October 2024 arXiv papers — page 93

Ali Eghbali

We proceed to construct a dual pair for the $AdS_3 \times S^3$ background by applying non-Abelian T-duality (here as Poisson-Lie (PL) T-duality on a semi-Abelian double). By using a certain parametrization of the $4$-dimensional Lie group ${A}_2 \otimes 2{A}_1$ and by a suitable choice of spectator-dependent matrices, the original $\sigma$-model including th

Zihui Wu, Haichang Gao, Ping Wang, Shudong Zhang

Glitch tokens, inputs that trigger unpredictable or anomalous behavior in Large Language Models (LLMs), pose significant challenges to model reliability and safety. Existing detection methods primarily rely on heuristic embedding patterns or statistical anomalies within internal representations, limiting their generalizability across different model architec

Fengjun Pan, Xiaobao Wu, Zongrui Li, Anh Tuan Luu

Fallacies are defective arguments with faulty reasoning. Detecting and classifying them is a crucial NLP task to prevent misinformation, manipulative claims, and biased decisions. However, existing fallacy classifiers are limited by the requirement for sufficient labeled data for training, which hinders their out-of-distribution (OOD) generalization abilitie

Jiaxin Yu, Tianchen Qian

To optimize mobile health interventions and advance domain knowledge on intervention design, it is critical to understand how the intervention effect varies over time and with contextual information. This study aims to assess how a push notification suggesting physical activity influences individuals' step counts using data from the HeartSteps micro-randomiz

Siyuan Lu, Jiaqi Shao, Bing Luo, Tao Lin

Large Language Model (LLM) based multi-agent systems (MAS) have shown promise in tackling complex tasks, but often rely on predefined roles and centralized coordination, limiting their adaptability to evolving challenges. This paper introduces MorphAgent, a novel Autonomous, Self-Organizing, and Self-Adaptive Multi-Agent System for decentralized agent collab

Tugrul Cabir Hakyemez, Omer Adar

Accurate forecasting of electrical demand is essential for maintaining a stable and reliable power grid, optimizing the allocation of energy resources, and promoting efficient energy consumption practices. This study investigates the effectiveness of five hyperparameter optimization (HPO) algorithms -- Random Search, Covariance Matrix Adaptation Evolution St

Huihui Yang, Chunxue Zhu, Longlong Lin, Pingpeng Yuan

Identifying communities from temporal networks facilitates the understanding of potential dynamic relationships among entities, which has already received extensive applications. However, existing methods primarily rely on lower-order connectivity (e.g., temporal edges) to capture the structural and temporal cohesiveness of the community, often neglecting hi

Jiaqi Shao, Tao Lin, Xiaojin Zhang, Qiang Yang

Federated Unlearning (FU) enables the removal of specific clients' data influence from trained models. However, in non-IID settings, removing clients creates critical side effects: remaining clients with similar data distributions suffer disproportionate performance degradation, while the global model's stability deteriorates. These vulnerable clients then h

Shuning Zhang, Xin Yi, Haobin Xing, Lyumanshan Ye

Current Large Language Models (LLMs) cannot support users to precisely balance privacy protection and output performance during individual consultations. We introduce Adanonymizer, an anonymization plug-in that allows users to control this balance by navigating a trade-off curve. A survey (N=221) revealed a privacy paradox, where users frequently disclosed s

Effie Papageorgiou

Let $\mu$ be a radial compactly supported distribution on a harmonic $NA$ group. We prove that the right convolution operator $c_{\mu}:f \mapsto f* \mu$ maps the space of smooth $\mathfrak{v}$-radial functions onto itself if and only if the spherical Fourier transform $\widetilde{\mu}(\lambda)$, $\lambda \in \mathbb{C}$, is slowly decreasing. As an applicati

Mengnan Zhao, Lihe Zhang, Jingwen Ye, Huchuan Lu

Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the effectiveness of AT in improving the robustness of deep neural networks against diverse adversarial attacks. However, a compr

Tian-Ming Li, Jia-Chi Zhang, Bing-Jie Chen, Kaixuan Huang

For superconducting quantum processors, stable high-fidelity two-qubit operations depend on precise flux control of the tunable coupler. However, the pulse distortion poses a significant challenge to the control precision. Current calibration methods, which often rely on microwave crosstalk or additional readout resonators for coupler excitation and readout,

Zichen Wang, Yaokun Ji, Jianing Tian, Shuangjia Zheng

Antibodies are essential proteins responsible for immune responses in organisms, capable of specifically recognizing antigen molecules of pathogens. Recent advances in generative models have significantly enhanced rational antibody design. However, existing methods mainly create antibodies from scratch without template constraints, leading to model optimizat

