May 2024 arXiv papers — page 48

Sunhao Dai, Changle Qu, Sirui Chen, Xiao Zhang

In real-world recommender systems, such as in the music domain, repeat consumption is a common phenomenon where users frequently listen to a small set of preferred songs or artists repeatedly. The key point of modeling repeat consumption is capturing the temporal patterns between a user's repeated consumption of the items. Existing studies often rely on heur

Zhenkun Li, Shunyu Wan

We show that in $(S^3,\xi_{std})$ if $K$ is a non-trivial knot that realizes the three-dimensional Thurston-Bennequin bound (i.e. $K$ has a Legendrian representative $\Lambda$ with $tb(\Lambda)-rot(\Lambda)=2g(K)-1$), then $K$ has a Legendrian representative $L$ with $tb=0$. Moreover, this result can be easily generalized to contact manifolds that uniquely r

Moritz Cygorek, Brendon W. Lovett, Jonathan Keeling, Erik M. Gauger

The algorithm "automated compression of environments" (ACE) [Nat. Phys. 18, 662 (2022)] provides a versatile way of simulating an extremely broad class of open quantum systems. This is achieved by encapsulating the influence of the environment, which is determined by the interaction Hamiltonian(s) and initial states, into compact process tensor matrix produc

Sunhao Dai, Weihao Liu, Yuqi Zhou, Liang Pang

The proliferation of Large Language Models (LLMs) has led to an influx of AI-generated content (AIGC) on the internet, transforming the corpus of Information Retrieval (IR) systems from solely human-written to a coexistence with LLM-generated content. The impact of this surge in AIGC on IR systems remains an open question, with the primary challenge being th

Kuo-Han Hung, Pang-Chi Lo, Jia-Fong Yeh, Han-Yuan Hsu

We study reward models for long-horizon manipulation tasks by learning from action-free videos and language instructions, which we term the visual-instruction correlation (VIC) problem. Recent advancements in cross-modality modeling have highlighted the potential of reward modeling through visual and language correlations. However, existing VIC methods face

Erik Sandström, Keisuke Tateno, Michael Oechsle, Michael Niemeyer

3D Gaussian Splatting has emerged as a powerful representation of geometry and appearance for RGB-only dense Simultaneous Localization and Mapping (SLAM), as it provides a compact dense map representation while enabling efficient and high-quality map rendering. However, existing methods show significantly worse reconstruction quality than competing methods u

Yehia Abdelsalam, Sankaranarayanan Subramanian, Sebastian Engell

This work proposes a new a framework for determining robust periodic invariant sets and their associated control laws for constrained uncertain linear systems. Necessary and sufficient conditions for stabilizability by periodic controllers are stated and proven using finite step Lyapunov functions for the unconstrained case. We then introduce a scenario tree

Yang Cao, Wei Zhang

Knowledge tracing (KT) enhances student learning by leveraging past performance to predict future performance. Current research utilizes models based on attention mechanisms and recurrent neural network structures to capture long-term dependencies and correlations between exercises, aiming to improve model accuracy. Due to the growing amount of data in smart

Isaac Reid, Stratis Markou, Krzysztof Choromanski, Richard E. Turner

Random features (RFs) are a popular technique to scale up kernel methods in machine learning, replacing exact kernel evaluations with stochastic Monte Carlo estimates. They underpin models as diverse as efficient transformers (by approximating attention) to sparse spectrum Gaussian processes (by approximating the covariance function). Efficiency can be furth

Kelvin Onggadinata, Pawel Kurzynski, Dagomir Kaszlikowski

We show that a maximal violation of the Bell-CHSH inequality for two entangled qubits, i.e., Bell non-locality, is a direct consequence of a local bit erasure by means of a quasi-stochastic process, i.e., a stochastic process in which some transition probabilities are negative.

Nicolas Aragon, Alain Couvreur, Victor Dyseryn, Philippe Gaborit

The McEliece scheme is a generic frame which allows to use any error correcting code of which there exists an efficient decoding algorithm to design an encryption scheme by hiding the generator matrix code. Similarly, the Niederreiter frame is the dual version of the McEliece scheme, and achieves smaller ciphertexts. We propose a generalization of the McElie

Paramita Kundu Maji, Soubhik Acharya, Priti Paul, Sanjay Chakraborty

This paper aims to develop a new deep learning-inspired gaming approach for early detection of dementia. This research integrates a robust convolutional neural network (CNN)-based model for early dementia detection using health metrics data as well as facial image data through a cognitive assessment-based gaming application. We have collected 1000 data sampl

