May 2024 arXiv papers — page 52

Pascal Bergsträßer, Chris Köcher, Anthony Widjaja Lin, Georg Zetzsche

Formal language theory has recently been successfully employed to unravel the power of transformer encoders. This setting is primarily applicable in Natural Language Processing (NLP), as a token embedding function (where a bounded number of tokens is admitted) is first applied before feeding the input to the transformer. On certain kinds of data (e.g. time s

Chun-Xue Yuan, Zhao Zhang, Chengfeng Cai, Yi-Lei Tang

The vector boson dark matter particles which stem from some broken gauge symmetries usually requires some unbroken symmetries to keep themselves stable. In the previous literature, some simplest cases have been discussed, in which the unbroken symmetry is provided by a remnant subgroup of the gauge group. It would be interesting to ask whether all the possib

Yunlong Song, Davide Scaramuzza

Control systems are at the core of every real-world robot. They are deployed in an ever-increasing number of applications, ranging from autonomous racing and search-and-rescue missions to industrial inspections and space exploration. To achieve peak performance, certain tasks require pushing the robot to its maximum agility. How can we design control algorit

Roel Bouman, Linda Schmeitz, Luco Buise, Jacco Heres

In this paper we present novel methodology for automatic anomaly and switch event filtering to improve load estimation in power grid systems. By leveraging unsupervised methods with supervised optimization, our approach prioritizes interpretability while ensuring robust and generalizable performance on unseen data. Through experimentation, a combination of b

Salvatore Capozziello, Maurizio Capriolo

We investigate the polarization modes of gravitational waves in $f(Q)$ non-metric gravity without gauge fixing. The main result of this study is that no further scalar mode appears more than the two standard plus and cross transverse polarizations of massless tensor gravitational radiation, typical of General Relativity. This is because the first-order pertu

Zhen-Yu Li, Guo-Liang Yu, Zhi-Gang Wang, Jian-Zhong Gu

In the framework of the relativized quark model, the calculation of spin-orbit interactions is improved by considering the contribution from the light quark cluster in a singly heavy baryon. It modifies the energy level splitting of the orbital excitation significantly and causes the emergence of fine structures for $\Sigma_{Q}$, $\Xi '_{Q}$ and $\Omega_{Q}$

Yuwen Cheng, Shu Yang

Personalized decision-making, tailored to individual characteristics, is gaining significant attention. The optimal treatment regime aims to provide the best-expected outcome in the entire population, known as the value function. One approach to determine this optimal regime is by maximizing the Augmented Inverse Probability Weighting (AIPW) estimator of the

Yicheng Huang, Wanyu Zhang, Hongpei Li, Dongdong Ge

Convex quadratic programming (QP) is an essential class of optimization problems with broad applications across various fields. Traditional QP solvers, typically based on simplex or barrier methods, face significant scalability challenges. In response to these limitations, recent research has shifted towards matrix-free first-order methods to enhance scalabi

Hasan M Jamil

The popularity of data science as a discipline and its importance in the emerging economy and industrial progress dictate that machine learning be democratized for the masses. This also means that the current practice of workforce training using machine learning tools, which requires low-level statistical and algorithmic details, is a barrier that needs to b

Michal Nauman, Mateusz Ostaszewski, Krzysztof Jankowski, Piotr Miłoś

Sample efficiency in Reinforcement Learning (RL) has traditionally been driven by algorithmic enhancements. In this work, we demonstrate that scaling can also lead to substantial improvements. We conduct a thorough investigation into the interplay of scaling model capacity and domain-specific RL enhancements. These empirical findings inform the design choice

Matteo Colangeli, Manh Hong Duong, Adrian Muntean

We consider a classical model of non-equilibrium statistical mechanics accounting for non-Markovian effects, which is referred to as the Generalized Langevin Equation in the literature. We derive reduced Markovian descriptions obtained through the neglection of inertial terms and/or heat bath variables. The adopted reduction scheme relies on the framework of

Derek Xu, Olcay Cirit, Reza Asadi, Yizhou Sun

Recent benchmarks found In-Context Learning (ICL) outperforms both deep learning and tree-based algorithms on small tabular datasets. However, on larger datasets, ICL for tabular learning cannot run without severely compromising performance, due to its quadratic space and time complexity w.r.t. dataset size. We propose MIXTUREPFN, which both extends nearest-

