December 2024 arXiv papers — page 62

Xingchen Song, Chengdong Liang, Binbin Zhang, Pengshen Zhang

Large Automatic Speech Recognition (ASR) models demand a vast number of parameters, copious amounts of data, and significant computational resources during the training process. However, such models can merely be deployed on high-compute cloud platforms and are only capable of performing speech recognition tasks. This leads to high costs and restricted capab

Bhupendra Acharya, Dario Lazzaro, Antonio Emanuele Cinà, Thorsten Holz

With the widespread use of social media, organizations, and individuals use these platforms to raise funds and support causes. Unfortunately, this has led to the rise of scammers in soliciting fraudulent donations. In this study, we conduct a large-scale analysis of donation-based scams on social media platforms. More specifically, we studied profile creatio

Jianming Chen, Yawen Wang, Junjie Wang, Xiaofei Xie

Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has proveided explanations for the actions or states of agents, yet falls short in understanding the black-boxed agent's importance within a MAS and the overall team strategy. To bridge this gap, we propose EMAI, a novel agent-

Zhuomeng Zhang, Fangqi Li, Chong Di, Hongyu Zhu

Despite the impressive synthesis quality of text-to-image (T2I) diffusion models, their black-box deployment poses significant regulatory challenges: Malicious actors can fine-tune these models to generate illegal content, circumventing existing safeguards through parameter manipulation. Therefore, it is essential to verify the integrity of T2I diffusion mod

Jen-Hao Rick Chang, Yuyang Wang, Miguel Angel Bautista Martin, Jiatao Gu

We introduce a latent 3D representation that models 3D surfaces as probability density functions in 3D, i.e., p(x,y,z), with flow-matching. Our representation is specifically designed for consumption by machine learning models, offering continuity and compactness by construction while requiring only point clouds and minimal data preprocessing. Despite being

Gayatri Singh, Arvind, Kavita Dorai

Neutrino oscillations can be efficiently simulated on a quantum computer using the Pontecorvo-Maki-Nakagawa-Sakata (PMNS) theory in close analogy to the physical processes realized in experiments. We simulate three-flavor neutrino oscillations on a two-qubit NMR quantum information processor. The three-flavor neutrino states were encoded into the two-qubit s

Biman Barua, M. Shamim Kaiser

The paper presents a framework of microservices-based architecture dedicated to enhancing the performance of real-time travel reservation systems using the power of predictive analytics. Traditional monolithic systems are bad at scaling and performing with high loads, causing backup resources to be underutilized along with delays. To overcome the above-state

Andrés F. Ducuara, Ryo Takakura, Fernando J. Hernandez, Cristian E. Susa

We introduce multi-object operational tasks for measurement incompatibility in the form of multi-object quantum subchannel discrimination and exclusion games with prior information, where a player can simultaneously harness the resources contained within both a quantum state and a set of measurements. We show that any fully or partially resourceful pair of o

Yangyang Guo, Ziwei Xu, Xilie Xu, YongKang Wong

This technical report introduces our top-ranked solution that employs two approaches, \ie suffix injection and projected gradient descent (PGD) , to address the TiFA workshop MLLM attack challenge. Specifically, we first append the text from an incorrectly labeled option (pseudo-labeled) to the original query as a suffix. Using this modified query, our secon

Xing-Yu Li, Jun Wang, Zhi-Tao Wen

We show a necessary and sufficient condition on the existence of finite order entire solutions of linear differential equations $$ f^{(n)}+a_{n-1}f^{(n-1)}+\cdots+a_1f'+a_0f=0,\eqno(+) $$ where $a_i$ are exponential sums for $i=0,\ldots,n-1$ with all positive (or all negative) rational frequencies and constant coefficients. Moreover, under the condition that

Yuhao Yang, Yue Wang, Dongxu Li, Ziyang Luo

Digital agents for automating tasks across different platforms by directly manipulating the GUIs are increasingly important. For these agents, grounding from language instructions to target elements remains a significant challenge due to reliance on HTML or AXTree inputs. In this paper, we introduce Aria-UI, a large multimodal model specifically designed for

Burcu Bektaş Demirci, Ferdağ Kahraman Aksoyak, Murat Babaarslan

In this paper, we study $K^{\alpha}$--translators on parallel surfaces and canal surfaces in 3-dimensional Euclidean space $\mathbb{E}^3$. First, we investigate the condition under which two parallel surfaces can become $K^{\alpha}$--translators moving with the same speed $w$. Then, we examine $K^{\alpha}$--translators on canal surfaces and we show that if a