Wenqi Ouyang, Yi Dong, Lei Yang, Jianlou Si

The remarkable generative capabilities of diffusion models have motivated extensive research in both image and video editing. Compared to video editing which faces additional challenges in the time dimension, image editing has witnessed the development of more diverse, high-quality approaches and more capable software like Photoshop. In light of this gap, we

Iasson Karafyllis, Filippos Vokos, Miroslav Krstic

This paper presents a complete inverse optimality study for a linearized tank-liquid system where the liquid is described by the viscous Saint-Venant model with surface tension and possible wall friction. We define an appropriate weak solution notion for which we establish existence/uniqueness results with inputs that do not necessarily satisfy any compatibi

Tianyun Yang, Juan Cao, Chang Xu

Despite the impressive capabilities of generating images, text-to-image diffusion models are susceptible to producing undesirable outputs such as NSFW content and copyrighted artworks. To address this issue, recent studies have focused on fine-tuning model parameters to erase problematic concepts. However, existing methods exhibit a major flaw in robustness,

Zhengliang Shi, Shen Gao, Lingyong Yan, Yue Feng

Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extend their utility, enabling them to solve practical tasks. Previous methods manually parse tool documentation and create in-context demonstrations, transforming tools into structured formats for LLMs to use in their step-by-step reasoning. However, this manu

Guangzhi Sun, Xiao Zhan, Jose Such

The incorporation of Large Language Models (LLMs) such as the GPT series into diverse sectors including healthcare, education, and finance marks a significant evolution in the field of artificial intelligence (AI). The increasing demand for personalised applications motivated the design of conversational agents (CAs) to possess distinct personas. This paper

A. Mikhailov, T. Skrypnyk

In this letter, we revisit the quantisation problem for a fundamental model of classical mechanics - the Zhukovsky-Volterra top. We have discovered a four-parametric pencil of compatible Poisson brackets, comprising two quadratic and two linear Poisson brackets. Using the quantisation ideal method, we have identified two distinct quantisations of the Zhukovs

Pitágoras Pinheiro de Carvalho, Juan Bautista Límaco Ferrel, Enrique Fernandez-Cara

This paper deals with the control of a kind of turbulent flows. We consider a simplified k-e model with distributed controls, locally supported in space. We proof that the system is partially locally null-controllable, in the sense that the velocity field can be driven exactly to zero if the initial state is small enough. The proof relies on an argument wher

V. Hnizdo, G. Vaman

There is a simple formula for the gauge function of the transformation from the Lorenz gauge to the Coulomb gauge, valid under a condition that is satisfied by some charge densities employed in the literature. An equation for the gauge function of this transformation that is alternative but equivalent to a formula of Jackson is derived also.

Wen-Han Zhou, David Vokrouhlicky, Masanori Kanamaru, Harrison Agrusa

We explore the Yarkovsky effect on small binary asteroids. While significant attention has been given to the binary YORP effect, the Yarkovsky effect is often overlooked. We develop an analytical model for the binary Yarkovsky effect, considering both the Yarkovsky-Schach and planetary Yarkovsky components, and verify it against thermophysical numerical simu

Sebastian Loeschcke, Mads Toftrup, Michael J. Kastoryano, Serge Belongie

Despite advances using low-rank adapters and quantization, pretraining of large models on consumer hardware has not been possible without model sharding, offloading during training, or per-layer gradient updates. To address these limitations, we propose Low-Rank Adapters for Quantized Training (LoQT), a method for efficiently training quantized models. LoQT

Galatia Cleanthous, Athanasios G. Georgiadis, Oleg V. Lepski

This is the second part of the research project initiated in Cleanthous et al (2024). We deal with the problem of the adaptive estimation of the $\mathbb{L}_2$-norm of a probability density on $\mathbb{R}^d$, $d\geq 1$, from independent observations. The unknown density is assumed to be uniformly bounded by unknown constant and to belong to the union of ball

Jonas Oppenlaender

Science is a complex system comprised of many scientists who individually make decisions that, due to the size and nature of the academic system, largely do not affect the system as a whole. However, certain decisions at the meso-level of research communities, such as the Human-Computer Interaction (HCI) community, may result in deep and long-lasting behavio

Alexander Bernal, Paweł Caban, Jakub Rembieliński

We discuss entanglement and the violation of the CGLMP inequality in a system of two vector bosons produced in the decay of a spin-0 particle. We assume the most general CPT conserving, Lorentz-invariant coupling of the spin-0 particle with the daughter bosons. We compute the most general two-boson density matrix obtained by averaging over kinematical config