Yuedan Ding, Shidi Zhang, Henggeng Han, Wenyuan Cui

Using the LAMOST DR7 low-resolution spectra, we carried out a systematic study of stellar chromospheric activity in both single and binary stars. We constructed a binary sample and a single-star sample, mainly using the binary belt and the main sequence in the Hertzsprung-Russell diagram, respectively. By comparing the $S$ indices between single and binary s

Siyuan Yan, Zhen Yu, Clare Primiero, Cristina Vico-Alonso

Diagnosing and treating skin diseases require advanced visual skills across domains and the ability to synthesize information from multiple imaging modalities. While current deep learning models excel at specific tasks like skin cancer diagnosis from dermoscopic images, they struggle to meet the complex, multimodal requirements of clinical practice. Here, we

Thang Pang Ern

We wish to discuss positive integer solutions to the Diophantine equation $$\prod_{k=1}^n(k^2+1)=b^2.$$ Some methods in analytic number theory will be used to tackle this problem.

Nishat Raihan, Antonios Anastasopoulos, Marcos Zampieri

Recent advancements in large language models (LLMs) have significantly enhanced code generation from natural language prompts. The HumanEval Benchmark, developed by OpenAI, remains the most widely used code generation benchmark. However, this and other Code LLM benchmarks face critical limitations, particularly in task diversity, test coverage, and linguisti

Chenguang Lu

Recent advances in deep learning suggest that we need to maximize and minimize two different kinds of information simultaneously. The Information Max-Min (IMM) method has been used in deep learning, reinforcement learning, and maximum entropy control. Shannon's information rate-distortion function is the theoretical basis of Minimizing Mutual Information (MM

Xin Li, Wenhui Zhu, Xuanzhao Dong, Oana M. Dumitrascu

With the rapid development of deep learning, CNN-based U-shaped networks have succeeded in medical image segmentation and are widely applied for various tasks. However, their limitations in capturing global features hinder their performance in complex segmentation tasks. The rise of Vision Transformer (ViT) has effectively compensated for this deficiency of

Mingxin Li, Zhijie Nie, Yanzhao Zhang, Dingkun Long

Text embeddings are vital for tasks such as text retrieval and semantic textual similarity (STS). Recently, the advent of pretrained language models, along with unified benchmarks like the Massive Text Embedding Benchmark (MTEB), has facilitated the development of versatile general-purpose text embedding models. Advanced embedding models are typically develo

Haoran Feng, Zhiwei Chen, Zhibo Jiang, Yuehui Ma

Structures in molecular ISM are observed to follow a power-law relation between the velocity dispersion and spatial size, known as Larson's first relation, which is often attributed to the turbulent nature of molecular ISM and imprints the dynamics of molecular cloud structures. Using the ${}^{13}\mathrm{CO}~(J=1-0)$ data from the Milky Way Imaging Scroll Pa

Mingyi Zhou, Xiang Gao, Xiao Chen, Chunyang Chen

Deploying DL models on mobile Apps has become ever-more popular. However, existing studies show attackers can easily reverse-engineer mobile DL models in Apps to steal intellectual property or generate effective attacks. A recent approach, Model Obfuscation, has been proposed to defend against such reverse engineering by obfuscating DL model representations,

Sudipta Das, Ayan Patra, Rivu Gupta, Aditi Sen De

In order to enable the sequential implementation of quantum information theoretic protocols in the continuous variable framework, we propose two schemes for resource reusability, resource-splitting protocol and unsharp homodyne measurements. We demonstrate the advantage offered by the first scheme in implementing sequential attempts at continuous variable te

Zhiguang Zhang, Yuxiang Li

In this work, we study the doubly degenerate nutrient taxis system with logistic source \begin{align} \begin{cases}\tag{$\star$}\label{eq 0.1} u_t=\nabla \cdot(u^{l-1} v \nabla u)- \nabla \cdot\left(u^{l} v \nabla v\right)+ u - u^2, \\ v_t=\Delta v-u v \end{cases} \end{align} in a smooth bounded domain $\Omega \subset \mathbb{R}^2$, where $l \geqslant 1$. It

Thomas Bläsius, Max Göttlicher, Sascha Gritzbach, Wendy Yi

Motivated by the cabling of solar farms, we study the problem Constrained Layer Tree. At its core, it asks whether there exists a tree that connects a set of sources (the leaves) to one sink (the root) such that certain capacity constraints at the inner nodes are satisfied. Our main algorithmic contribution is a dynamic program with various optimizations for