Yury Kochetkov, Lev Pyatko

In this experimental work we study billiard trajectories in triangular pyramids and try to establish conditions that guarantee the existence (or absence) of 4-cycles (there can be not more, than three of them). We formulate conjectures and prove some statements. For example, if a pyramid has two orthogonal faces, then it has not more than two 4-cycles. Also

Jianfei Xu

This study analyzes 13,218 product reviews from JD.com, covering four categories: mobile phones, computers, cosmetics, and food. A novel method for feature label extraction is proposed by integrating dependency parsing and sentiment polarity analysis. The proposed method addresses the challenges of low robustness in existing extraction algorithms and signifi

Jotaro Sakamiya, I-Chao Shen, Jinsong Zhang, Mustafa Doga Dogan

Creating high-quality 3D avatars using 3D Gaussian Splatting (3DGS) from a monocular video benefits virtual reality and telecommunication applications. However, existing automatic methods exhibit artifacts under novel poses due to limited information in the input video. We propose AvatarPerfect, a novel system that allows users to iteratively refine 3DGS ava

Jiaming Cheng, Duong Thuy Anh Nguyen, Duong Tung Nguyen

Edge computing allows Service Providers (SPs) to enhance user experience by placing their services closer to the network edge. Determining the optimal provisioning of edge resources to meet the varying and uncertain demand cost-effectively is a critical task for SPs. This paper introduces a novel two-stage multi-period robust model for edge service placement

Bang Nguyen, Mayank Panwar, Rob Hovsapian, Yashodhan Agalgaonkar

Internet of Things (IoT) devices in smart grids enable intelligent energy management for grid managers and personalized energy services for consumers. Investigating a smart grid with IoT devices requires a simulation framework with IoT devices modeling. However, there lack comprehensive study on the modeling of IoT devices in smart grids. This paper investig

Zhi Gao, Bofei Zhang, Pengxiang Li, Xiaojian Ma

The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks. In this paper, we propose a multi-modal agent tuning method that automatically generates multi-modal tool-usage data and tunes a vision-language model (VLM) as

Brian J Chan, Chao-Ting Chen, Jui-Hung Cheng, Hen-Hsen Huang

Retrieval-augmented generation (RAG) has gained traction as a powerful approach for enhancing language models by integrating external knowledge sources. However, RAG introduces challenges such as retrieval latency, potential errors in document selection, and increased system complexity. With the advent of large language models (LLMs) featuring significantly

Quoc Nam Trinh, Bang Nguyen, Rob Hovsapian

This paper proposes an advanced control strategy to eliminate both current sharing error and DC circulating current caused by line impedance mismatched and measurement errors in islanded AC microgrid system. The proposed adaptive virtual impedance scheme is developed with the aid of a low bandwidth communication and a simple PI compensator to adaptively adju

Gyutae Park, Ingeol Baek, ByeongJeong Kim, Joongbo Shin

Dialogue intent classification aims to identify the underlying purpose or intent of a user's input in a conversation. Current intent classification systems encounter considerable challenges, primarily due to the vast number of possible intents and the significant semantic overlap among similar intent classes. In this paper, we propose a novel approach to few

Yichen Liu, Abhijit Dasgupta, Qiwei He

Music Genre Classification is one of the most popular topics in the fields of Music Information Retrieval (MIR) and digital signal processing. Deep Learning has emerged as the top performer for classifying music genres among various methods. The letter introduces a novel approach by combining ensemble learning with attention to sub-components, aiming to enha

Guanzhong Zeng, Jingjing Wang, Zefu Xu, Pengwei Yin

Gaze estimation methods encounter significant performance deterioration when being evaluated across different domains, because of the domain gap between the testing and training data. Existing methods try to solve this issue by reducing the deviation of data distribution, however, they ignore the existence of label deviation in the data due to the acquisitio

Amin Pishehvar, Zhaoyou Wang, Yujie Zhu, Yu Jiang

Cavity magnonics is a promising field focusing the interaction between spin waves (magnons) and other types of signals. In cavity magnonics, the function of isolating magnons from the cavity to allow signal storage and processing fully in the magnonic domain is highly desired, but its realization is often hindered by the lack of necessary tunability on the i

Min Huang, Zifeng Xie, Bo Sun, Ning Wang

Multi-source domain adaptation (MSDA) plays an important role in industrial model generalization. Recent efforts on MSDA focus on enhancing multi-domain distributional alignment while omitting three issues, e.g., the class-level discrepancy quantification, the unavailability of noisy pseudo-label, and source transferability discrimination, potentially result