Polina Lakrisenko, Dilan Pathirana, Daniel Weindl, Jan Hasenauer

Estimating parameters of dynamic models from experimental data is a challenging, and often computationally-demanding task. It requires a large number of model simulations and objective function gradient computations, if gradient-based optimization is used. The gradient depends on derivatives of the state variables with respect to parameters, also called stat

Avior Almoalem, Roni Gofman, Yuval Nitzav, Ilay Mangel

4Hb-TaS$_2$ is a superconductor that exhibits unique characteristics such as time-reversal symmetry breaking, hidden magnetic memory, and topological edge modes. It is a naturally occurring heterostructure comprising of alternating layers of 1H-TaS$_2$ and 1T-TaS$_2$. The former is a well-known superconductor, while the latter is a correlated insulator with

Wuhao Wang, Zhiyong Chen, Lepeng Zhang

Temporal difference (TD) learning is a fundamental technique in reinforcement learning that updates value estimates for states or state-action pairs using a TD target. This target represents an improved estimate of the true value by incorporating both immediate rewards and the estimated value of subsequent states. Traditionally, TD learning relies on the val

Shakti Singh, Akhilesh Kumar Mishra

Ultrashort optical pulses with orbital angular momentum (OAM) owing to their applications in classical as well as quantum domains attract a lot of research attention. The evolution of their spatio-temporal dynamics is of particular interest. In the present work, the spatio-temporal evolution of ultrashort Laguerre Gauss (LG) vortex with power exponential spe

Meinolf Geck, Donna M. Testerman

Roger Carter (1934--2022) was a very well known mathematician working in algebra, representation theory and Lie theory. He spent most of his mathematical career in Warwick. Roger was a great communicator of mathematics: the clarity, precision and enthusiasm of his lectures delivered in his beautiful handwriting were hallmark features recalled by numerous stu

Tal Amir, Nadav Dym

We present the Fourier Sliced-Wasserstein (FSW) embedding - a novel method to embed multisets and measures over R^d into Euclidean space. Our proposed embedding approximately preserves the sliced Wasserstein distance on distributions, thereby yielding geometrically meaningful representations that better capture the structure of the input. Moreover, it is inj

Ziran Xie, Zhiyu Tian, Shihai Sun

Reference frame independent quantum key distribution (RFI-QKD) has gained widespread attention due to the unique advantage for practical application, as it circumvents the need for active reference frame alignment within the system. However, in comparison to the standard BB84 protocol, the original 6-state RFI protocol requires a greater number of quantum st

Soumava Paul, Christopher Wewer, Bernt Schiele, Jan Eric Lenssen

We aim to tackle sparse-view reconstruction of a 360 3D scene using priors from latent diffusion models (LDM). The sparse-view setting is ill-posed and underconstrained, especially for scenes where the camera rotates 360 degrees around a point, as no visual information is available beyond some frontal views focused on the central object(s) of interest. In th

Kun Huang, Xiao Ma, Yuhan Zhang, Na Su

Optical coherence tomography (OCT) image analysis plays an important role in the field of ophthalmology. Current successful analysis models rely on available large datasets, which can be challenging to be obtained for certain tasks. The use of deep generative models to create realistic data emerges as a promising approach. However, due to limitations in hard

Galatia Cleanthous, Athanasios G. Georgiadis, Oleg V. Lepski

We deal with the problem of the adaptive estimation of the $\mathbb{L}_2$-norm of a probability density on $\mathbb{R}^d$, $d\geq 1$, from independent observations. The unknown density is assumed to be uniformly bounded and to belong to the union of balls in the isotropic/anisotropic Nikolskii's spaces. We will show that the optimally adaptive estimators ove

Abdolnaser Bahlekeh, Fahimeh Sadat Fotouhi, Mohammad Amin Hamlehdari, Shokrollah Salarian

Let (S; n) be a commutative noetherian local ring and let w in n be non-zero divisor. This paper is concerned with the two categories of monomorphisms between finitely generated (Gorenstein) projective S-modules, such that their cokernels are annihilated by w. It is shown that these categories, which will be denoted by Mon(w;P) and Mon(w; G), are both Froben

Pazit Haim-Kislev, Yaron Ostrover

We present a counterexample to Viterbo's volume-capacity conjecture. This implies, in particular, that in contrast with a well-known conjecture, symplectic capacities do not coincide on the class of convex domains in the classical phase space.