Minsu Park, Seyeon Choi, Chanyeol Choi, Jun-Seong Kim

Making decent multi-lingual sentence representations is critical to achieve high performances in cross-lingual downstream tasks. In this work, we propose a novel method to align multi-lingual embeddings based on the similarity of sentences measured by a pre-trained mono-lingual embedding model. Given translation sentence pairs, we train a multi-lingual model

Nigel P. Byott

Several constructions have been given for families of simple braces, but few examples are known of simple skew braces which are not braces. In this paper, we exhibit the first example of an infinite family of simple skew braces which are not braces and which do not arise from nonabelian simple groups. More precisely, we show that, for any primes $p$, $q$ suc

Xiaodong Liu

This paper presents a significant improvement on the previous conference paper known as DefSent. The prior study seeks to improve sentence embeddings of language models by projecting definition sentences into the vector space of dictionary entries. We discover that this approach is not fully explored due to the methodological limitation of using word embeddi

Jiawei Fang, Haishan Song, Chengxu Zuo, Xiaoxia Gao

Flexible sensors hold promise for human motion capture (MoCap), offering advantages such as wearability, privacy preservation, and minimal constraints on natural movement. However, existing flexible sensor-based MoCap methods rely on deep learning and necessitate large and diverse labeled datasets for training. These data typically need to be collected in Mo

Linjie Zhao

We study the weakly asymmetric simple exclusion process on the integer lattice. Under suitable constraints on the strength of the weak asymmetry of the dynamics, we prove moderate deviation principles for the fluctuation fields when the process starts from stationary measures. As an application, we obtain sample path moderate deviation principles for the occ

Yang Cao, Yangsong Lan, Feiyan Zhai, Piji Li

The extraction of essential news elements through the 5W1H framework (\textit{What}, \textit{When}, \textit{Where}, \textit{Why}, \textit{Who}, and \textit{How}) is critical for event extraction and text summarization. The advent of Large language models (LLMs) such as ChatGPT presents an opportunity to address language-related tasks through simple prompts w

Tianwei Zhang, Tomáš Peitl, Stefan Szeider

We obtain the smallest unsatisfiable formulas in subclasses of $k$-CNF (exactly $k$ distinct literals per clause) with bounded variable or literal occurrences. Smaller unsatisfiable formulas of this type translate into stronger inapproximability results for MaxSAT in the considered formula class. Our results cover subclasses of 3-CNF and 4-CNF; in all subcla

Hoai-Chau Tran, Duy M. H. Nguyen, Duy M. Nguyen, Trung-Tin Nguyen

Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an important problem in machine learning. One recent and effective strategy is to merge token representations within Transformer models, aiming to reduce computational and memory req

Laura Gambera, Umberto Guarnotta

Moving from the seminal papers by Bobkov and Tanaka \cite{BT,BT2,BT3} on the spectrum of the $(p,q)$-Laplacian, we analyze the case of the double-phase operator. We discuss the region of parameters in which existence and non-existence of positive solutions occur. The proofs are based on normalization procedures, the Nehari manifold, and truncation techniques

Xinyi Chen, Yaohui Li, Haoxing Chen

We study the problem of few-shot out-of-distribution (OOD) detection, which aims to detect OOD samples from unseen categories during inference time with only a few labeled in-domain (ID) samples. Existing methods mainly focus on training task-aware prompts for OOD detection. However, training on few-shot data may cause severe overfitting and textual prompts

Ning-An Lai, Alessandro Palmieri, Hiroyuki Takamura

In this paper, we prove a blow-up result for a generalized semilinear Euler-Poisson-Darboux equation with polynomially growing speed of propagation, when the power of the semilinear term is a shift of the Strauss' exponent for the classical semilinear wave equation. Our proof is based on a comparison argument of Kato-type for a second-order ODE with time-dep

Hong-Shuo Chen, Yao Zhu, Suya You, Azad M. Madni

We introduce GreenCOD, a green method for detecting camouflaged objects, distinct in its avoidance of backpropagation techniques. GreenCOD leverages gradient boosting and deep features extracted from pre-trained Deep Neural Networks (DNNs). Traditional camouflaged object detection (COD) approaches often rely on complex deep neural network architectures, seek

Gennady Eremin

We partition a series of natural numbers into infinite number sequences. We consider two partitioning options: (a) a forest of unary trees with recurrence formula of Mersenne numbers, and (b) a set of arithmetic progressions with difference $2^k$. Every tree starts with an even number, and any even number starts a certain tree. In the partitioning into arith