Zheng Chen, Yasuko Matsubara, Yasushi Sakurai, Jimeng Sun

Deep learning models have recently shown great success in classifying epileptic patients using EEG recordings. Unfortunately, classification-based methods lack a sound mechanism to detect the onset of seizure events. In this work, we propose a two-stage framework, SODor, that explicitly models seizure onset through a novel task formulation of subsequence clu

Yixuan Guo, Qingwei Jiang, Mingliang Xiong, Wen Fang

With the increasing demand for internet of things (IoT) applications, especially for location-based services, how to locate passive mobile targets (MTs) with minimal beam control has become a challenge. Resonant beam systems are considered promising IoT technologies with advantages such as beam self-alignment and energy concentration. To establish a resonant

Yixuan Guo, Mingliang Xiong, Wen Fang, Qingwei Jiang

With the rapid development of the internet of things (IoT), location-based services are becoming increasingly prominent in various aspects of social life, and accurate location information is crucial. However, RF-based indoor positioning solutions are severely limited in positioning accuracy due to signal transmission losses and directional difficulties, and

Yuzhi Wu, Jun Liu, Guangfeng Jiang, Weijian Liu

As a cost-effective and robust technology, automotive radar has seen steady improvement during the last years, making it an appealing complement to commonly used sensors like camera and LiDAR in autonomous driving. Radio frequency data with rich semantic information are attracting more and more attention. Most current radar-based models take radio frequency

Xiaoqiang Kang, Zimu Wang, Xiaobo Jin, Wei Wang

Solving tabular math word problems (TMWPs) has become a critical role in evaluating the mathematical reasoning ability of large language models (LLMs), where large-scale TMWP samples are commonly required for LLM fine-tuning. Since the collection of high-quality TMWP datasets is costly and time-consuming, recent research has concentrated on automatic TMWP ge

Andrea Aiello

Bell's theorem proves the incompatibility between quantum mechanics and local realistic hidden-variable theories. In this paper we show that, contrary to a common belief, the theoretical proof of Bell's theorem is not affected by counterfactual reasoning. Then, we demonstrate that the experimental verification of this theorem may be affected in an unknowable

Pochun Li

This paper proposes a frequent pattern data mining algorithm based on support vector machine (SVM), aiming to solve the performance bottleneck of traditional frequent pattern mining algorithms in high-dimensional and sparse data environments. By converting the frequent pattern mining task into a classification problem, the SVM model is introduced to improve

Lea Gassab, Onur Pusuluk, Marco Cattaneo, Özgür E. Müstecaplıoğlu

This perspective explores various quantum models of consciousness from the viewpoint of quantum information science, offering potential ideas and insights. The models under consideration can be categorized into three distinct groups based on the level at which quantum mechanics might operate within the brain: those suggesting that consciousness arises from e

Xingyu Xiao, Peng Chen, Ben Qi, Hongru Zhao

Human reliability analysis (HRA) is crucial for evaluating and improving the safety of complex systems. Recent efforts have focused on estimating human error probability (HEP), but existing methods often rely heavily on expert knowledge,which can be subjective and time-consuming. Inspired by the success of large language models (LLMs) in natural language pro

Wenkang Du, Haiping Huang

In realistic neural circuits, both neurons and synapses are coupled in dynamics with separate time scales. The circuit functions are intimately related to these coupled dynamics. However, it remains challenging to understand the intrinsic properties of the coupled dynamics. Here, we develop the neuron-synapse coupled quasi-potential method to demonstrate how

Shanshan Liu, Rhonald Burgos, Enze Zhang, Naizhou Wang

The discovery of the nonlinear Hall effect provides an avenue for studying the interplay among symmetry, topology, and phase transitions, with potential applications in signal doubling and high-frequency rectification. However, practical applications require devices fabricated on large area thin film as well as room-temperature operation. Here, we demonstrat

Xiaoting Zhang, Tao Wang, Junhao Ji

While large-scale face datasets have advanced deep learning-based face analysis, they also raise privacy concerns due to the sensitive personal information they contain. Recent schemes have implemented differential privacy to protect face datasets. However, these schemes generally treat each image as a separate database, which does not fully meet the core re

Van Thuy Hoang, O-Joun Lee

This study aims to build a pre-trained Graph Neural Network (GNN) model on molecules without human annotations or prior knowledge. Although various attempts have been proposed to overcome limitations in acquiring labeled molecules, the previous pre-training methods still rely on semantic subgraphs, i.e., functional groups. Only focusing on the functional gro