Amelia Jones

This research delves into the development of a fatigue detection system based on modern object detection algorithms, particularly YOLO (You Only Look Once) models, including YOLOv5, YOLOv6, YOLOv7, and YOLOv8. By comparing the performance of these models, we evaluate their effectiveness in real-time detection of fatigue-related behavior in drivers. The study

Yuzhe Weng, Haotian Wang, Tian Gao, Kewei Li

In multimodal sentiment analysis, collecting text data is often more challenging than video or audio due to higher annotation costs and inconsistent automatic speech recognition (ASR) quality. To address this challenge, our study has developed a robust model that effectively integrates multimodal sentiment information, even in the absence of text modality. S

Dipo Dunsin, Mohamed Chahine Ghanem, Karim Ouazzane, Vassil Vassilev

This Research proposes a Novel Reinforcement Learning (RL) model to optimise malware forensics investigation during cyber incident response. It aims to improve forensic investigation efficiency by reducing false negatives and adapting current practices to evolving malware signatures. The proposed RL framework leverages techniques such as Q-learning and the M

Lianghua Huang, Wei Wang, Zhi-Fan Wu, Huanzhang Dou

While large language models (LLMs) have revolutionized natural language processing with their task-agnostic capabilities, visual generation tasks such as image translation, style transfer, and character customization still rely heavily on supervised, task-specific datasets. In this work, we introduce Group Diffusion Transformers (GDTs), a novel framework tha

Wenyi Liu, Rui Wang, Yuanshuai Luo, Jianjun Wei

With the explosive growth of Internet data, users are facing the problem of information overload, which makes it a challenge to efficiently obtain the required resources. Recommendation systems have emerged in this context. By filtering massive amounts of information, they provide users with content that meets their needs, playing a key role in scenarios suc

Minsun Kim, SeonGyeom Kim, Suyoun Lee, Yoosang Yoon

This paper presents the development of a dashboard designed specifically for teachers in English as a Foreign Language (EFL) writing education. Leveraging LLMs, the dashboard facilitates the analysis of student interactions with an essay writing system, which integrates ChatGPT for real-time feedback. The dashboard aids teachers in monitoring student behavio

Behnaz Omoomi Marzieh Vahid Dastjerdi

The star chromatic index of a graph $G$, denoted by $\chi^\prime_s(G)$, is the smallest integer $k$ for which $G$ admits a proper edge coloring with $k$ colors such that every path and cycle of length four is not bicolored. Let $d$ be the greatest common divisor of $n$ and $k$. Zhu~et~al. (\footnotesize{Discussiones Mathematicae: Graph Theory, 41(2): 1265, 2

Yuchi Yahagi, Rintaro Chujo, Yuga Harada, Changyo Han

Listening to audio content, such as podcasts and audiobooks, is one way for people to engage with knowledge. Listening affords people more mobility than reading by seeing, thereby broadening their learning opportunities. This study explores the potential applications of large language models (LLMs) to adapt text documents to audio content and addresses the l

Nguyen Thang Loi, Duong Tan Loc, Vo Nguyen Le Duy

Feature Selection (FS) under domain adaptation (DA) is a critical task in machine learning, especially when dealing with limited target data. However, existing methods lack the capability to guarantee the reliability of FS under DA. In this paper, we introduce a novel statistical method to statistically test FS reliability under DA, named SFS-DA (statistical

Hidetaka Kamigaito, Hiroyuki Deguchi, Yusuke Sakai, Katsuhiko Hayashi

Inference methods play an important role in eliciting the performance of large language models (LLMs). Currently, LLMs use inference methods utilizing generated multiple samples, which can be derived from Minimum Bayes Risk (MBR) Decoding. Previous studies have conducted empirical analyses to clarify the improvements in generation performance achieved by MBR

Baojian Zhou, Yifan Sun, Reza Babanezhad Harikandeh, Xingzhi Guo

Given the damping factor $\alpha$ and precision tolerance $\epsilon$, \citet{andersen2006local} introduced Approximate Personalized PageRank (APPR), the \textit{de facto local method} for approximating the PPR vector, with runtime bounded by $\Theta(1/(\alpha\epsilon))$ independent of the graph size. Recently, \citet{fountoulakis2022open} asked whether faste

Jinggui Liang, Yuxia Wu, Yuan Fang, Hao Fei

In the rapidly evolving field of conversational AI, Ontology Expansion (OnExp) is crucial for enhancing the adaptability and robustness of conversational agents. Traditional models rely on static, predefined ontologies, limiting their ability to handle new and unforeseen user needs. This survey paper provides a comprehensive review of the state-of-the-art te