Denis Bodrov

We present here the major results obtained in $\tau$ physics by the Belle and Belle II experiments. For the Belle II experiment, we also discuss prospects for improved measurements of the $\tau$ lepton properties, new results in Michel parameters determination, and searches for $CP$ and lepton flavor violation in $\tau$ decays.

Hongfei Wu, Lijun Wu, Guoqing Liu, Zhirong Liu

In this paper, we develop SE3Set, an SE(3) equivariant hypergraph neural network architecture tailored for advanced molecular representation learning. Hypergraphs are not merely an extension of traditional graphs; they are pivotal for modeling high-order relationships, a capability that conventional equivariant graph-based methods lack due to their inherent

Cong Zhang, Derrick Goh Xin Deik, Dexun Li, Hao Zhang

The rapid advancement of neural language models has sparked a new surge of intelligent agent research. Unlike traditional agents, large language model-based agents (LLM agents) have emerged as a promising paradigm for achieving artificial general intelligence (AGI) due to their superior reasoning and generalization capabilities. Effective planning is crucial

Dominykas Gudavicius, Lukas Kontenis, Wolfgang Langbein

We demonstrate coherent anti-Stokes Raman scattering (CARS) microscopy with 1089 foci, enabled by a high repetition rate amplified oscillator and optical parametric amplifier. We employ a camera as multichannel detector to acquire and separate the signals from the foci, rather than using the camera image itself. This allows to retain the insensitivity of the

Gabriele Dominici, Pietro Barbiero, Francesco Giannini, Martin Gjoreski

Interpretable deep learning aims at developing neural architectures whose decision-making processes could be understood by their users. Among these techniqes, Concept Bottleneck Models enhance the interpretability of neural networks by integrating a layer of human-understandable concepts. These models, however, necessitate training a new model from the begin

Gabriele Dominici, Pietro Barbiero, Mateo Espinosa Zarlenga, Alberto Termine

Causal opacity denotes the difficulty in understanding the "hidden" causal structure underlying the decisions of deep neural network (DNN) models. This leads to the inability to rely on and verify state-of-the-art DNN-based systems, especially in high-stakes scenarios. For this reason, circumventing causal opacity in DNNs represents a key open challenge at t

Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan

Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and, as a result, falls short in handling networked documents which are very popular in many applications such as citation graphs, social media, and knowledge graphs. To overcome this limitation, we introduce Graph Retrieval-Augmented Generation (GRAG), which tackles

G. Costa, T. Dumont, A. Lançon, A. Palacios

A common property of globular clusters (GC) is to host multiple populations characterized by peculiar chemical abundances. Recent photometric studies suggest that the He content could vary between the populations of a GC by up to $\Delta$He $\sim$ 0.13, in mass fraction. The initial He content impacts the evolution of low-mass stars by ultimately modifying t

Itamar Zimerman, Ameen Ali, Lior Wolf

Recent advances in efficient sequence modeling have led to attention-free layers, such as Mamba, RWKV, and various gated RNNs, all featuring sub-quadratic complexity in sequence length and excellent scaling properties, enabling the construction of a new type of foundation models. In this paper, we present a unified view of these models, formulating such laye

Masahito Uwamichi, Simon K. Schnyder, Tetsuya J. Kobayashi, Satoshi Sawai

Analyzing the motion of multiple biological agents, be it cells or individual animals, is pivotal for the understanding of complex collective behaviors. With the advent of advanced microscopy, detailed images of complex tissue formations involving multiple cell types have become more accessible in recent years. However, deciphering the underlying rules that

Xinyue Pei, Xingwei Wang, Yingyang Chen, Tingrui Pei

In this paper, we investigate the performance of ambient backscatter communication non-orthogonal multiple access (AmBC-NOMA)-assisted short packet communication for high-mobility vehicle-to-everything transmissions. In the proposed system, a roadside unit (RSU) transmits a superimposed signal to a typical NOMA user pair. Simultaneously, the backscatter devi

Linhao Zhong, Yan Hong, Wentao Chen, Binglin Zhou

Text-to-image generation models have seen considerable advancement, catering to the increasing interest in personalized image creation. Current customization techniques often necessitate users to provide multiple images (typically 3-5) for each customized object, along with the classification of these objects and descriptive textual prompts for scenes. This

Sushil Chhetri, Krishna Kiran Vamsi Dasu, K N Kavya, Sharath B N

Tuberculosis remains a significant global health challenge, with millions of new cases reported annually. Recent studies suggest that expanding the accessibility of TB intervention programs can lead to a substantial decrease in both TB incidence and prevalence. This paper initiates by examining a deterministic mathematical model for TB transmission, aiming t