Leonardo N. Coregliano, Jarosław Swaczyna, Agnieszka Widz

The Rado Graph, sometimes also known as the (countable) Random Graph, can be generated almost surely by putting an edge between any pair of vertices with some fixed probability $p \in (0, 1)$, independently of other pairs. In this article, we study the influence of allowing different probabilities for each pair of vertices. More specifically, we characterize

Jiayan Guo, Yusen Huo, Zhilin Zhang, Tianyu Wang

Auto-bidding plays a crucial role in facilitating online advertising by automatically providing bids for advertisers. Reinforcement learning (RL) has gained popularity for auto-bidding. However, most current RL auto-bidding methods are modeled through the Markovian Decision Process (MDP), which assumes the Markovian state transition. This assumption restrict

Mohammad Alkousa, Fedor Stonyakin, Alexander Gasnikov, Asmaa Abdo

In this paper, it was proposed a new concept of the inexact higher degree $(\delta, L, q)$-model of a function that is a generalization of the inexact $(\delta, L)$-model, $(\delta, L)$-oracle and $(\delta, L)$-oracle of degree $q \in [0,2)$. Some examples were provided to illustrate the proposed new model. Adaptive inexact gradient and fast gradient methods

Robin Feldmann, Markus Reiher

In this work, we combine the many-body formulation of the internally contracted multireference coupled cluster (ic-MRCC) method with Evangelista's multireference formulation of the driven similarity renormalization group (DSRG). The DSRG method can be viewed as a unitary multireference coupled cluster theory, which renormalizes the amplitudes based on a flow

Gan Sun, Qing-Geng Yang, Da Wang, Qiang-Hua Wang

Isotope effect with a large coefficient $\alpha=-\partial \ln T_c/\partial \ln M$ is usually taken as an evidence of phonon mediated superconductors in the Bardeen-Cooper-Schrieffer (BCS) theory. However, in cuprates which are now widely believed to be strong correlation induced d-wave superconductors, $\alpha$ is experimentally observed to be quite small at

Matteo Iovino, Julian Förster, Pietro Falco, Jen Jen Chung

Behavior Trees (BTs) were first conceived in the computer games industry as a tool to model agent behavior, but they received interest also in the robotics community as an alternative policy design to Finite State Machines (FSMs). The advantages of BTs over FSMs had been highlighted in many works, but there is no thorough practical comparison of the two desi

Allen Hao Huang

Activation functions are core components of all deep learning architectures. Currently, the most popular activation functions are smooth ReLU variants like GELU and SiLU. These are self-gated activation functions where the range of the gating function is between zero and one. In this paper, we explore the viability of using arctan as a gating mechanism. A se

Zixuan Wang, Qinkai Duan, Yu-Wing Tai, Chi-Keung Tang

We introduce C3LLM (Conditioned-on-Three-Modalities Large Language Models), a novel framework combining three tasks of video-to-audio, audio-to-text, and text-to-audio together. C3LLM adapts the Large Language Model (LLM) structure as a bridge for aligning different modalities, synthesizing the given conditional information, and making multimodal generation

Ke Xiang, Da Wang, Qiang-Hua Wang

The bound states around a vortex in anisotropic superconductors is a longstanding yet important issue. In this work, we develop a variational theory on the basis of the Andreev approximation to obtain the energy levels and wave functions of the low-energy quantized bound states in superconductors with anisotropic pairing on arbitrary Fermi surface. In the ca

Mingli Zhu, Siyuan Liang, Baoyuan Wu

Deep neural networks face persistent challenges in defending against backdoor attacks, leading to an ongoing battle between attacks and defenses. While existing backdoor defense strategies have shown promising performance on reducing attack success rates, can we confidently claim that the backdoor threat has truly been eliminated from the model? To address i

Tong Ye, Yangkai Du, Tengfei Ma, Lingfei Wu

Large Language Models (LLMs) have demonstrated remarkable proficiency in generating code. However, the misuse of LLM-generated (synthetic) code has raised concerns in both educational and industrial contexts, underscoring the urgent need for synthetic code detectors. Existing methods for detecting synthetic content are primarily designed for general text and

Seungjae Lee, Suhui Jeong, Jiwon Seo

Quantum computing holds the potential to solve problems that are practically unsolvable by classical computers due to its ability to significantly reduce time complexity. We aim to harness this potential to enhance ray casting, a pivotal technique in computer graphics for simplifying the rendering of 3D objects. To perform ray casting in a quantum computer,