Arturo Mariani, Federico Senocrate, Jason Mikiel-Hunter, David McAlpine

Background: In Kreuz et al., J Neurosci Methods 381, 109703 (2022) two methods were proposed that perform latency correction, i.e., optimize the spike time alignment of sparse neuronal spike trains with well defined global spiking events. The first one based on direct shifts is fast but uses only partial latency information, while the other one makes use of

Md Mubtasim Ahasan, Md Fahim, Tasnim Mohiuddin, A K M Mahbubur Rahman

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains challenging. This process demands acoustic, semantic, and contextual information for precise speech representations. Existing spe

Jiahao Wang, Amer Shalaby

Users of the transit system flood social networks daily with messages that contain valuable insights crucial for improving service quality. These posts help transit agencies quickly identify emerging issues. Parsing topics and sentiments is key to gaining comprehensive insights to foster service excellence. However, the volume of messages makes manual analys

Yue Zhan, Zhihong Zeng, Haijun Liu, Xiaoheng Tan

The purpose of RGB-D Salient Object Detection (SOD) is to pinpoint the most visually conspicuous areas within images accurately. While conventional deep models heavily rely on CNN extractors and overlook the long-range contextual dependencies, subsequent transformer-based models have addressed the issue to some extent but introduce high computational complex

Oleg Zubelevich

In this short note we present a far generalization of the following very well-known assertion: assume that we have two orthonormal sequences in a Hilbert space and these sequences are quadratically close to each other. Then if one of these sequences is a basis in the Hilbert space then so is the other one.

Weiyong He, Long Li, Xiaowei Xu

The purpose of this article is to study the (residual) Monge-Amp\`{e}re mass of a plurisubharmonic function with an isolated unbounded locus. A general decomposition formula is obtained under the Sasakian structure of the unit sphere. In complex dimension two, we obtain an $L^{1}$-apriori estimate on the complex Monge-Amp\`{e}re operator. This induces an upp

Jiahao Wang, Amer Shalaby

Accurate prediction of public transit ridership is vital for efficient planning and management of transit in rapidly growing urban areas in Canada. Unexpected increases in passengers can cause overcrowded vehicles, longer boarding times, and service disruptions. Traditional time series models like ARIMA and SARIMA face limitations, particularly in short-term

Gesa Mittmann, Sara Laiouar-Pedari, Hendrik A. Mehrtens, Sarah Haggenmüller

The aggressiveness of prostate cancer, the most common cancer in men worldwide, is primarily assessed based on histopathological data using the Gleason scoring system. While artificial intelligence (AI) has shown promise in accurately predicting Gleason scores, these predictions often lack inherent explainability, potentially leading to distrust in human-mac

Arnab Bhattacharya, Afsar Ahmed, Sreeparvathy PC, Daichi Kurebayashi

The synergy between real and reciprocal space topology is anticipated to yield a diverse array of topological properties in quantum materials. We address this pursuit by achieving topologically safeguarded magnetic order in novel Weyl metallic Heusler alloy, Mn$_{2}$Pd$_{0.5}$Ir$_{0.5}$Sn. The system possesses non-centrosymmetric D$_{2d}$ crystal symmetry wi

Sizhe Liu, Jun Xia, Lecheng Zhang, Yuchen Liu

Molecular relational learning (MRL) is crucial for understanding the interaction behaviors between molecular pairs, a critical aspect of drug discovery and development. However, the large feasible model space of MRL poses significant challenges to benchmarking, and existing MRL frameworks face limitations in flexibility and scope. To address these challenges

M. Rostami, S. S. Kia

In this article, we consider the problem of unconstrained time-varying convex optimization, where the cost function changes with time. We provide an in-depth technical analysis of the problem and argue why freezing the cost at each time step and taking finite steps toward the minimizer is not the best tracking solution for this problem. We propose a set of a

Minseok Seo, Xuan Truong Nguyen, Seok Joong Hwang, Yongkee Kwon

Accelerating end-to-end inference of transformer-based large language models (LLMs) is a critical component of AI services in datacenters. However, diverse compute characteristics of end-to-end LLM inference present challenges as previously proposed accelerators only address certain operations or stages (e.g., self-attention, generation stage, etc.). To addr

Ying Hu, Chenyi Zhuang, Pan Gao

Style transfer aims to fuse the artistic representation of a style image with the structural information of a content image. Existing methods train specific networks or utilize pre-trained models to learn content and style features. However, they rely solely on textual or spatial representations that are inadequate to achieve the balance between content and