Waleed Esmail, A. Hammad, Adil Jueid, Stefano Moretti

The precise measurement of the top-Higgs coupling is crucial in particle physics, offering insights into potential new physics Beyond the Standard Model (BSM) carrying {\cal CP} Violation (CPV) effects. In this paper, we explore the {\cal CP} properties of a Higgs boson coupling with a top quark pair, focusing on events where the Higgs state decays into a pa

Menghao Waiyan William Zhu, Ercan Engin Kuruoğlu

We formulate sequential maximum a posteriori inference as a recursion of loss functions and reduce the problem of continual learning to approximating the previous loss function. We then propose two coreset-free methods: autodiff quadratic consolidation, which uses an accurate and full quadratic approximation, and neural consolidation, which uses a neural net

Jerzy Lukierski, Anna Pachoł

Recently it was shown that by using two different realizations of $\hat{o}(1,4)$ Lie algebra one can describe one-parameter standard Snyder model and two-parameter $\kappa$-deformed Snyder model. In this paper, by using the generalized Born duality and Jacobi identities we obtain from the $\kappa$-deformed Snyder model the doubly $\kappa$-deformed Yang model

Heng Yim Nicole Oo, Min Hun Lee, Jeong Hoon Lim

Algorithmic detection of facial palsy offers the potential to improve current practices, which usually involve labor-intensive and subjective assessment by clinicians. In this paper, we present a multimodal fusion-based deep learning model that utilizes unstructured data (i.e. an image frame with facial line segments) and structured data (i.e. features of fa

Michael T. C. Chiu, Sachit Mahajan, Mark C. Ballandies, Uroš V. Kalabić

There is always demand for integrating data into microeconomic decision making. Participatory sensing deals with how real-world data may be extracted with stakeholder participation and resolves a problem of Big Data, which is concerned with monetizing data extracted from individuals without their participation. We present how Decentralized Physical Infrastru

Hao Hao, Xiaoqun Zhang, Bingdong Li, Aimin Zhou

Surrogate-assisted Evolutionary Algorithm (SAEA) is an essential method for solving expensive expensive problems. Utilizing surrogate models to substitute the optimization function can significantly reduce reliance on the function evaluations during the search process, thereby lowering the optimization costs. The construction of surrogate models is a critica

Shuangpeng Han, Ziyu Wang, Mengmi Zhang

Biological motion perception (BMP) refers to humans' ability to perceive and recognize the actions of living beings solely from their motion patterns, sometimes as minimal as those depicted on point-light displays. While humans excel at these tasks without any prior training, current AI models struggle with poor generalization performance. To close this rese

Pedro Miranda Afonso, Dimitris Rizopoulos, Anushka K. Palipana, Emrah Gecili

Joint models for longitudinal and survival data have become a popular framework for studying the association between repeatedly measured biomarkers and clinical events. Nevertheless, addressing complex survival data structures, especially handling both recurrent and competing event times within a single model, remains a challenge. This causes important infor

Shuo Lin, Jin-Yu Hu, Hao-Jie Xu, Shi Pu

We have investigated the $\rho^{0}$ meson photoproduction in ultraperipheral isobaric collisions between $_{44}^{96}\textrm{Ru}+_{44}^{96}\textrm{Ru}$ and $_{40}^{96}\textrm{Zr}+_{40}^{96}\textrm{Zr}$ at $\sqrt{s_{NN}}=200$ GeV, employing the dipole model with the equivalent photon approximation. By implementing the Woods-Saxon distribution to represent the

Simon McGregor, timorl, Nathaniel Virgo

This article presents a formalism inspired by Dennett's notion of the intentional stance. Whereas Dennett's treatment of these concepts is informal, we aim to provide a more formal analogue. We introduce a framework based on stochastic processes with inputs and outputs, in which we can talk precisely about *interpreting* systems as having *normative-epistemi

Peiwen Li, Xin Wang, Zeyang Zhang, Yijian Qin

Graph NAS has emerged as a promising approach for autonomously designing GNN architectures by leveraging the correlations between graphs and architectures. Existing methods fail to generalize under distribution shifts that are ubiquitous in real-world graph scenarios, mainly because the graph-architecture correlations they exploit might be spurious and varyi

Yong Li, Han Gao

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories on the poisoned samples. Backdoor attacks are full of threats. Poisoned samples are becoming more and more similar to co