Sarah Nakato, Roswitha Rissner

We study the question up to which power an irreducible integer-valued polynomial that is not absolutely irreducible can factor uniquely. For example, for integer-valued polynomials over principal ideal domains with square-free denominator, already the third power has to factor non-uniquely or the element is absolutely irreducible. Recently, it has been shown

Feng Xie, Zhengming Chen, Shanshan Luo, Wang Miao

Recently, interest has grown in the use of proxy variables of unobserved confounding for inferring the causal effect in the presence of unmeasured confounders from observational data. One difficulty inhibiting the practical use is finding valid proxy variables of unobserved confounding to a target causal effect of interest. These proxy variables are typicall

Harshit Gupta, Manav Chaudhary, Tathagata Raha, Shivansh Subramanian

This paper describes our approach for SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense. The BRAINTEASER task comprises multiple-choice Question Answering designed to evaluate the models' lateral thinking capabilities. It consists of Sentence Puzzle and Word Puzzle subtasks that require models to defy default common-sense associations and e

Siddhartha K. Vemuri, Raj Sanjay Shah, Sashank Varma

How well do representations learned by ML models align with those of humans? Here, we consider concept representations learned by deep learning models and evaluate whether they show a fundamental behavioral signature of human concepts, the typicality effect. This is the finding that people judge some instances (e.g., robin) of a category (e.g., Bird) to be m

Zhuoxi Bai, Ning Wu, Fengyu Cai, Xinyi Zhu

Large Language Models (LLMs) have demonstrated remarkable performance across various domains, motivating researchers to investigate their potential use in recommendation systems. However, directly applying LLMs to recommendation tasks has proven challenging due to the significant disparity between the data used for pre-training LLMs and the specific requirem

Qihao Zhou, Haishan Ye, Luo Luo

This paper considers the distributed convex-concave minimax optimization under the second-order similarity. We propose stochastic variance-reduced optimistic gradient sliding (SVOGS) method, which takes the advantage of the finite-sum structure in the objective by involving the mini-batch client sampling and variance reduction. We prove SVOGS can achieve the

Xiao Zhang, Jeroen van den Brink, Jinbin Li

High-harmonic generation (HHG) offers an all-optical approach to discern structural symmetries through its selection rules and probe topological phases with its spectral signatures. Here we develop a universal theoretical framework -- the Jones matrix formalism -- establishing the fundamental relationship between pulse-crystal shared symmetries and HHG selec

Anna Vettoruzzo, Lorenzo Braccaioli, Joaquin Vanschoren, Marlena Nowaczyk

Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that leverages the generalization abilities of in-context learning observed in transformer architectures. Our method reframes meta

Chengyang Tian, Yuhang Chang, Yangpeng Zhang, Yang Liu

Retrosynthesis, which aims to identify viable synthetic pathways for target molecules by decomposing them into simpler precursors, is often treated as a search problem. However, its complexity arises from multi-branched tree-structured pathways rather than linear paths. Some algorithms have been successfully applied in this task, but they either overlook the

Zhaoxuan Wu, Xiaoqiang Lin, Zhongxiang Dai, Wenyang Hu

Large language models (LLMs) have shown impressive capabilities in real-world applications. The capability of in-context learning (ICL) allows us to adapt an LLM to downstream tasks by including input-label exemplars in the prompt without model fine-tuning. However, the quality of these exemplars in the prompt greatly impacts performance, highlighting the ne

Zhang Yutian, Huang Shan, Zhang Jianing, Fan Ci'en

Traditional brain-computer systems are complex and expensive, and emotion classification algorithms lack repre-sentations of the intrinsic relationships between different channels of electroencephalogram (EEG) signals. There is still room for improvement in accuracy. To lower the research barrier for EEG and harness the rich information embedded in multi-cha

Xiaopeng Ye, Chen Xu, Jun Xu, Xuyang Xie

Out of sustainable and economical considerations, two-sided recommendation platforms must satisfy the needs of both users and providers. Previous studies often show that the two sides' needs show different urgency: providers need a relatively long-term exposure demand while users want more short-term and accurate service. However, our empirical study reveals

Oleh Berezsky, Petro Liashchynskyi, Oleh Pitsun, Grygoriy Melnyk

A wide variety of biomedical image data, as well as methods for generating training images using basic deep neural networks, were analyzed. Additionally, all platforms for creating images were analyzed, considering their characteristics. The article develops a method for generating artificial biomedical images based on GAN. GAN architecture has been develope

Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Federico Fusco

We address a generalization of the bandit with knapsacks problem, where a learner aims to maximize rewards while satisfying an arbitrary set of long-term constraints. Our goal is to design best-of-both-worlds algorithms that perform optimally under both stochastic and adversarial constraints. Previous works address this problem via primal-dual methods, and r

Shihua Gong, Young-Ju Lee, Yukun Li, Yue Yu

We introduce a new concept of the locally conservative flux and investigate its relationship with the compatible discretization pioneered by Dawson, Sun and Wheeler [11]. We then demonstrate how the new concept of the locally conservative flux can play a crucial role in obtaining the L2 norm stability of the discontinuous Galerkin finite element scheme for t

Maëlic Neau, Paulo E. Santos, Anne-Gwenn Bosser, Cédric Buche

Scene Graph Generation (SGG) is a task that encodes visual relationships between objects in images as graph structures. SGG shows significant promise as a foundational component for downstream tasks, such as reasoning for embodied agents. To enable real-time applications, SGG must address the trade-off between performance and inference speed. However, curren

Mikhail Kulyabin, Gleb Sokolov, Aleksandr Galaida, Andreas Maier

The extraction and analysis of insights from medical data, primarily stored in free-text formats by healthcare workers, presents significant challenges due to its unstructured nature. Medical coding, a crucial process in healthcare, remains minimally automated due to the complexity of medical ontologies and restricted access to medical texts for training Nat

Huanbai Liu, Fanlong Zhang, Yin Tan, Lian Huang

In recent years, deep learning has led to significant advances in bearing fault diagnosis (FD). Most techniques aim to achieve greater accuracy. However, they are sensitive to noise and lack robustness, resulting in insufficient domain adaptation and anti-noise ability. The comparison of studies reveals that giving equal attention to all features does not di

Gelei Xu, Ningzhi Tang, Jun Xia, Wei Jin

Upon deployment to edge devices, it is often desirable for a model to further learn from streaming data to improve accuracy. However, extracting representative features from such data is challenging because it is typically unlabeled, non-independent and identically distributed (non-i.i.d), and is seen only once. To mitigate this issue, a common strategy is t

Shaokui Wei, Hongyuan Zha, Baoyuan Wu

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming to train a clean model even when the dataset may be potentially poisoned. Unlike most existing methods that primarily d

Jajati Keshari Sahoo, Saroja Kumar Panda, Ratikanta Behera, Predrag S. Stanimirović

This paper introduces notions of the Drazin and the core-EP inverses on tensors via M-product. We propose a few properties of the Drazin and core-EP inverses of tensors, as well as effective tensor-based algorithms for calculating these inverses. In addition, definitions of composite generalized inverses are presented in the framework of the M-product, inclu

Zeinab Kalantari, Sohrab Rahvar

The duration of more than one thousand gamma-ray bursts (GRBs) has been measured by Swift satellite. Besides the redshift distribution of GRBs, the burst duration could be another significant property of GRBs that can be analyzed. In this project, First, we find the detection rate of Swift/BAT for a cosmological model with the $ \omega CDM$ model, then by pe

Cheng-Long Zhou, Yu-Chen Peng, Yong Zhang, Hong-Liang Yi

We explore a novel approach to achieving anisotropic thermal photon tunneling, inspired by the concept of parity-time symmetry in quantum physics. Our method leverages the modulation of constitutive optical parameters, oscillating between loss and gain regimes. This modulation reveals a variety of distinct effects in thermal photon behavior and dispersion. S

Kevin William Baron

This paper represents a pilot study examining learners who are new to computer science (CS). Subjects are taught to program in one of two virtual reality (VR) applications developed by the researcher that use interactable objects representing programming concepts. The different versions are the basis for two experimental groups. One version of the app uses t

Yuanhuiyi Lyu, Xu Zheng, Dahun Kim, Lin Wang

Research on multi-modal learning dominantly aligns the modalities in a unified space at training, and only a single one is taken for prediction at inference. However, for a real machine, e.g., a robot, sensors could be added or removed at any time. Thus, it is crucial to enable the machine to tackle the mismatch and unequal-scale problems of modality combina

Xiaolun Jing, Genke Yang, Jian Chu

CLIP4Clip model transferred from the CLIP has been the de-factor standard to solve the video clip retrieval task from frame-level input, triggering the surge of CLIP4Clip-based models in the video-text retrieval domain. In this work, we rethink the inherent limitation of widely-used mean pooling operation in the frame features aggregation and investigate the