Baohua Huang, Jiakai Chen, Wen Li

One of the tasks in color image processing and computer vision is to recover clean data from partial observations corrupted by noise. To this end, robust quaternion matrix completion (QMC) has recently attracted more attention and shown its effectiveness, whose convex relaxation is to minimize the quaternion nuclear norm plus the quaternion $L_1$-norm. Howev

Zhiqiang Zhong, Yang Yang, Fengqiang Wan, Henglu Wei

This report presents our method for Single Object Tracking (SOT), which aims to track a specified object throughout a video sequence. We employ the LoRAT method. The essence of the work lies in adapting LoRA, a technique that fine-tunes a small subset of model parameters without adding inference latency, to the domain of visual tracking. We train our model u

Yi Zhao, Jing Li, Linyi Yang

Large language models (LLMs) are widely used, but concerns about data contamination challenge the reliability of LLM evaluations. Existing contamination detection methods are often task-specific or require extra prerequisites, limiting practicality. We propose a novel framework, Consistency Amplification-based Data Contamination Detection (CAP), which introd

Robert Mercaş, Wen Chean Teh

The focus of this work is the study of Parikh matrices with emphasis on two concrete problems. In the first part of our presentation we show that a conjecture by Dick at al. in 2021 only stands in the case of ternary alphabets, while providing counterexamples for larger alphabets. In particular, we show that the only type of distinguishability in the case of

Chen Yan, Weina Wang, Lei Ying

We study the finite-horizon Restless Multi-Armed Bandit (RMAB) problem with $N$ homogeneous arms. Prior work has shown that when an RMAB satisfies a non-degeneracy condition, Linear-Programming-based (LP-based) policies derived from the fluid approximation, which captures the mean dynamics of the system, achieve an exponentially small optimality gap. However

Sahil Verma, Royi Rassin, Arnav Das, Gantavya Bhatt

Text-to-image models are trained using large datasets of image-text pairs collected from the internet. These datasets often include copyrighted and private images. Training models on such datasets enables them to generate images that might violate copyright laws and individual privacy. This phenomenon is termed imitation -- generation of images with content

Shubhajit Roy, Hrriday Ruparel, Kishan Ved, Anirban Dasgupta

Scalability of Graph Neural Networks (GNNs) remains a significant challenge. To tackle this, methods like coarsening, condensation, and computation trees are used to train on a smaller graph, resulting in faster computation. Nonetheless, prior research has not adequately addressed the computational costs during the inference phase. This paper presents a nove

Songnian Xu, Wenhao Zhen, Dein Wong

Let $G$ be a simple connected graph of order $n$ with diameter $d$. Let $m_G(-1)$ denote the multiplicity of the eigenvalue $-1$ of the adjacency matrix of $G$, and let $P = P_{d+1}$ be the diameter path of $G$. If $-1$ is not an eigenvalue of $P$, then by the interlacing theorem, we have $m_G(-1)\leq n - d - 1$. In this article, we characterize the extremal

Peter Kuchment, Leonid Kunyansky

The forward problem arising in several hybrid imaging modalities can be modeled by the Cauchy problem for the free space wave equation. Solution to this problems describes propagation of a pressure wave, generated by a source supported inside unit sphere $S$. The data $g$ represent the time-dependent values of the pressure on the observation surface $S$. Fin

Raymundo Vazquez Martinez, Raj Abhijit Dandekar, Rajat Dandekar, Sreedath Panat

In this study, we apply two pillars of Scientific Machine Learning: Neural Ordinary Differential Equations (Neural ODEs) and Universal Differential Equations (UDEs) to the Chandrasekhar White Dwarf Equation (CWDE). The CWDE is fundamental for understanding the life cycle of a star, and describes the relationship between the density of the white dwarf and its

Tuan Nam Nguyen, Seymanur Akti, Ngoc Quan Pham, Alexander Waibel

Previous approaches on accent conversion (AC) mainly aimed at making non-native speech sound more native while maintaining the original content and speaker identity. However, non-native speakers sometimes have pronunciation issues, which can make it difficult for listeners to understand them. Hence, we developed a new AC approach that not only focuses on acc

Ankur Mudgal, Abhishek Verma, Munesh Singh, Kshira Sagar Sahoo

Software Defined Networking (SDN) has evolved to revolutionize next-generation networks, offering programmability for on-the-fly service provisioning, primarily supported by the OpenFlow (OF) protocol. The limited storage capacity of Ternary Content Addressable Memory (TCAM) for storing flow tables in OF switches introduces vulnerabilities, notably the Low-R

