December 2023 arXiv papers — page 97

Animesh Karnewar, Roman Shapovalov, Tom Monnier, Andrea Vedaldi

Encoding information from 2D views of an object into a 3D representation is crucial for generalized 3D feature extraction. Such features can then enable 3D reconstruction, 3D generation, and other applications. We propose GOEmbed (Gradient Origin Embeddings) that encodes input 2D images into any 3D representation, without requiring a pre-trained image featur

Minghao Lu, Xiyu Fan, Han Chen, Peng Lu

Obstacle avoidance for Unmanned Aerial Vehicles (UAVs) in cluttered environments is significantly challenging. Existing obstacle avoidance for UAVs either focuses on fully static environments or static environments with only a few dynamic objects. In this paper, we take the initiative to consider the obstacle avoidance of UAVs in dynamic cluttered environmen

Daniel Schaub, Mark Spivakovsky

The Casas--Alvero conjecture predicts that every univariate polynomial $f$ over a field $K$ of characteristic zero having a common factor with each of its derivatives $H\_i(f)$ is a power of a linear polynomial. Let $f=x^d+a\_1x^{d-1}+\cdots+a\_1x \in K[a\_1,\ldots,a\_{d-1}][x]$ and let $R\_i = Res(f,H\_i(f))\in K[a\_1,\ldots,a\_{d-1}]$ be the resultant of $

Yu. N. Chiang, M. O. Dzyuba

The direct electrical method was used to study the behavior of the spin Hall effect in a magnetic field perpendicular to the injection current in aluminum samples with resistivities that differed by two orders of magnitude at a temperature of 4.2 K. The parabolic behavior of the spin-Hall voltage curves with maxima at the same value of the magnetic field was

Zhenrong Liu, Yang Li, Yi Gong, Yik-Chung Wu

In continual learning, networks confront a trade-off between stability and plasticity when trained on a sequence of tasks. To bolster plasticity without sacrificing stability, we propose a novel training algorithm called LRFR. This approach optimizes network parameters in the null space of the past tasks' feature representation matrix to guarantee the stabil

Jelena Sedlar, Riste Škrekovski

A normal 5-edge-coloring of a cubic graph is a coloring such that for every edge the number of distinct colors incident to its end-vertices is 3 or 5 (and not 4). The well known Petersen Coloring Conjecture is equivalent to the statement that every bridgeless cubic graph has a normal 5-edge-coloring. All 3-edge-colorings of a cubic graph are obviously normal

A. K. Koryttseva, A. I. Orlova, N. S. Litonova, A. V. Nokhrin

The paper presents the investigation of ordinary and ternary vanadates with zircon and monazite structures. Vanadates LnVO4 and CaLnZr(VO4)3 , where (Ln = La, Nd, Sm, Eu, Gd, Dy, Yb) and solid solution La0.3Nd0.5Sm0.1Eu0.1VO4, were prepared by precipitation reaction. Bulk ceramic samples were obtained from powders by Spark Plasma Sintering (SPS). The powders

Thinh Pham, Dat Quoc Nguyen

Profile-based intent detection and slot filling are important tasks aimed at reducing the ambiguity in user utterances by leveraging user-specific supporting profile information. However, research in these two tasks has not been extensively explored. To fill this gap, we propose a joint model, namely JPIS, designed to enhance profile-based intent detection a

Monica Montardini, Giancarlo Sangalli, Mattia Tani

In this paper, we propose an innovative isogeometric low-rank solver for the linear elasticity model problem, specifically designed to allow multipatch domains. Our approach splits the domain into subdomains, each formed by the union of neighboring patches. Within each subdomain, we employ Tucker low-rank matrices and vectors to approximate the system matric

Hao Shao, Yang Zhang, Qibin Hou

We present a new boundary sensitive framework for polyp segmentation, called Polyper. Our method is motivated by a clinical approach that seasoned medical practitioners often leverage the inherent features of interior polyp regions to tackle blurred boundaries.Inspired by this, we propose explicitly leveraging polyp regions to bolster the model's boundary di

Philipp Schmitz, Lukas Lanza, Karl Worthmann

We study output reference tracking for unknown continuous-time systems with arbitrary relative degree. The control objective is to keep the tracking error within predefined time-varying bounds while measurement data is only available at discrete sampling times. To achieve the control objective, we propose a two-component controller. One part is a recently de