Rupak Roy, Samir Mandal, D. K. Sahu, G. C. Anupama

ASASSN-20hx, a.k.a AT2020ohl, is an ambiguous nuclear transient (ANT), which was discovered in the nearby galaxy NGC6297 by the All-Sky Automated Survey for Supernovae (ASAS-SN). We have investigated the evolution of AT2020ohl using a multi-wavelength dataset to explain the geometry of the system and the energy radiated by it between X-ray and radio waveleng

Carlo Zaccardi, Pasquale Valentini, Luigi Ippoliti, Alexandra M. Schmidt

In epidemiological studies of air pollution and public health, estimating the health impact of exposure to air pollution may be hindered by the unknown functional form of the exposure-outcome association and by unmeasured confounding factors that are linked to both exposure and outcome. These challenges are especially relevant in spatio-temporal analyses, wh

Jiangwei Weng, Zhiqiang Yan, Ying Tai, Jianjun Qian

Recent advances in low light image enhancement have been dominated by Retinex-based learning framework, leveraging convolutional neural networks (CNNs) and Transformers. However, the vanilla Retinex theory primarily addresses global illumination degradation and neglects local issues such as noise and blur in dark conditions. Moreover, CNNs and Transformers s

Connor Mooney, Zhongjian Wang, Jack Xin, Yifeng Yu

We establish global well-posedness and convergence of the score-based generative models (SGM) under minimal general assumptions of initial data for score estimation. For the smooth case, we start from a Lipschitz bound of the score function with optimal time length. The optimality is validated by an example whose Lipschitz constant of scores is bounded at in

Andrzej Lingas

We present a protocol for the Boolean matrix product of two $n\times b$ Boolean matrices on the congested clique designed for the situation when the rows of the first matrix or the columns of the second matrix are highly clustered in the space $\{0,1\}^n.$ With high probability (w.h.p), it uses $\tilde{O}\left(\sqrt {\frac M n+1}\right)$ rounds on the conges

Hongye Zeng, Ke Zou, Zhihao Chen, Rui Zheng

Source-Free Unsupervised Domain Adaptation (SFUDA) has recently become a focus in the medical image domain adaptation, as it only utilizes the source model and does not require annotated target data. However, current SFUDA approaches cannot tackle the complex segmentation task across different MRI sequences, such as the vestibular schwannoma segmentation. To

Sanaa Agarwal, A. Piñeiro Orioli, J. K. Thompson, A. M. Rey

We investigate the driven-dissipative dynamics of 1D and 2D arrays of multilevel atoms interacting via dipole-dipole interactions and trapped at subwavelength scales. Here we show that in the weakly driven low excitation regime, multilevel atoms, in contrast to two-level atoms, can become strongly entangled. The entanglement manifests as the growth of collec

Lorenzo Di Meco, Mirko Degli Esposti, Federico Bellisardi, Armando Bazzani

The congestion formation on a urban road network is one of the key issue for the development of a sustainable mobility in the future smart cities. In this work we propose a reductionist approach studying the stationary states of a simple transport model using of a random process on a graph, where each node represents a location and the weight links give the

Ziyan Wang, Mohamed Ragab, Wenmian Yang, Min Wu

Unsupervised domain adaptation (UDA) has achieved remarkable success in fault diagnosis, bringing significant benefits to diverse industrial applications. While most UDA methods focus on cross-working condition scenarios where the source and target domains are notably similar, real-world applications often grapple with severe domain shifts. We coin the term

Huizhou Chen, Jiangyi Wang, Yuxin Li, Na Zhao

3D environment recognition is essential for autonomous driving systems, as autonomous vehicles require a comprehensive understanding of surrounding scenes. Recently, the predominant approach to define this real-life problem is through 3D occupancy prediction. It attempts to predict the occupancy states and semantic labels for all voxels in 3D space, which en

Zizhao Hu, Mohammad Rostami

The Transformer architecture has dominated machine learning in a wide range of tasks. The specific characteristic of this architecture is an expensive scaled dot-product attention mechanism that models the inter-token interactions, which is known to be the reason behind its success. However, such a mechanism does not have a direct parallel to the human brain

Tasnim Assali, Zayneb Trabelsi Ayoub, Sofiane Ouni

Big Data works perfectly along with Deep learning to extract knowledge from a huge amount of data. However, this processing could take a lot of training time. Genomics is a Big Data science with high dimensionality. It relies on deep learning to solve complicated problems in certain diseases like cancer by using different DNA information such as the transcri