Junkai Jiang, Zeyu Han, Yuning Wang, Mengchi Cai

Driving risk assessment is crucial for both autonomous vehicles and human-driven vehicles. The driving risk can be quantified as the product of the probability that an event (such as collision) will occur and the consequence of that event. However, the probability of events occurring is often difficult to predict due to the uncertainty of drivers' or vehicle

Michał Borowski, Pierre Bousquet, Iwona Chlebicka, Benjamin Lledos

We establish that the Lavrentiev gap between Sobolev and Lipschitz maps does not occur for a scalar variational problem of the form: \[ \textrm{to minimize} \qquad u \mapsto \int_\Omega f(x,u,\nabla u)\,dx \,, \] under a Dirichlet boundary condition. Here, \(\Omega\) is a bounded Lipschitz open set in \(\rn\), \(N\geq 1\) and the function $f$ is required to

Prateek Chennuri, Yiheng Chi, Enze Jiang, G. M. Dilshan Godaliyadda

The proliferation of single-photon image sensors has opened the door to a plethora of high-speed and low-light imaging applications. However, data collected by these sensors are often 1-bit or few-bit, and corrupted by noise and strong motion. Conventional video restoration methods are not designed to handle this situation, while specialized quanta burst alg

Hao Wu, Donglin Bai, Shiqi Jiang, Qianxi Zhang

Video activity recognition has become increasingly important in robots and embodied AI. Recognizing continuous video activities poses considerable challenges due to the fast expansion of streaming video, which contains multi-scale and untrimmed activities. We introduce a novel system, CARS, to overcome these issues through adaptive video context modeling. Ad

Woojin Chae, Kihyuk Hong, Yufan Zhang, Ambuj Tewari

This paper proposes a computationally tractable algorithm for learning infinite-horizon average-reward linear mixture Markov decision processes (MDPs) under the Bellman optimality condition. Our algorithm for linear mixture MDPs achieves a nearly minimax optimal regret upper bound of $\widetilde{\mathcal{O}}(d\sqrt{\mathrm{sp}(v^*)T})$ over $T$ time steps wh

Deeparghya Dutta Barua, Md Sakib Ul Rahman Sourove, Md Fahim, Fabiha Haider

Visual Question Answer (VQA) poses the problem of answering a natural language question about a visual context. Bangla, despite being a widely spoken language, is considered low-resource in the realm of VQA due to the lack of proper benchmarks, challenging models known to be performant in other languages. Furthermore, existing Bangla VQA datasets offer littl

Sivangi Chatterjee, Srishti Ganguly, Avik Bose, Hrithik Raj Prasad

This project explores the application of machine learning techniques for music genre classification using the GTZAN dataset, which contains 100 audio files per genre. Motivated by the growing demand for personalized music recommendations, we focused on classifying five genres-Blues, Classical, Jazz, Hip Hop, and Country-using a variety of algorithms includin

Longtao Zhu, Hongyu Yang, Ge Song, Xin Ma

Current flight procedure design methods heavily rely on human-led design process, which is not only low auto-mation but also suffer from complex algorithm modelling and poor generalization. To address these challenges, this paper proposes an agent-driven flight procedure design method based on large language model, named Au-toFPDesigner, which utilizes multi

Noam Ginio, Michael Lindenbaum, Barak Fishbain, Dan Liberzon

Effective spatio-temporal measurements of water surface elevation (water waves) in laboratory experiments are crucial for scientific and engineering research. Existing techniques are often cumbersome, computationally heavy and generally suffer from limitations in wavenumber/frequency response. To address these challenges, we propose Wave (from) Polarized Lig

Zhewei Dai, Shilei Zeng, Haotian Liu, Xurui Li

We introduce SeaS, a unified industrial generative model for automatically creating diverse anomalies, authentic normal products, and precise anomaly masks. While extensive research exists, most efforts either focus on specific tasks, i.e., anomalies or normal products only, or require separate models for each anomaly type. Consequently, prior methods either

Yunqi Cai, Jiangnan Li, Dong Wang

Micromagnetics has made significant strides, particularly due to its wide-ranging applications in magnetic storage design. Numerical simulation is a cornerstone of micromagnetics research, relying on first-principle rules to compute the dynamic evolution of micromagnetic systems based on the renowned LLG equation, named after Landau, Lifshitz, and Gilbert. H

Andrew Fleck, Edward Furman, Yang Shen

Nowadays insurers have to account for potentially complex dependence between risks. In the field of loss reserving, there are many parametric and non-parametric models attempting to capture dependence between business lines. One common approach has been to use additive background risk models (ABRMs) which provide rich and interpretable dependence structures