Danial Kamali, Elham J. Barezi, Parisa Kordjamshidi

Compositional generalization is crucial for artificial intelligence agents to solve complex vision-language reasoning tasks. Neuro-symbolic approaches have demonstrated promise in capturing compositional structures, but they face critical challenges: (a) reliance on predefined predicates for symbolic representations that limit adaptability, (b) difficulty in

Hengxu Yan, Haoshu Fang, Cewu Lu

Dexterous manipulation has received considerable attention in recent research. Predominantly, existing studies have concentrated on reinforcement learning methods to address the substantial degrees of freedom in hand movements. Nonetheless, these methods typically suffer from low efficiency and accuracy. In this work, we introduce a novel reinforcement learn

Masahiro Ohkuma, Eikichi Kimura, Eunsang Lee, Ryo Matsumoto

Monolithic integration, which refers to the incorporation of all device functionalities within a single material, shows significant potential for creating scalable solid-state quantum devices. This study demonstrated the coherent control of nitrogen-vacancy (NV) spins using an electronic circuit monolithically integrated within diamond: a patterned, conducti

Ion Grama, Ronan Lauvergnat, Émile Le Page

Let $(Z_n)_{n\geq 0}$ be a critical branching process in a random environment defined by a Markov chain $(X_n)_{n\geq 0}$ with values in a finite state space $\mathbb X$. Let $ S_n = \sum_{k=1}^n \ln f_{X_k}'(1)$ be the Markov walk associated to $(X_n)_{n\geq 0}$, where $f_i$ is the offspring generating function when the environment is $i \in \mathbb X$. Con

Jessica Y. Bo, Sophia Wan, Ashton Anderson

As Large Language Models become integral to decision-making, optimism about their power is tempered with concern over their errors. Users may over-rely on LLM advice that is confidently stated but wrong, or under-rely due to mistrust. Reliance interventions have been developed to help users of LLMs, but they lack rigorous evaluation for appropriate reliance.

Gabriela Pinto, Charles Bickham, Tanishq Salkar, Joyston Menezes

This paper presents the TikTok 2024 U.S. Presidential Election Dataset, a large-scale, resource designed to advance research into political communication and social media dynamics. The dataset comprises 3.14 million videos published on TikTok between November 1, 2023, and October 16, 2024, encompassing video ids and transcripts. Data collection was conducted

Hetvi Waghela, Jaydip Sen, Sneha Rakshit

Adversarial attacks pose a significant threat to the reliability of pre-trained language models (PLMs) such as GPT, BERT, RoBERTa, and T5. This paper presents Adversarial Robustness through Dynamic Ensemble Learning (ARDEL), a novel scheme designed to enhance the robustness of PLMs against such attacks. ARDEL leverages the diversity of multiple PLMs and dyna

Ryien Hosseini, Filippo Simini, Venkatram Vishwanath, Henry Hoffmann

Recent advancements in graph representation learning have shifted attention towards dynamic graphs, which exhibit evolving topologies and features over time. The increased use of such graphs creates a paramount need for generative models suitable for applications such as data augmentation, obfuscation, and anomaly detection. However, there are few generative

Yanshun Zhao, Jingrun Chen, Zhiwen Zhang

The Random Batch Method (RBM) is an effective technique to reduce the computational complexity when solving certain stochastic differential problems (SDEs) involving interacting particles. It can transform the computational complexity from O(N^2) to O(N), where N represents the number of particles. However, the traditional RBM can only be effectively applied

Kazuya Iwata, Keiichi Maeda

Most previous efforts for hydrodynamic studies on detonation in the context of Type Ia supernovae did not take into account the scale of the cellular structure for a criterion in initiation, propagation, quenching, and the resolution requirement of detonation, whereas it is quite common to consider cell sizes in the discussion on terrestrial detonation in ch

Chengyi Liu, Jiahao Zhang, Shijie Wang, Wenqi Fan

With the prevalence of social networks on online platforms, social recommendation has become a vital technique for enhancing personalized recommendations. The effectiveness of social recommendations largely relies on the social homophily assumption, which presumes that individuals with social connections often share similar preferences. However, this foundat

Ye Jiang, Wen-Biao Han

Gravitational waves (GWs) are regarded as standard sirens for Cosmology. GWs from compact binary coalescence (CBC) can directly determine the luminosity distance but usually can not obtain information about the redshift. However, if the universe is not flat but accelerating, GWs should carry this cosmological effect. In this Letter, for the first time, we ex