Kunye Shen, Xiaofei Zhou, Zhi Liu

The automated surface defect detection is a fundamental task in industrial production, and the existing saliencybased works overcome the challenging scenes and give promising detection results. However, the cutting-edge efforts often suffer from large parameter size, heavy computational cost, and slow inference speed, which heavily limits the practical appli

Wenjing Chen, Zexi Wang

In this paper, we consider the following critical polyharmonic equation \begin{align*}%\label{abs} ( -\Delta)^m u+V(|y'|,y'')u=u^{m^*-1},\quad u>0, \quad y=(y',y'')\in \mathbb{R}^3\times \mathbb{R}^{N-3}, \end{align*} where $m^*=\frac{2N}{N-2m}$, $N>4m+1$, $m\in \mathbb{N}^+$, and $V(|y'|,y'')$ is a bounded nonnegative function in $\mathbb{R}^+\times \mathbb

Zhaochen Liu, Limeng Qiao, Xiangxiang Chu, Tingting Jiang

Aiming to predict the complete shapes of partially occluded objects, amodal segmentation is an important step towards visual intelligence. With crucial significance, practical prior knowledge derives from sufficient training, while limited amodal annotations pose challenges to achieve better performance. To tackle this problem, utilizing the mighty priors ac

Ying Zhang, Xiaofeng Li, Zhaoyang Liu, Haipeng Zhang

The life trajectories of notable people have been studied to pinpoint the times and places of significant events such as birth, death, education, marriage, competition, work, speeches, scientific discoveries, artistic achievements, and battles. Understanding how these individuals interact with others provides valuable insights for broader research into human

Qikai Wang, Rundong He, Yongshun Gong, Chunxiao Ren

Semi-supervised learning can significantly boost model performance by leveraging unlabeled data, particularly when labeled data is scarce. However, real-world unlabeled data often contain unseen-class samples, which can hinder the classification of seen classes. To address this issue, mainstream safe SSL methods suggest detecting and discarding unseen-class

Amirmasoud Geevechi

In this project, we study the hyperbolic Abelian Higgs model in dimension $3$ at the critical coupling. The stationary solutions to the two-dimensional version of this equation have been found by Jaffe and Taubes, the so called $N$-vortex configurations. One can consider the space of all $N$-vortex configurations $M_N$ as a smooth Riemannian manifold. Stuart

Myong Chol Jung, Joanna Dipnall, Belinda Gabbe, He Zhao

Prompt learning has emerged as an efficient and effective method for fine-tuning vision-language models such as CLIP. While many studies have explored generalisation abilities of these models in few-shot classification tasks and a few studies have addressed far out-of-distribution (OOD) of the models, their potential for addressing near OOD detection remains

Xicheng Lou, Xinwei Li, Hongying Meng, Jun Hu

Motor imagery electroencephalogram (EEG)-based brain-computer interfaces (BCIs) offer significant advantages for individuals with restricted limb mobility. However, challenges such as low signal-to-noise ratio and limited spatial resolution impede accurate feature extraction from EEG signals, thereby affecting the classification accuracy of different actions

Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai

Recently, integrating external tools with Large Language Models (LLMs) has gained significant attention as an effective strategy to mitigate the limitations inherent in their pre-training data. However, real-world systems often incorporate a wide array of tools, making it impractical to input all tools into LLMs due to length limitations and latency constrai

Jonathan So

The normal-inverse-Wishart (NIW) distribution is commonly used as a prior distribution for the mean and covariance parameters of a multivariate normal distribution. The family of NIW distributions is also a minimal exponential family. In this short note we describe a convergent procedure for converting from mean parameters to natural parameters in the NIW fa

Feng Jin, Subhaskar Mandal, Zhenhan Zhang, Jinqi Wu

Topological exciton-polaritons are a burgeoning class of topological photonic systems distinguished by their hybrid nature as part-light, part-matter quasiparticles. Their further control over novel valley degree of freedom (DOF) has offered considerable potential for developing active topological optical devices towards information processing. However, the

Yunbo Li, Jiaping Gui, Yue Wu

Federated learning is highly valued due to its high-performance computing in distributed environments while safeguarding data privacy. To address resource heterogeneity, researchers have proposed a semi-asynchronous federated learning (SAFL) architecture. However, the performance gap between different aggregation targets in SAFL remain unexplored. In this pa

Junjie Gao, Chongjian Wang, Zhongjun Ding, Shuangmin Chen

In the realm of point cloud registration, the most prevalent pose evaluation approaches are statistics-based, identifying the optimal transformation by maximizing the number of consistent correspondences. However, registration recall decreases significantly when point clouds exhibit a low overlap rate, despite efforts in designing feature descriptors and est