Yi Xin, Junlong Du, Qiang Wang, Zhiwen Lin

Large-scale pre-trained models have achieved remarkable success in various computer vision tasks. A standard approach to leverage these models is to fine-tune all model parameters for downstream tasks, which poses challenges in terms of computational and storage costs. Recently, inspired by Natural Language Processing (NLP), parameter-efficient transfer lear

Shuhua Liu, Chunyu Zhang, Binshuai Li, Niantong Qin

Intonation is one of the important factors affecting the teaching language arts, so it is an urgent problem to be addressed by evaluating the teachers' intonation through artificial intelligence technology. However, the lack of an intonation assessment dataset has hindered the development of the field. To this end, this paper constructs a Teaching Intonation

Zhe Zeng, Xiao Wang, Felix Wilhelm Siebert, Hailong Liu

Eye typing interfaces enable a person to enter text into an interface using only their own eyes. But despite the inherent advantages of touchless operation and intuitive design, such eye-typing interfaces often suffer from slow typing speeds, resulting in slow words per minute (WPM) counts. In this study, we add word and letter prediction to the eye-typing i

Hui EnPang, Zhongang Cai, Lei Yang, Qingyi Tao

Whole-body pose and shape estimation aims to jointly predict different behaviors (e.g., pose, hand gesture, facial expression) of the entire human body from a monocular image. Existing methods often exhibit degraded performance under the complexity of in-the-wild scenarios. We argue that the accuracy and reliability of these models are significantly affected

Sheng Zhang, Haohao Sheng, Zhi-Da Song, Chenhao Liang

The $k\cdot p$ method is significant in condensed matter physics for the compact and analytical Hamiltonian. In the presence of magnetic field, it is described by the effective Zeeman's coupling Hamiltonian with Land\'e $ g $-factors. Here, we develop an open-source package VASP2KP (including two parts: vasp2mat and mat2kp) to compute $k\cdot p$ parameters a

Haobo Qi, Du Huang, Yingqiu Zhu, Danyang Huang

In this paper, we studied a buffered mini-batch gradient descent (BMGD) algorithm for training complex model on massive datasets. The algorithm studied here is designed for fast training on a GPU-CPU system, which contains two steps: the buffering step and the computation step. In the buffering step, a large batch of data (i.e., a buffer) are loaded from the

Xiaoqiang Gui, Yueyao Cheng, Xiang-Rong Sheng, Yunfeng Zhao

In machine learning systems, privileged features refer to the features that are available during offline training but inaccessible for online serving. Previous studies have recognized the importance of privileged features and explored ways to tackle online-offline discrepancies. A typical practice is privileged features distillation (PFD): train a teacher mo

Bo Li, Wei Ye, Quansen Wang, Wen Zhao

Textual label names (descriptions) are typically semantically rich in many natural language understanding (NLU) tasks. In this paper, we incorporate the prompting methodology, which is widely used to enrich model input, into the label side for the first time. Specifically, we propose a Mask Matching method, which equips an input with a prompt and its label w

Sorouralsadat Fatemi, Yuheng Hu

Financial sentiment analysis plays a crucial role in uncovering latent patterns and detecting emerging trends, enabling individuals to make well-informed decisions that may yield substantial advantages within the constantly changing realm of finance. Recently, Large Language Models (LLMs) have demonstrated their effectiveness in diverse domains, showcasing r

Dat Hong, Tong Wang

This paper introduces Personalized Path Recourse, a novel method that generates recourse paths for a reinforcement learning agent. The goal is to edit a given path of actions to achieve desired goals (e.g., better outcomes compared to the agent's original path) while ensuring a high similarity to the agent's original paths and being personalized to the agent

Julian D. Parker, Janne Spijkervet, Katerina Kosta, Furkan Yesiler

End-to-end generation of musical audio using deep learning techniques has seen an explosion of activity recently. However, most models concentrate on generating fully mixed music in response to abstract conditioning information. In this work, we present an alternative paradigm for producing music generation models that can listen and respond to musical conte

Müge Kural, Ali Gebeşçe, Tilek Chubakov, Gözde Gül Şahin

Predicting the collaboration likelihood and measuring cognitive trust to AI systems is more important than ever. To do that, previous research mostly focus solely on the model features (e.g., accuracy, confidence) and ignore the human factor. To address that, we propose several decision-making similarity measures based on divergence metrics (e.g., KL, JSD) c

Ingrid Irmer

A conjecture of Broaddus is proven, giving a simple characterisation of a representative of the unique orbit of the action of the mapping class group on the homology of Harvey's complex of curves for any genus surface. As an application, the kernel of the action of the mapping class group of a genus $g$ surface on the Steinberg module is shown to be trivial.