Yuhao Li, Jianping Li, Zhen Dong, Yuan Wang

Image to point cloud global localization is crucial for robot navigation in GNSS-denied environments and has become increasingly important for multi-robot map fusion and urban asset management. The modality gap between images and point clouds poses significant challenges for cross-modality fusion. Current cross-modality global localization solutions either r

Xinyang Tong, Pengxiang Ding, Yiguo Fan, Donglin Wang

This paper addresses the inherent inference latency challenges associated with deploying multimodal large language models (MLLM) in quadruped vision-language-action (QUAR-VLA) tasks. Our investigation reveals that conventional parameter reduction techniques ultimately impair the performance of the language foundation model during the action instruction tunin

Fan Zhang

In this brief note, we tentatively investigate the possibility that the radio filaments are produced when the Galactic center wind washes over magnetic field structures. The electrons and ions, with their disparate charge-to-mass ratios, are deflected differently by the magnetic field, and a current results. The current is subsequently Z-pinched into filamen

Takero Yoshida, Yuikazu Ito, Yoshihiro Fujiwara, Shinji Tsuchida

Japan Agency for Marine-Earth Science and Technology (JAMSTEC) has made available the JAMSTEC Earth Deep-sea Image (J-EDI), a deep-sea video and image archive (https://www.godac.jamstec.go.jp/jedi/e/index.html). This archive serves as a valuable resource for researchers and scholars interested in deep-sea imagery. The dataset comprises images and videos of d

Joshua Holder, Natasha Jaques, Mehran Mesbahi

Assignment problems are a classic combinatorial optimization problem in which a group of agents must be assigned to a group of tasks such that maximum utility is achieved while satisfying assignment constraints. Given the utility of each agent completing each task, polynomial-time algorithms exist to solve a single assignment problem in its simplest form. Ho

Saleh Momeni, Sahisnu Mazumder, Bing Liu

Continual learning (CL) learns a sequence of tasks incrementally. This paper studies the challenging CL setting of class-incremental learning (CIL). CIL has two key challenges: catastrophic forgetting (CF) and inter-task class separation (ICS). Despite numerous proposed methods, these issues remain persistent obstacles. This paper proposes a novel CIL method

Yichun Tai, Zhenzhen Huang, Tao Peng, Zhijiang Zhang

Current saliency-based defect detection methods show promise in industrial settings, but the unpredictability of defects in steel production environments complicates dataset creation, hampering model performance. Existing data augmentation approaches using generative models often require pixel-level annotations, which are time-consuming and resource-intensiv

Apurba Das

Our primary aim in this paper is to introduce and study the cohomology of a Nijenhuis operator and of a Nijenhuis algebra. Our cohomology of a Nijenhuis algebra controls the simultaneous deformations of the underlying associative structure and the Nijenhuis operator. We interpret the second cohomology group as the space of all isomorphism classes of abelian

Fumika Suzuki, Wojciech H. Zurek

The formation of topological defects in second-order phase transitions can be investigated by solving partial differential equations for the evolution of the order parameter in space and time, such as the Langevin equation. We demonstrate that the ordinary differential equations governing either the temporal or spatial dependence in the Langevin equation pro

Eliot W. Robson, Jack Spalding-Jamieson, Da Wei Zheng

We show the following problems are in $\textsf{P}$: 1. The contiguous art gallery problem -- a variation of the art gallery problem where each guard can protect a contiguous interval along the boundary of a simple polygon. This was posed at the open problem session at CCCG '24 by Thomas C. Shermer. 2. The polygon separation problem for line segments -- For t

Alfonso Jaimes-Nájera

In this work, a group theory-based formulation that introduces new classes of dihedral-symmetric beams is presented. Our framework leverages the algebraic properties of the dihedral group of rotations and reflections to transform input beams into closed-form families of dihedral-invariant wavefields, which will be referred to as dihedral beams. Each transfor

Chaehyeong Ha, Yoon Jang Chung

Quantum materials have been in the limelight for several years now. These materials exhibit intriguing quantum phenomena, which when harnessed properly, promise extraordinary advancements across various scientific and technological domains. To fully exploit their potential, it is imperative to synthesize such quantum materials in thin film form so that they

Hongyi Cao, Gang Xu, Renshu Gu, Jinlan Xu

We introduce a novel offset meshing approach that can robustly handle a 3D surface mesh with an arbitrary geometry and topology configurations, while nicely capturing the sharp features on the original input for both inward and outward offsets. Compared to the existing approaches focusing on constant-radius offset, to the best of our knowledge, we propose th