Lachlan Scott, Tangyou Liu, Liao Wu

Surgical robotic systems equipped with microscale, high-dexterity manipulators have shown promising results in minimally invasive surgery (MIS). One barrier to the widespread adoption of such systems is the prohibitive cost of research and development efforts using current state-of-the-art equipment. To address this challenge, this paper proposes a low-cost

Ruichu Cai, Zhifang Jiang, Zijian Li, Weilin Chen

Existing methods for multi-modal time series representation learning aim to disentangle the modality-shared and modality-specific latent variables. Although achieving notable performances on downstream tasks, they usually assume an orthogonal latent space. However, the modality-specific and modality-shared latent variables might be dependent on real-world sc

Hyekyoung Hwang, Jitae Shin

Deep Learning (DL) has made remarkable achievements in computer vision and adopted in safety critical domains such as medical imaging or autonomous drive. Thus, it is necessary to understand the uncertainty of the model to effectively reduce accidents and losses due to misjudgment of the Deep Neural Networks (DNN). This can start by efficiently selecting dat

Yuchen He, Jinghua Wang, Bertrand Kibler, Amin Chabchoub

The modulation instability (MI) is responsible for the disintegration of a regular nonlinear wave train and can lead to strong localizations in a from of rogue waves. This mechanism has been studied in a variety of nonlinear dispersive media, such as hydrodynamics, optics, plasma, mechanical systems, electric transmission lines, and Bose-Einstein condensates

Ningzhi Tang, Meng Chen, Zheng Ning, Aakash Bansal

The increasing use of large language model (LLM)-powered code generation tools, such as GitHub Copilot, is transforming software engineering practices. This paper investigates how developers validate and repair code generated by Copilot and examines the impact of code provenance awareness during these processes. We conducted a lab study with 28 participants,

Yasser Abduallah, Jason T. L. Wang

Solar flares are explosions on the Sun. They happen when energy stored in magnetic fields around solar active regions (ARs) is suddenly released. In this paper, we present a transformer-based framework, named SolarFlareNet, for predicting whether an AR would produce a gamma-class flare within the next 24 to 72 hours. We consider three gamma classes, namely t

Xinyue Huang, Zhigang Song, Yuchen Gao, Pingfan Gu

We present a comprehensive investigation of optical properties in MoSe$_2$/CrSBr heterostructures, unveiling the presence of localized excitons represented by a new emission feature, X$^*$. We demonstrate through temperature- and power-dependent photoluminescence spectroscopy that X$^*$ originates from excitons confined by intrinsic defects within the CrSBr

Xiaowu Liu, Yun Wang, Kan Yu, Dianxia Chen

The task offloading technology plays a vital role in the Internet of Vehicles (IoV), by satisfying the diversified demands of the vehicles, such as the energy consumption and processing latency of the computing task. Different from the previous works, on the one hand, they ignored the wireless interference of communications among vehicle-to-vehicle (V2V), as

Yudan Wang, Peiyao Xiao, Hao Ban, Kaiyi Ji

Multi-task reinforcement learning (MTRL) has shown great promise in many real-world applications. Existing MTRL algorithms often aim to learn a policy that optimizes individual objective functions simultaneously with a given prior preference (or weights) on different tasks. However, these methods often suffer from the issue of \textit{gradient conflict} such

Angran Li, Stephen Becker, Alireza Doostan

Traditional low-rank approximation is a powerful tool to compress the huge data matrices that arise in simulations of partial differential equations (PDE), but suffers from high computational cost and requires several passes over the PDE data. The compressed data may also lack interpretability thus making it difficult to identify feature patterns from the or

Zekun Cai, Guangji Bai, Renhe Jiang, Xuan Song

Temporal Domain Generalization (TDG) addresses the challenge of training predictive models under temporally varying data distributions. Traditional TDG approaches typically focus on domain data collected at fixed, discrete time intervals, which limits their capability to capture the inherent dynamics within continuous-evolving and irregularly-observed tempor

Huafei Di, Liang Li, Xiaoming Peng, Quan Wang

Considered herein is the global existence of weak, strong solutions and Rayleigh-Taylor (RT) instability for 2D semi-dissipative Boussinesq equations in an infinite strip domain $\Omega_{\infty}$ subject to Navier boundary conditions with non-positive slip coefficients. We first prove the global existence of weak and strong solutions on bounded domain $\Omeg