Yi-Chun Chen, Arnav Jhala

Understanding how humans communicate and perceive narratives is important for media technology research and development. This is particularly important in current times when there are tools and algorithms that are easily available for amateur users to create high-quality content. Narrative media develops over time a set of recognizable patterns of features a

Rajat, Ritu, Arko Roy, Sandeep Gautam

Close to the superfluid plane-wave (PW) - supersolid stripe (ST) phase transition point of a zero temperature quasi-one-dimensional spin-orbit-coupled Bose gas, we find that an increase in temperature induces a phase transition to the supersolid phase with a broken translational symmetry from the superfluid plane-wave phase. We use the Hartree-Fock-Bogoliubo

Dongnan Hu, Ruihao Xia, Xin Jin, Yang Tang

Hybrid Flying-Crawling Quadrotors (HyFCQs) are transformable robots with the ability of terrestrial and aerial hybrid motion. This article presents a trajectory planning and tracking framework designed for HyFCQs. In this framework, a terrestrial-aerial path-searching method with the crawling limitation of HyFCQs is proposed to guarantee the dynamical feasib

Matías Brizzio, César Sánchez

Developing critical components, such as mission controllers or embedded systems, is a challenging task. Reactive synthesis is a technique to automatically produce correct controllers. Given a high-level specification written in LTL, reactive synthesis consists of computing a system that satisfies the specification as long as the environment respects the assu

Chuan-Xiong Xu, Hao-Ping Yu, Mei Zhou, Xuanting Ji

Measuring the magnetoconductivity induced from impurities may help determine the impurity distribution and reveal the structure of a Weyl semimetal sample. To verify this, we utilized the Gaussian random disorder to simulate charged impurities in a two-node Weyl semimetal model and investigate the impact of charged impurities on magnetoconductivity in Weyl s

Nishad Gothoskar, Matin Ghavami, Eric Li, Aidan Curtis

Robots cannot yet match humans' ability to rapidly learn the shapes of novel 3D objects and recognize them robustly despite clutter and occlusion. We present Bayes3D, an uncertainty-aware perception system for structured 3D scenes, that reports accurate posterior uncertainty over 3D object shape, pose, and scene composition in the presence of clutter and occ

Pyae Sone Aung, Loc X. Nguyen, Yan Kyaw Tun, Zhu Han

Multi-access Edge Computing (MEC) addresses computational and battery limitations in devices by allowing them to offload computation tasks. To overcome the difficulties in establishing line-of-sight connections, integrating unmanned aerial vehicles (UAVs) has proven beneficial, offering enhanced data exchange, rapid deployment, and mobility. The utilization

Francis Frydman, Philippe Mangion

The synthesis of string transformation programs from input-output examples utilizes various techniques, all based on an inductive bias that comprises a restricted set of basic operators to be combined. A new algorithm, Transduce, is proposed, which is founded on the construction of abstract transduction grammars and their generalization. We experimentally de

Qi Lü, Bowen Ma

We study the time-inconsistent linear quadratic optimal control problem for forward-backward stochastic differential equations with potentially indefinite cost weighting matrices for both the state and the control variables. Our research makes two contributions. Firstly, we introduce a novel type of Riccati equation system with parameters and constraint cond

Pascal Hémon, Françoise Santi

This paper presents a method for generating a turbulent velocity field that can be used as an input for the temporal simulation in wind excited structure problems. Temporal simulations become necessary when nonlinear behaviour, in the structure or in aeroelastic forces, must be accounted for. The main difficulty is then to reproduce correctly the statistical