Andrew Fleck, Edward Furman, Yang Shen

In order to properly manage risk, practitioners must understand the aggregate risks they are exposed to. Additionally, to properly price policies and calculate bonuses the relative riskiness of individual business units must be well understood. Certainly, Insurers and Financiers are interested in the properties of the sums of the risks they are exposed to an

Huyen Le, Khiet Dang, Nhung Nguyen, Mai Tran

Human-induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) are a powerful tool in advancing cardiovascular research and clinical applications. The maturation of sarcomere organization in hiPSC-CMs is crucial, as it supports the contractile function and structural integrity of these cells. Traditional methods for assessing this maturation like man

Vindhyawasini Prasad

Dark matter (DM) is a new type of invisible matter introduced to explain various features of recent astrophysical observations, including galaxy rotation curves and other fundamental characteristics of our universe. DM may couple to ordinary matter via portals, which open up possibilities for new particles, such as axion-like particle, light Higgs boson, dar

William Zhao

We introduce the stack-sorting map $\text{SC}_\sigma$ that sorts, in a right-greedy manner, an input permutation through a stack that avoids some vincular pattern $\sigma$. The stack-sorting maps of Cerbai et al. in which the stack avoids a pattern classically and Defant and Zheng in which the stack avoids a pattern consecutively follow as special cases. We

Ken Sekimoto

In the previous paper we have shown analytically that, if the drift function of the d-dimensional Langevin equation is the Langevin function with a properly chosen scale factor, then the evolution of the drift function is a martingale associated with the histories generated by the very Langevin equation. Moreover, we numerically demonstrated that those gener

Kun Wang, Zhiqiang Yan, Junkai Fan, Wanlu Zhu

In this paper, we introduce DCDepth, a novel framework for the long-standing monocular depth estimation task. Moving beyond conventional pixel-wise depth estimation in the spatial domain, our approach estimates the frequency coefficients of depth patches after transforming them into the discrete cosine domain. This unique formulation allows for the modeling

Wei Xie, Shuoyoucheng Ma, Zhenhua Wang, Enze Wang

The cognitive mechanism by which Large Language Models (LLMs) solve mathematical problems remains a widely debated and unresolved issue. Currently, there is little interpretable experimental evidence that connects LLMs' problem-solving with human cognitive psychology.To determine if LLMs possess human-like mathematical reasoning, we modified the problems use

Kent K. Chang, Anna Ho, David Bamman

Television is often seen as a site for subcultural identification and subversive fantasy, including in queer cultures. How might we measure subversion, or the degree to which the depiction of social relationship between a dyad (e.g. two characters who are colleagues) deviates from its typical representation on TV? To explore this question, we introduce the t

Linh Van Ma, Muhammad Ishfaq Hussain, Kin-Choong Yow, Moongu Jeon

The MS-GLMB filter offers a robust framework for tracking multiple objects through the use of multi-sensor data. Building on this, the MV-GLMB and MV-GLMB-AB filters enhance the MS-GLMB capabilities by employing cameras for 3D multi-sensor multi-object tracking, effectively addressing occlusions. However, both filters depend on overlapping fields of view fro

Woong Bae Jeon, Dong Hyun Park, Jong Sung Moon, Kyu-Young Kim

Scalable, reliable quantum light sources are essential for increasing quantum channel capacity and advancing quantum protocols based on photonic qubits. Although recent developments in solid-state quantum emitters have enabled the generation of single photons with high performance, the scalable integration of multiple quantum light sources onto practical opt

Silong Yong, Yaqi Xie, Simon Stepputtis, Katia Sycara

Volume rendering in neural radiance fields is inherently time-consuming due to the large number of MLP calls on the points sampled per ray. Previous works would address this issue by introducing new neural networks or data structures. In this work, We propose GL-NeRF, a new perspective of computing volume rendering with the Gauss-Laguerre quadrature. GL-NeRF

Jihyo Kim, Seulbi Lee, Sangheum Hwang

With the recent emergence of foundation models trained on internet-scale data and demonstrating remarkable generalization capabilities, such foundation models have become more widely adopted, leading to an expanding range of application domains. Despite this rapid proliferation, the trustworthiness of foundation models remains underexplored. Specifically, th

Shangning Xia, Hongjie Fang, Cewu Lu, Hao-Shu Fang

Generalization in robotic manipulation remains a critical challenge, particularly when scaling to new environments with limited demonstrations. This paper introduces CAGE, a novel robotic manipulation policy designed to overcome these generalization barriers by integrating a causal attention mechanism. CAGE utilizes the powerful feature extraction capabiliti