Saleh Momeni, Sahisnu Mazumder, Zixuan Ke, Bing Liu

Existing continual learning (CL) methods mainly rely on fine-tuning or adapting large language models (LLMs). They still suffer from catastrophic forgetting (CF). Little work has been done to exploit in-context learning (ICL) to leverage the extensive knowledge within LLMs for CL without updating any parameters. However, incrementally learning each new task

Sergei Masaev, Ivan Oreshnikov, Nikita Ivanitskiy, Valentina Vingert

Digital transformation acts as a main factor in the development and competitiveness of Japanese companies. In this context, the digital copy management algorithm based on the P2M (Project to Method) method plays a significant role in increasing efficiency and reducing costs through the implementation of digital technologies. This research aims to develop and

Clément Jambon, Changwoon Choi, Dongsu Zhang, Olga Sorkine-Hornung

Photorealistic 3D scene generation is challenging due to the scarcity of large-scale, high-quality real-world 3D datasets and complex workflows requiring specialized expertise for manual modeling. These constraints often result in slow iteration cycles, where each modification demands substantial effort, ultimately stifling creativity. We propose a fast, exe

Zhengyu Zou

The deep diagonal map $T_k$ acts on planar polygons by connecting the $k$-th diagonals and intersecting them successively. The map $T_2$ is the pentagram map, and $T_k$ is a generalization. We study the action of $T_k$ on two subsets of the so-called twisted polygons, which we term type-$α$ and type-$β$ $k$-spirals. For $k \geq 2$, $T_{k}$ preserves both typ

Taketo Akama, Zhuohao Zhang, Pengcheng Li, Kotaro Hongo

Recent studies have demonstrated that the representations of artificial neural networks (ANNs) can exhibit notable similarities to cortical representations when subjected to identical auditory sensory inputs. In these studies, the ability to predict cortical representations is probed by regressing from ANN representations to cortical representations. Buildin

Nahian Ahmed, Mark Roth, Tyler A. Hallman, W. Douglas Robinson

Citizen science biodiversity data present great opportunities for ecology and conservation across vast spatial and temporal scales. However, the opportunistic nature of these data lacks the sampling structure required by modeling methodologies that address a pervasive challenge in ecological data collection: imperfect detection, i.e., the likelihood of under

Abhimanyu Singareddy, Pradeep R. Nair

Organic-inorganic hybrid perovskite solar cells (PSC) have demonstrated impressive performance improvement. Among the various characteristics, the time-dependent current-voltage (J-V) hysteresis allows a direct exploration of various critical phenomena that affect the stability of PSCs. The hysteresis is associated with various spatial heterogeneity-related

Shuto Kawai, Shun Sato, Takayasu Matsuo

Numerical schemes that conserve invariants have demonstrated superior performance in various contexts, and several unified methods have been developed for constructing such schemes. However, the mathematical properties of these schemes remain poorly understood, except in norm-preserving cases. This study introduces a novel analytical framework applicable to

Ion Grama, Émile Le Page, Marc Peigné

We prove an invariance principle for non-stationary random processes and establish a rate of convergence under a new type of mixing condition. The dependence is exponentially decaying in the gap between the past and the future and is controlled by an assumption on the characteristic function of the finite dimensional increments of the process. The distinct f

Yanna Ding, Zijie Huang, Xiao Shou, Yihang Guo

Learning curve extrapolation predicts neural network performance from early training epochs and has been applied to accelerate AutoML, facilitating hyperparameter tuning and neural architecture search. However, existing methods typically model the evolution of learning curves in isolation, neglecting the impact of neural network (NN) architectures, which inf

Shuaijun Chen, Omid Tavallaie, Niousha Nazemi, Xin Chen

As data volumes expand rapidly, distributed machine learning has become essential for addressing the growing computational demands of modern AI systems. However, training models in distributed environments is challenging with participants hold skew, Non-Independent-Identically distributed (Non-IID) data. Low-Rank Adaptation (LoRA) offers a promising solution

L. M. Platt, D. Baillie, P. B. Blakie

We develop a linear response theory to provide a unified description of two recent spectroscopy protocols for probing one-dimensional supersolid states realized in cold-atom systems. Both protocols involve applying a periodic optical potential to excite the supersolid and determine its excitation frequencies and density response characteristics. This informa

Cong Yu, Shixin Zhu, Hao Chen, Yang Li

In this paper, we employ group rings and automorphism groups of binary linear codes to construct new record-breaking binary linear codes. We consider the semidirect product of abelian groups and cyclic groups and use these groups to construct linear codes. Finally, we obtain some linear codes which have better parameters than the code in \cite{bib5}. All the