J. M. Algarín, T. Guallart-Naval, J. Borreguero, F. Galve

The open-source console MaRCoS, which stands for "Magnetic Resonance Control System", combines hardware, firmware and software elements for integral control of Magnetic Resonance Imaging (MRI) scanners. Previous developments have focused on making the system robust and reliable, rather than on users, who have been somewhat overlooked. This work describes a G

Sanghyun Son, Laura Yu Zheng, Ryan Sullivan, Yi-Ling Qiao

We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. To incorporate analytical gradients into the PPO framework, we introduce the concept of an {\alpha}-policy that stands as a locally superior policy. By adaptively modifying the {\alpha} value

Li Wan

We propose an ensemble theory for the non-equilibrium statistics to study the thermal transport in anharmonic crystals. In the theory, lattice vibrations of the crystals are quantized by local Bosons(LBs), instead of Phonons as usually used for the thermal transport. LBs are driven by the temperature gradient and move from atom to atom in the crystals. Based

Ilaria Malanchini, Nicola Michailow, Patrick Agostini, Janne Ali-Tolppa

The roll out of 5G has been mainly characterized by its distinct support for vertical industries, especially manufacturing. Leveraging synergies among these two worlds, namely production facilities and network systems, is a fundamental aspect to enable flexibility and economic viability in future factories. This work highlights the potential for intelligent

Panisara Thepthong, Peera Pongkitiwanichakul, David Ruffolo, Rungployphan Kieokaew

Alfv\'enicity is a well-known property, common in the solar wind, characterized by a high correlation between magnetic and velocity fluctuations. Data from the Parker Solar Probe (PSP) enable the study of this property closer to the Sun than ever before, as well as in sub-Alfv\'enic solar wind. We consider scale-dependent measures of Alfv\'enicity based on s

Tirthankar Bhattacharyya, Arup Chattopadhyay, Saikat Giri, Chandan Pradhan

In this note, we provide an elementary proof for the expression of $f(U)-f(V)$ in the form of a double operator integral for every Lipschitz function $f$ on the unit circle $\cir$ and for a pair of unitary operators $(U,V)$ with $U-V\in\mathcal{S}_{2}(\hilh)$ (the Hilbert-Schmidt class). As a consequence, we obtain the Schatten $2$-Lipschitz estimate $\|f(U)

Alex Bouquet, Andrés R. Vindas-Meléndez

A barcode is a finite multiset of intervals on the real line. Jaramillo-Rodriguez (2023) previously defined a map from the space of barcodes with a fixed number of bars to a set of multipermutations, which presented new combinatorial invariants on the space of barcodes. A partial order can be defined on these multipermutations, resulting in a class of posets

Rixin Zhou, Ding Xia, Yi Zhang, Honglin Pang

In this paper, we propose a learning-based image fragment pair-searching and -matching approach to solve the challenging restoration problem. Existing works use rule-based methods to match similar contour shapes or textures, which are always difficult to tune hyperparameters for extensive data and computationally time-consuming. Therefore, we propose a neura

Juyoung Park, Seokho Jeong, Minhyuk Kim, Kangheun Kim

The task of factoring integers poses a significant challenge in modern cryptography, and quantum computing holds the potential to efficiently address this problem compared to classical algorithms. Thus, it is crucial to develop quantum computing algorithms to address this problem. This study introduces a quantum approach that utilizes Rydberg atoms to tackle

Linzhuang Sun, Yao Dong, Nan Xu, Jingxuan Wei

The development of Large Language Models (LLMs) provides human-centered Artificial General Intelligence (AGI) with a glimmer of hope. Empathy serves as a key emotional attribute of humanity, playing an irreplaceable role in human-centered AGI. Despite numerous researches aim to improve the cognitive empathy of models by incorporating external knowledge, ther

Bin Shen, Yuhan Zhu

In this paper, we explore the positive solutions to the Finslerian nonlinear equation $$\frac{\partial u}{\partial t} = \Delta^{\nabla u} u + au\log u + bu,$$ which is related to Ricci solitons and serves as the Euler-Lagrange equation to the Finslerian log-energy functional. We then obtain the global gradient estimate of its positive solution on a compact F

Trung-Hieu Hoang, Jordan Fuhrman, Ravi Madduri, Miao Li

Facilitating large-scale, cross-institutional collaboration in biomedical machine learning projects requires a trustworthy and resilient federated learning (FL) environment to ensure that sensitive information such as protected health information is kept confidential. In this work, we introduce APPFLx, a low-code FL framework that enables the easy setup, con

Yi Guo, Yiqian He, Xiaoyang Li, Haotong Qin

Knowledge Distillation (KD) emerges as one of the most promising compression technologies to run advanced deep neural networks on resource-limited devices. In order to train a small network (student) under the guidance of a large network (teacher), the intuitive method is regularizing the feature maps or logits of the student using the teacher's information.