Tyler Han, Sidharth Talia, Rohan Panicker, Preet Shah

Current developments in autonomous off-road driving are steadily increasing performance through higher speeds and more challenging, unstructured environments. However, this operating regime subjects the vehicle to larger inertial effects, where consideration of higher-order states is necessary to avoid failures such as rollovers or excessive impact forces. A

Rongyu Zhang, Aosong Cheng, Yulin Luo, Gaole Dai

Continual Test-Time Adaptation (CTTA), which aims to adapt the pre-trained model to ever-evolving target domains, emerges as an important task for vision models. As current vision models appear to be heavily biased towards texture, continuously adapting the model from one domain distribution to another can result in serious catastrophic forgetting. Drawing i

Congbo Bi, Lipeng Zhu, Di Liu, Chao Lu

The high penetration of renewable energy and power electronic equipment bring significant challenges to the efficient construction of adaptive emergency control strategies against various presumed contingencies in today's power systems. Traditional model-based emergency control methods have difficulty in adapt well to various complicated operating conditions

Kun Xu, Y. P. Jing, Hongyu Gao, Xiaolin Luo

Magnification serves as an independent and complementary gravitational lensing measurement to shear. We develop a novel method to achieve an accurate and robust magnification measurement around BOSS CMASS galaxies across physical scales of $0.016h^{-1}{\rm Mpc} < r_{\rm p} < 10h^{-1}{\rm Mpc}$. We first measure the excess total flux density $\delta M$ of the

Jinho Choi

Low Earth orbit (LEO) satellites play a crucial role in providing global connectivity for non-terrestrial networks (NTNs) and supporting various Internet-of-Remote-Things (IoRT) applications. Each LEO satellite functions as a relay node in the sky, employing store-and-forward transmission strategies that necessitate the use of buffers. However, due to the fi

Abderrahman Skiredj, Ferdaous Azhari, Ismail Berrada, Saad Ezzini

Navigating the complexities of language diversity is a central challenge in developing robust natural language processing systems, especially in specialized domains like banking. The Moroccan Dialect (Darija) serves as the common language that blends cultural complexities, historical impacts, and regional differences. The complexities of Darija present a spe

De-Chang Dai, Changbo Fu

While two highly intensive laser beams collide, they create a region where the refractive index varies so quickly that photons are created. The variance of the refractive index is analog to the universe scale factor variance. Therefore, this laser system can be an analog to the expansion of the universe. We find that several hundreds of photons can be create

Cedric Loretan, Andreas Müller, Marine Delaval, Sebastien Roch

Understanding size and scale (USS) and order-of-magnitude reasoning (OMR) are critical for scientific literacy. This study examines an educational approach to enhance these skills in high school science, considering the cognitive prerequisites and challenges. It explores worked examples (WEs) as an effective method to teach USS and OMR, comparing their impac

Haoru Tan, Chuang Wang, Xu-Yao Zhang, Cheng-Lin Liu

Graph matching is a fundamental tool in computer vision and pattern recognition. In this paper, we introduce an algorithm for graph matching based on the proximal operator, referred to as differentiable proximal graph matching (DPGM). Specifically, we relax and decompose the quadratic assignment problem for the graph matching into a sequence of convex optimi

Chathura Wimalasiri, Prasan Kumar Sahoo

In response to the increasing demand for efficient and non-invasive methods to estimate food weight, this paper presents a vision-based approach utilizing 2D images. The study employs a dataset of 2380 images comprising fourteen different food types in various portions, orientations, and containers. The proposed methodology integrates deep learning and compu

Akash Sinha, Pramod Padmanabhan, Vladimir Korepin

The circuit model of quantum computation can be interpreted as a scattering process. In particular, factorised scattering operators result in integrable quantum circuits that provide universal quantum computation and are potentially less noisy. These are realized through Yang-Baxter or 2-simplex operators. A natural question is to extend this construction to

Anantaa Kotal, Brandon Luton, Anupam Joshi

In the realm of IoT/CPS systems connected over mobile networks, traditional intrusion detection methods analyze network traffic across multiple devices using anomaly detection techniques to flag potential security threats. However, these methods face significant privacy challenges, particularly with deep packet inspection and network communication analysis.