Takeshi Gotoda

We investigate enstrophy variations by collapse of point vortices in an inviscid flow and, in particular, focus on the enstrophy dissipation that is a significant property characterizing 2D turbulent flows. Point vortex is an ideal vortex whose vorticity is concentrated on a point and the dynamics of point vortices on an inviscid flow is described by the poi

Suning Huang, Zheyu Zhang, Tianhai Liang, Yihan Xu

Visual deep reinforcement learning (RL) enables robots to acquire skills from visual input for unstructured tasks. However, current algorithms suffer from low sample efficiency, limiting their practical applicability. In this work, we present MENTOR, a method that improves both the architecture and optimization of RL agents. Specifically, MENTOR replaces the

Jilong Li, Zhenxi Song, Jiaqi Wang, Meishan Zhang

Current EEG/MEG-to-text decoding systems suffer from three key limitations: (1) reliance on teacher-forcing methods, which compromises robustness during inference, (2) sensitivity to session-specific noise, hindering generalization across subjects, and (3) misalignment between brain signals and linguistic representations due to pre-trained language model ove

Xiaohang Xu, Renhe Jiang, Chuang Yang, Zipei Fan

With the popularity of location-based services, human mobility prediction plays a key role in enhancing personalized navigation, optimizing recommendation systems, and facilitating urban mobility and planning. This involves predicting a user's next POI (point-of-interest) visit using their past visit history. However, the uneven distribution of visitations o

Marie Roald, Magnus Breder Birkenes, Lars Gunnarsønn Bagøien Johnsen

Digital tools for text analysis have long been essential for the searchability and accessibility of digitised library collections. Recent computer vision advances have introduced similar capabilities for visual materials, with deep learning-based embeddings showing promise for analysing visual heritage. Given that many books feature visuals in addition to te

Ryan Diaz, Adam Imdieke, Vivek Veeriah, Karthik Desingh

Operating in unstructured environments like households requires robotic policies that are robust to out-of-distribution conditions. Although much work has been done in evaluating robustness for visuomotor policies, the robustness evaluation of a multisensory approach that includes force-torque sensing remains largely unexplored. This work introduces a novel,

Tarkes Dora Pallicity, Maximillian Krause, Thomas Böhlke

Statistical fluctuations of local tensorial fields beyond the mean are relevant to predict localized failure or overall behavior of the inelastic composites. The expression for second moments of the local fields can be established using the Hill-Mandel condition. Complete estimation of statistical fluctuations via second moments is usually ignored despite it

Naz Yaldiz, Amaresh Chakrabarti

The design of an inclusive product lifecycle is important for empowering stakeholders through their meaningful inclusion in lifecycle processes. To achieve this, the inclusion of stakeholders must be structured in a way that supports their empowerment. Inclusivity addresses the lifecycle context to improve how diverse stakeholders are included across phases,

Zilong Li

This papers presents the submission of team Ryu to the canceled SIGMORPHON 2024 shared task on subword tokenization. My submission explores whether morphological segmentation methods can be used as a part of subword tokenizers. I adopt two approaches: the statistical segmentation method Morfessor and a transformer based sequence-to-sequence (seq2seq) segment

Michael Huylo, Sina Taheri, Atila Novoselac

There is currently a large federal effort to decarbonize the country's electrical grid as part of the clean energy transition. The elimination of fossil fuel fired systems, and their replacement with intermittent renewable sources and other electric equipment will require better load management techniques to ensure a reliable grid. One strategy for maintaini

Haichuan Zhang, Meiyu Lin, Zhaoyi Liu, Renyuan Li

As generative models achieve great success, tampering and modifying the sensitive image contents (i.e., human faces, artist signatures, commercial logos, etc.) have induced a significant threat with social impact. The backdoor attack is a method that implants vulnerabilities in a target model, which can be activated through a trigger. In this work, we innova

Hongqiu Wang, Zhaohu Xing, Weitong Wu, Yijun Yang

Fundus imaging is a pivotal tool in ophthalmology, and different imaging modalities are characterized by their specific advantages. For example, Fundus Fluorescein Angiography (FFA) uniquely provides detailed insights into retinal vascular dynamics and pathology, surpassing Color Fundus Photographs (CFP) in detecting microvascular abnormalities and perfusion

Yuhao Gong, Yuchen Zhang, Fei Wang, Chi-Han Lee

As global climate change intensifies, accurate weather forecasting has become increasingly important, affecting agriculture, energy management, environmental protection, and daily life. This study introduces a hybrid model combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to predict historical temperature data. CNNs ar