Yixiong Huo, Guangfeng Jiang, Hongyang Wei, Ji Liu

3D Gaussian Splatting (3D GS) has gained popularity due to its faster rendering speed and high-quality novel view synthesis. Some researchers have explored using 3D GS for reconstructing driving scenes. However, these methods often rely on various data types, such as depth maps, 3D boxes, and trajectories of moving objects. Additionally, the lack of annotati

Geoff Penington, Edward Witten

In bosonic JT gravity, minimally coupled to bulk matter, there exists a single, delta-function-normalisable state in each $SL(2,R)$ representation of the matter QFT for any pair of positive energies $E_L, E_R$ at the left and right boundaries. In $\mathcal{N} = 2$ super-JT gravity coupled to matter, we show that there exists a single normalisable state in ea

Ling Zhang, Zhichao Hou, Tingxiang Ji, Yuanyuan Xu

Model interpretability and explainability have garnered substantial attention in recent years, particularly in decision-making applications. However, existing interpretability tools often fall short in delivering satisfactory performance due to limited capabilities or efficiency issues. To address these challenges, we propose a novel post-hoc method: Iterati

Chirag Sakhuja, Charles Hong, Calvin Lin

This paper presents a tool for automatically exploring the design space of deep learning accelerators (DLAs). Our main advancement is Starlight, a data-driven performance model that uses transfer learning to bridge the gap between fast, low-fidelity evaluation methods (such as analytical models) and slow, high-fidelity evaluation methods (such as RTL simulat

Zheyuan Zhang, Yiyang Li, Nhi Ha Lan Le, Zehong Wang

Diet plays a critical role in human health, yet tailoring dietary reasoning to individual health conditions remains a major challenge. Nutrition Question Answering (QA) has emerged as a popular method for addressing this problem. However, current research faces two critical limitations. On one hand, the absence of datasets involving user-specific medical inf

Zhao-Rong Lai, Xiaotian Wu, Liangda Fang, Ziliang Chen

The Weber location problem is widely used in several artificial intelligence scenarios. However, the gradient of the objective does not exist at a considerable set of singular points. Recently, a de-singularity subgradient method has been proposed to fix this problem, but it can only handle the $q$-th-powered $\ell_2$-norm case ($1\leqslant q<2$), which has

Zilin Huang, Zihao Sheng, Yansong Qu, Junwei You

In recent years, reinforcement learning (RL)-based methods for learning driving policies have gained increasing attention in the autonomous driving community and have achieved remarkable progress in various driving scenarios. However, traditional RL approaches rely on manually engineered rewards, which require extensive human effort and often lack generaliza

Michael Giudici, Luke Morgan, Cheryl E. Praeger

For a finite group $A$ with normal subgroup $G$, a subgroup $U$ of $G$ is an $A$-prime-power-covering subgroup if $U$ meets every $A$-conjugacy-class of elements of $G$ of prime power order. It is conjectured that $|G:U|$ is bounded by some function of $|A:G|$, and this conjecture has number theoretic implications for relative Brauer groups of algebraic numb

Xianlin Zeng, Yufeng Wang, Yuqi Sun, Guodong Guo

Graph Neural Networks (GNNs) have recently gained widespread attention as a successful tool for analyzing graph-structured data. However, imperfect graph structure with noisy links lacks enough robustness and may damage graph representations, therefore limiting the GNNs' performance in practical tasks. Moreover, existing generative architectures fail to fit

Xin-ran Yang, Guo-yun Shao, Chong-long Xie, Zhi-Peng Li

We investigate the correlations between net baryon number and electric charge up to sixth order related to the interactions of nuclear matter at low temperature, and explore their relationship with the nuclear liquid-gas phase transition (LGPT) within the framework of the nonlinear Walecka model. The calculation shows that strong correlations between the bar

Qi Zang, Jiayi Yang, Shuang Wang, Dong Zhao

Data-driven deep learning models have enabled tremendous progress in change detection (CD) with the support of pixel-level annotations. However, collecting diverse data and manually annotating them is costly, laborious, and knowledge-intensive. Existing generative methods for CD data synthesis show competitive potential in addressing this issue but still fac

Zhang Siyue, Xue Yuxiang, Zhang Yiming, Wu Xiaobao

Understanding temporal relations and answering time-sensitive questions is crucial yet a challenging task for question-answering systems powered by large language models (LLMs). Existing approaches either update the parametric knowledge of LLMs with new facts, which is resource-intensive and often impractical, or integrate LLMs with external knowledge retrie

