressive multi-granular Vision-Language alignments (PromViL), a novel framework to enhance LVLMs' ability in performing grounded compositional visua

Xi Wang, Xiaoyi Wang, Victor Solo

In this paper, we develop a novel method for deriving a global optimal control strategy for stochastic attitude kinematics on the special orthogonal group SO(3). We first introduce a stochastic Lie-Hamilton-Jacobi-Bellman (SL-HJB) equation on SO(3), which theoretically provides an optimality condition for the global optimal control strategy of the stochastic

Jia-Jia Wang, Yu-Hong He, Chang-Geng Liao, Rong-Xin Chen

Quantum physics can be extended into the complex domain by considering non-Hermitian Hamiltonians that are $\mathcal{PT}$-symmetric. These exhibit exceptional points (EPs) where the eigenspectrum changes from purely real to purely imaginary values and have useful properties enabling applications such as accelerated entanglement generation and the delay of th

Amir Zakerimanesh, Tony Zhijun Qiu, Mahdi Tavakoli

This paper investigates the impact of rigid communication topologies (RCTs) on the performance of vehicular platoons, aiming to identify beneficial features in RCTs that enhance vehicles behavior. We introduce four performance metrics, focusing on safety, energy consumption, passenger comfort, and robustness of vehicular platoons. The safety metric is based

Samuel Nordström, Björn Lindquist, George Nikolakopoulos

Proactive collision avoidance measures are imperative in environments where humans and robots coexist. Moreover, the introduction of high quality legged robots into workplaces highlighted the crucial role of a robust, fully autonomous safety solution for robots to be viable in shared spaces or in co-existence with humans. This article establishes for the fir

Kenta Horikawa, Mariko Isogawa, Hideo Saito, Shohei Mori

We propose a method for dense depth estimation from an event stream generated when sweeping the focal plane of the driving lens attached to an event camera. In this method, a depth map is inferred from an ``event focal stack'' composed of the event stream using a convolutional neural network trained with synthesized event focal stacks. The synthesized event

Yuanhao Shen, Xiaodan Zhu, Lei Chen

The tool-use ability of Large Language Models (LLMs) has a profound impact on a wide range of industrial applications. However, LLMs' self-control and calibration capability in appropriately using tools remains understudied. The problem is consequential as it raises potential risks of degraded performance and poses a threat to the trustworthiness of the mode

J. Seeyangnok, U. Pinsook, G. J. Ackland

Two-dimensional (2D) lithium-decorated materials have emerged as a significant area of study since the prediction of superconductivity in lithium-decorated graphene at temperatures around 8.1 K, with experimental evidence observed at Tc = 5.9 K. Following earlier studies, this paper focuses on the hexagonal Janus MoSeLi monolayer as a promising candidate for

Qi'an Guan, Xun Sun, Zheng Yuan

In this article, we use a class of harmonic functions (maybe multi-valued) to study the equality part in a weighted version of Suita conjecture for higher derivatives and finite points case, and we obtain some sufficient and necessary conditions for the equality part to hold when the harmonic part $u$ of the weight is trivial.

Haowei Lou, Helen Paik, Pari Delir Haghighi, Wen Hu

Diffusion-based Generative AI gains significant attention for its superior performance over other generative techniques like Generative Adversarial Networks and Variational Autoencoders. While it has achieved notable advancements in fields such as computer vision and natural language processing, their application in speech generation remains under-explored.

Jaeho Moon, Jeonghwan Yun, Jaehyun Kim, Jaehyup Lee

Oil spills pose severe environmental risks, making early detection crucial for effective response and mitigation. As Synthetic Aperture Radar (SAR) images operate under all-weather conditions, SAR-based oil spill segmentation enables fast and robust monitoring. However, when using deep learning models, SAR oil spill segmentation often struggles in training d

Douglas Eacersall, Lynette Pretorius, Ivan Smirnov, Erika Spray

The rapid adoption of generative artificial intelligence (GenAI) in research presents both opportunities and ethical challenges that should be carefully navigated. Although GenAI tools can enhance research efficiency through automation of tasks such as literature review and data analysis, their use raises concerns about aspects such as data accuracy, privacy