Ryosuke Matsuo, Kazuhisa Ogawa, Hidehisa Shiomi, Makoto Negoro

This paper proposes a cost-effective architecture for an RF pulse generator for superconducting qubits. Most existing works use arbitrary waveform generators (AWGs) that require both a large amount of high-bandwidth memories and high-performance analog circuits to achieve the highest gate fidelity with an optimized RF pulse waveform. The proposed pulse gener

Shaoyang Jia

In order to solve the Bethe-Salpeter equation (BSE) in the Minkowski space, we first introduce the Nakanishi integral representations of the Bethe-Salpeter amplitude (BSA) and the Bethe-Salpeter wave function (BSWF). We then derive the explicit integral equations for the corresponding spectral functions from the BSE for states of $2$ scalar particles bound b

Guoqing Chao, Yi Jiang, Dianhui Chu

Incomplete multi-view clustering becomes an important research problem, since multi-view data with missing values are ubiquitous in real-world applications. Although great efforts have been made for incomplete multi-view clustering, there are still some challenges: 1) most existing methods didn't make full use of multi-view information to deal with missing v

Xi Li, Minfu Feng

This manuscript is devoted to investigating the conservation laws of incompressible Navier-Stokes equations(NSEs), written in the energy-momentum-angular momentum conserving(EMAC) formulation, after being linearized by the two-level methods. With appropriate correction steps(e.g., Stoke/Newton corrections), we show that the two-level methods, discretized fro

Yi-Chun Chen, Arnav Jhala

We investigate the challenges of style transfer in multi-modal visual narratives. Among static visual narratives such as comics and manga, there are distinct visual styles in terms of presentation. They include style features across multiple dimensions, such as panel layout, size, shape, and color. They include both visual and text media elements. The layout

Yong-Hui Lin, Hans-Werner Hammer, Ulf-G. Meißner

We comment on the puzzling status of the proton magnetic radius determinations.

E. S. Andriyakhina, P. A. Nosov, S. Raghu, I. S. Burmistrov

The interplay between electron-electron interactions and weak localization (or anti-localization) phenomena in two-dimensional systems can significantly enhance the superconducting transition temperature. We develop the theory of quantum fluctuations within such multifractally-enhanced superconducting states in thin films. In conditions of weak disorder, we

Ru Li, Jia Liu, Guanghui Liu, Shengping Zhang

In this paper, we propose SpectralNeRF, an end-to-end Neural Radiance Field (NeRF)-based architecture for high-quality physically based rendering from a novel spectral perspective. We modify the classical spectral rendering into two main steps, 1) the generation of a series of spectrum maps spanning different wavelengths, 2) the combination of these spectrum

Raju Nandi

A new class of simple symmetric digraphs called $\mathcal{D}$ is defined and studied here. Any digraph in $\mathcal{D}$ has the property that each non-pendant vertex is adjacent to at least one pendant vertex. A graph theoretical description for the entries of the group inverse of a real square matrix with any digraph belonging to this class is given. We cla

Giusy Mazzone, Mahdi Mohebbi

We consider a mass-spring system immersed in an incompressible fluid flow governed by the Navier-Stokes equations subject to a prescribed time-periodic flow rate (and possibly external time-periodic body forces on the fluid and the mass). We show that, with no restriction on the period of the flow rate (and of the external forces), when the flow rate is "sma

Jeeseop Kim, Jaemin Lee, Aaron D. Ames

This paper presents a safety-critical approach to the coordination of robots in dynamic environments. To this end, we leverage control barrier functions (CBFs) with the forward reachable set to guarantee the safe coordination of the robots while preserving a desired trajectory via a layered controller. The top-level planner generates a safety-ensured traject