Flint Xiaofeng Fan, Cheston Tan, Yew-Soon Ong, Roger Wattenhofer

In the era of increasing privacy concerns and demand for personalized experiences, traditional Reinforcement Learning with Human Feedback (RLHF) frameworks face significant challenges due to their reliance on centralized data. We introduce Federated Reinforcement Learning with Human Feedback (FedRLHF), a novel framework that decentralizes the RLHF process. F

Tao Zhou, Kai Ye, Zeyu Shi, Jiajing Lin

Numerous remarkable advancements have been made in accuracy, speed, and parallelism for solving the Unmanned Aerial Vehicle Route Planing (UAVRP). However, existing UAVRP solvers face challenges when attempting to scale effectively and efficiently for larger instances. In this paper, we present a generalization framework that enables current UAVRP solvers to

Justin Dachille, Chao Huang, Xin Liu

Split Federated Learning (SFL) is a distributed machine learning paradigm that combines federated learning and split learning. In SFL, a neural network is partitioned at a cut layer, with the initial layers deployed on clients and remaining layers on a training server. There are two main variants of SFL: SFL-V1 where the training server maintains separate se

William Bekerman, Marina Bogomolov, Ruth Heller, Matthew Spivey

The harmful effects of growing up with a parent with an alcohol use disorder have been closely examined in children and adolescents, and are reported to include mental and physical health problems, interpersonal difficulties, and a worsened risk of future substance use disorders. However, few studies have investigated how these impacts evolve into later life

Shengyu Feng, Yiming Yang

Mixed Integer Linear Program (MILP) solvers are mostly built upon a Branch-and-Bound (B\&B) algorithm, where the efficiency of traditional solvers heavily depends on hand-crafted heuristics for branching. The past few years have witnessed the increasing popularity of data-driven approaches to automatically learn these heuristics. However, the success of thes

Renhao Ye, Shiyin Shen, Rafael S. de Souza, Quanfeng Xu

The DESI Legacy Imaging Surveys (DESI-LIS) comprise three distinct surveys: the Dark Energy Camera Legacy Survey (DECaLS), the Beijing-Arizona Sky Survey (BASS), and the Mayall z-band Legacy Survey (MzLS). The citizen science project Galaxy Zoo DECaLS 5 (GZD-5) has provided extensive and detailed morphology labels for a sample of 253,287 galaxies within the

Ruiqi Shu, Hao Wu, Yuan Gao, Fanghua Xu

The unusually warm sea surface temperature events known as marine heatwaves (MHWs) have a profound impact on marine ecosystems. Accurate prediction of extreme MHWs has significant scientific and financial worth. However, existing methods still have certain limitations, especially in the most extreme MHWs. In this study, to address these issues, based on the

Qidong Wu, Fengqi Yi

Spatiotemporal pattern formations in two-layer coupled reaction-diffusion Lengyel-Epstein system with distributed delayed couplings are investigated. Firstly, for the original decoupled system, it is proved that when the intra-reactor diffusion rate $\ep$ of the inhibitor is sufficiently small and the intra-reactor diffusion rate $d$ of the inhibitor is larg

Linh H. Nghiem, Francis. K. C. Hui, Samuel Muller, A. H. Welsh

Sliced inverse regression (SIR) is a popular sufficient dimension reduction method that identifies a few linear transformations of the covariates without losing regression information with the response. In high-dimensional settings, SIR can be combined with sparsity penalties to achieve sufficient dimension reduction and variable selection simultaneously. Ne

Lin Shi, Jun Shen, Kening Lu

We study the long-term behavior of the distribution of the solution process to the non-autonomous McKean-Vlasov stochastic delay lattice system defined on the integer set $\mathbb{Z}$. Specifically, we first establish the well-posedness of solutions for this non-autonomous, distribution-dependent stochastic delay lattice system. Then, we prove the existence

Weizhi Xian, Mingliang Zhou, Leong Hou U, Zhengguo Li

In this paper, we propose a Physical Imaging Guided perceptual framework for Underwater Image Quality Assessment (UIQA), termed PIGUIQA. First, we formulate UIQA as a comprehensive problem that considers the combined effects of direct transmission attenuation and backward scattering on image perception. By leveraging underwater radiative transfer theory, we

Ke Yan, Qing Cai, Fan Zhang, Ziyan Cao

Although semi-supervised learning has made significant advances in the field of medical image segmentation, fully annotating a volumetric sample slice by slice remains a costly and time-consuming task. Even worse, most of the existing approaches pay much attention to image-level information and ignore semantic features, resulting in the inability to perceive