Regev Cohen, Idan Kligvasser, Ehud Rivlin, Daniel Freedman

The pursuit of high perceptual quality in image restoration has driven the development of revolutionary generative models, capable of producing results often visually indistinguishable from real data. However, as their perceptual quality continues to improve, these models also exhibit a growing tendency to generate hallucinations - realistic-looking details

Zhiqiang Kou, Jing Wang, Yuheng Jia, Xin Geng

In this paper, we introduce the Dependent Noise-based Inaccurate Label Distribution Learning (DN-ILDL) framework to tackle the challenges posed by noise in label distribution learning, which arise from dependencies on instances and labels. We start by modeling the inaccurate label distribution matrix as a combination of the true label distribution and a nois

Qiguang Chen, Libo Qin, Jin Zhang, Zhi Chen

Multi-modal Chain-of-Thought (MCoT) requires models to leverage knowledge from both textual and visual modalities for step-by-step reasoning, which gains increasing attention. Nevertheless, the current MCoT benchmark still faces some challenges: (1) absence of visual modal reasoning, (2) single-step visual modal reasoning, and (3) Domain missing, thereby hin

Yuang Chen, Hancheng Lu, Chang Wu, Langtian Qin

Industry 5.0 and beyond networks have driven the emergence of numerous mission-critical applications, prompting contemplation of the neXt-generation ultra-reliable low-latency communication (xURLLC). To guarantee low-latency requirements, xURLLC heavily relies on short-blocklength packets with sporadic arrival traffic. As a disruptive multi-access technique,

Shugo Yamashita, Masaaki Ikehara

Removing rain degradations in images is recognized as a significant issue. In this field, deep learning-based approaches, such as Convolutional Neural Networks (CNNs) and Transformers, have succeeded. Recently, State Space Models (SSMs) have exhibited superior performance across various tasks in both natural language processing and image processing due to th

Alexei Stepanov

In the present paper, we discuss the Pearson, Spearman, Kendall correlation coefficients and their statistical analogues. We propose a new correlation coefficient r and its statistical analogue. The coefficient r is based on Kendal's and Spearman's correlation coefficients. A new extension of the Pearson correlation coefficient is also discussed. We conduct

Ryo Kanda

We prove that every dualizable Grothendieck category whose dual is again a Grothendieck category satisfies Grothendieck's conditions Ab6 and Ab4*, by taking a module-theoretic approach based on the Gabriel-Popescu embedding. Combining this with a result by Stefanich, we conclude that the class of dualizable linear cocomplete categories is precisely the class

Sho Miyaji

Many studies run two-way fixed effects instrumental variable (TWFEIV) regressions, leveraging variation in the timing of policy adoption across units as an instrument for treatment. This paper studies the properties of the TWFEIV estimator in staggered instrumented difference-in-differences (DID-IV) designs. We show that in settings with the staggered adopti

JiaKui Hu, Man Yao, Xuerui Qiu, Yuhong Chou

Multi-timestep simulation of brain-inspired Spiking Neural Networks (SNNs) boost memory requirements during training and increase inference energy cost. Current training methods cannot simultaneously solve both training and inference dilemmas. This work proposes a novel Temporal Reversible architecture for SNNs (T-RevSNN) to jointly address the training and

Sarah Elizabeth Caddy, Lee Robert Spitler, Simon Charles Ellis

Observing stars and satellites in optical wavelengths during the day (optical daytime astronomy) has begun a resurgence of interest. The recent dramatic dimming event of Betelgeuse has spurred interest in continuous monitoring of the brightest variable stars, even when an object is only visible during the day due to their proximity to the Sun. In addition, a

Tianchen Deng, Yi Zhou, Wenhua Wu, Mingrui Li

This technical report presents the 1st winning model for UG2+, a task in CVPR 2024 UAV Tracking and Pose-Estimation Challenge. This challenge faces difficulties in drone detection, UAV-type classification and 2D/3D trajectory estimation in extreme weather conditions with multi-modal sensor information, including stereo vision, various Lidars, Radars, and aud

Dor Tsur, Haim Permuter

Despite the popularity of information measures in analysis of probabilistic systems, proper tools for their visualization are not common. This work develops a simple matrix representation of information transfer in sequential systems, termed information matrix (InfoMat). The simplicity of the InfoMat provides a new visual perspective on existing decompositio

Dian Feng, Masahiro Yamamoto

In this paper, we consider initial-boundary value problems for two-component nonlinear systems of time-fractional diffusion equations with the homogeneous Neumann boundary condition and non-negative initial values. The main results are the existence of solutions global in time and the blow-up. Our approach involves the truncation of the nonlinear terms, whic