Ye Chen, Wei Cai, Liangmin Wu, Xiaowei Li

We release and introduce the TigerBot family of large language models (LLMs), consisting of base and chat models, sized from 7, 13, 70 and 180 billion parameters. We develop our models embarking from Llama-2 and BLOOM, and push the boundary further in data, training algorithm, infrastructure, and application tools. Our models yield meaningful performance gai

Xingyue Han, Hee Taek Yi, Seongshik Oh, Liang Wu

Magnetic topological insulator is a fertile platform to study the interplay between magnetism and topology. The unique electronic band structure can induce exotic transport and optical properties. However, a comprehensive optical study in both near-infrared frequency and terahertz frequency has been lacking. Here, we report magneto-optical effects from a het

Mikhail Patrakeev, Vlad Smolin

In [5] we studied spaces with a Lusin $\pi$-base and $\pi$-spaces and posed the following question: Does the class of continuous open images of spaces with a Lusin $\pi$-base equal the class of continuous open images of $\pi$-spaces? We give a negative answer to this question.

T-H. Hubert Chan, Hao Xie, Mengshi Zhao

We examine a private ADMM variant for (strongly) convex objectives which is a primal-dual iterative method. Each iteration has a user with a private function used to update the primal variable, masked by Gaussian noise for local privacy, without directly adding noise to the dual variable. Privacy amplification by iteration explores if noises from later itera

Min-Won Seo, Solmaz S. Kia

State estimation in robotic systems presents significant challenges, particularly due to the prevalence of multimodal posterior distributions in real-world scenarios. One effective strategy for handling such complexity is to compute maximum a posteriori (MAP) sequences over a discretized or sampled state space, which enables a concise representation of the m

Becky Armstrong, Abraham C. S. Ng, Aidan Sims, Yumiao Zhou

We present an example of a twist over a minimal Hausdorff \'etale groupoid such that the restriction of the twist to the interior of the isotropy is not topologically trivial; that is, the restricted twist is not induced by a continuous 2-cocycle.

Xuguang Zhang, Zixuan Zhou, Yijun Guo, Minxue Zhuang

Coherent optics has profoundly impacted diverse applications ranging from communications, LiDAR to quantum computations. However, building coherent systems in integrated photonics previously came at great expense in hardware integration and energy efficiency: the lack of a power-efficient way to generate highly coherent light necessitates bulky lasers and am

Xiaolei Wu, Shengkui Ye

We prove that the triangle Artin group $\mathrm{Art}_{23M}$ splits as a graph of free groups if and only if $M$ is greater than $5$ and even. This answers two questions of Jankiewicz \cite[Question 2.2, Question 2.3]{Jan21} in the negative. Combined with the results of Squier and Jankiewicz, this completely determines when a triangle Artin group splits as a

Haoyuan Dong, Yang Gao, Haishuai Wang, Hong Yang

Heterogeneous graph neural architecture search (HGNAS) represents a powerful tool for automatically designing effective heterogeneous graph neural networks. However, existing HGNAS algorithms suffer from inefficient searches and unstable results. In this paper, we present a new GPT-4 based HGNAS model to improve the search efficiency and search accuracy of H

Ziyan Wang, Giljoo Nam, Aljaz Bozic, Chen Cao

Hair plays a significant role in personal identity and appearance, making it an essential component of high-quality, photorealistic avatars. Existing approaches either focus on modeling the facial region only or rely on personalized models, limiting their generalizability and scalability. In this paper, we present a novel method for creating high-fidelity av

Aurel Bulgac, Matthew Kafker, Ibrahim Abdurrahman, Ionel Stetcu

The presence of pairing correlations within the time-dependent density functional theory (TDDFT) extension to superfluid systems, is tantamount to the presence of a quantum collision integral in the evolution equations, which leads to an obviously non-Markovian behavior of the single-particle occupation probabilities, unexpected in a traditional quantum exte

Frank Liu, Agniva Chowdhury

In various scientific and engineering applications, there is typically an approximate model of the underlying complex system, even though it contains both aleatoric and epistemic uncertainties. In this paper, we present a principled method to incorporate these approximate models as physics priors in modeling, to prevent overfitting and enhancing the generali