Mathew D. Penrose, Xiaochuan Yang

Consider a spherical Poisson Boolean model $Z$ in Euclidean $d$-space with $d \geq 2$, with Poisson intensity $t$ and radii distributed like $rY$ with $r \geq 0$ a scaling parameter and $Y$ a fixed nonnegative random variable with finite $(2d-2)$-nd moment (or if $d=2$, a finite $(2 + \varepsilon)$-moment condition for some $\varepsilon >0$). Let $A \subset

Hongwei Bran Li, Cheng Ouyang, Tamaz Amiranashvili, Matthew S. Rosen

Self-supervised contrastive learning has predominantly adopted deterministic methods, which are not suited for environments characterized by uncertainty and noise. This paper introduces a new perspective on incorporating uncertainty into contrastive learning by embedding representations within a spherical space, inspired by the von Mises-Fisher distribution

Emilio N. M. Cirillo, Rainey Lyons, Adrian Muntean, Stela Andrea Muntean

Inspired by experimental evidence collected when processing thin films from ternary solutions made of two solutes, typically polymers, and one solvent, we computationally study the morphology formation of domains obtained in three-state systems using both a lattice model and a continuum counterpart. The lattice-based approach relies on the Blume-Capel neares

Tingting Chen, Shijing Si

Housing has emerged as a crucial concern among young individuals residing in major cities, including Shanghai. Given the unprecedented surge in property prices in this metropolis, young people have increasingly resorted to the rental market to address their housing needs. This study utilizes five traditional machine learning methods: multiple linear regressi

Ludovic Renou, Xavier Venel

This paper compares statistical experiments in discounted problems, ranging from the simplest ones where the state is fixed and the flow of information exogenous to more complex ones, where the decision-maker controls the flow of information or the state changes over time.

Yun-Feng Qu, Yi-Ling Lan, Hongwei Yu, Wen-Cong Gan

In this paper, we extend the method of calculating the entanglement entropy of Hawking radiation of black holes using the "in" vacuum state, which describes one-sided asymptotically flat neutral black hole formed by gravitational collapse, to dynamic charged black holes. We explore the influence of charge on the position of the boundary of island $\partial I

Kai Zhao, Zuojie He, Alex Hung, Dan Zeng

Recent studies have suggested frequency-domain Data augmentation (DA) is effec tive for time series prediction. Existing frequency-domain augmentations disturb the original data with various full-spectrum noises, leading to excess domain gap between augmented and original data. Although impressive performance has been achieved in certain cases, frequency-dom

Jiancong Xiao, Ziniu Li, Xingyu Xie, Emily Getzen

Accurately aligning large language models (LLMs) with human preferences is crucial for informing fair, economically sound, and statistically efficient decision-making processes. However, we argue that the predominant approach for aligning LLMs with human preferences through a reward model -- reinforcement learning from human feedback (RLHF) -- suffers from a

Saeed Mozaheb, Sohrab Rahvar

This study commenced by cross-matching data from the GAIA and OGLE telescopes with the aim of resolving the source star, long after microlensing is finished. The aim is breaking degeneracy between parameters of the microlensing equation, and ultimately calculating the mass of lens. We have examined different catalogs and found no evidence. Subsequently, empl

Moshe Shienman, Ohad Levy-Or, Michael Kaess, Vadim Indelman

We introduce an innovative method for incremental nonparametric probabilistic inference in high-dimensional state spaces. Our approach leverages \slices from high-dimensional surfaces to efficiently approximate posterior distributions of any shape. Unlike many existing graph-based methods, our \slices perspective eliminates the need for additional intermedia

Peter Frankl, Zoltán Füredi, Ido Goorevitch, Ron Holzman

There are four non-isomorphic configurations of triples that can form a triangle in a $3$-uniform hypergraph. Forbidding different combinations of these four configurations, fifteen extremal problems can be defined, several of which already appeared in the literature in some different context. Here we systematically study all of these problems solving the ne

Han Yu, Peikun Guo, Akane Sano

The utilization of deep learning on electrocardiogram (ECG) analysis has brought the advanced accuracy and efficiency of cardiac healthcare diagnostics. By leveraging the capabilities of deep learning in semantic understanding, especially in feature extraction and representation learning, this study introduces a new multimodal contrastive pretaining framewor

Hanting Li, Hongjing Niu, Feng Zhao

Micro-expression recognition (MER) has drawn increasing attention in recent years due to its potential applications in intelligent medical and lie detection. However, the shortage of annotated data has been the major obstacle to further improve deep-learning based MER methods. Intuitively, utilizing sufficient macro-expression data to promote MER performance