Sakshi Ranjan, Pooja Priyadarshini, Subhankar Mishra

Happiness underlines the intuitive constructs of a specified population based on positive psychological outcomes. It is the cornerstone of the cognitive skills and exploring university student's happiness has been the essence of the researchers lately. In this study, we have analyzed the university student's happiness and its facets using statistical distrib

Doyoung Kim, Dongmin Park, Yooju Shin, Jihwan Bang

We propose a novel framework DropTop that suppresses the shortcut bias in online continual learning (OCL) while being adaptive to the varying degree of the shortcut bias incurred by continuously changing environment. By the observed high-attention property of the shortcut bias, highly-activated features are considered candidates for debiasing. More important

Junjie Li, Yiwei Guo, Xie Chen, Kai Yu

Zero-shot voice conversion (VC) aims to transfer the source speaker timbre to arbitrary unseen target speaker timbre, while keeping the linguistic content unchanged. Although the voice of generated speech can be controlled by providing the speaker embedding of the target speaker, the speaker similarity still lags behind the ground truth recordings. In this p

Xiangtao Meng, Li Wang, Shanqing Guo, Lei Ju

While DeepFake applications are becoming popular in recent years, their abuses pose a serious privacy threat. Unfortunately, most related detection algorithms to mitigate the abuse issues are inherently vulnerable to adversarial attacks because they are built atop DNN-based classification models, and the literature has demonstrated that they could be bypasse

Tom G. Mackay, Akhlesh Lakhtakia

Depolarization dyadics play a central role in theoretical studies involving scattering from small particles and homogenization of particulate composite materials. Closed-form expressions for depolarization dyadics have been developed for truncated spheres and truncated spheroids, and the formalism has been extended to truncated ellipsoids; the evaluation of

Renjie Wu, Hu Wang, Feras Dayoub, Hsiang-Ting Chen

Augmented Reality (AR) devices, emerging as prominent mobile interaction platforms, face challenges in user safety, particularly concerning oncoming vehicles. While some solutions leverage onboard camera arrays, these cameras often have limited field-of-view (FoV) with front or downward perspectives. Addressing this, we propose a new out-of-view semantic seg

Silu He, Qinyao Luo, Xinsha Fu, Ling Zhao

Local Attention-guided Message Passing Mechanism (LAMP) adopted in Graph Attention Networks (GATs) is designed to adaptively learn the importance of neighboring nodes for better local aggregation on the graph, which can bring the representations of similar neighbors closer effectively, thus showing stronger discrimination ability. However, existing GATs suff

Asela Hevapathige, Qing Wang

Graph Neural Networks (GNNs) have paved the way for being a cornerstone in graph-related learning tasks. Yet, the ability of GNNs to capture structural interactions within graphs remains under-explored. In this work, we address this gap by drawing on the insight that permutation invariant graph partitioning enables a powerful way of exploring structural inte

Tao Hu, Honglong Zhang, Fan Zeng, Min Du

In the field of intracity freight transportation, changes in order volume are significantly influenced by temporal and spatial factors. When building subsidy and pricing strategies, predicting the causal effects of these strategies on order volume is crucial. In the process of calculating causal effects, confounding variables can have an impact. Traditional

Zesen Huang, Chen Shi, Marco Velli, Nikos Sioulas

One of the primary science objectives of Parker Solar Probe (PSP) is to determine the structures and dynamics of the plasma and magnetic fields at the sources of the solar wind. However, establishing the connection between {\it in situ} measurements and structures and dynamics in the solar atmosphere is challenging: most of the magnetic footpoint mapping tec

Sotaro Katayama, Noriaki Takasugi, Mitsuhisa Kaneko, Masaya Kinoshita

This paper presents a nonlinear model predictive control (NMPC) toward versatile motion generation for the telescopic-wheeled-legged robot Tachyon 3, the unique hardware structure of which poses challenges in control and motion planning. We apply the full-centroidal NMPC formulation with dedicated constraints that can capture the accurate kinematics and dyna

Yichen Wan, Youyang Qu, Wei Ni, Yong Xiang

Due to the greatly improved capabilities of devices, massive data, and increasing concern about data privacy, Federated Learning (FL) has been increasingly considered for applications to wireless communication networks (WCNs). Wireless FL (WFL) is a distributed method of training a global deep learning model in which a large number of participants each train

Bin Shu

Suppose $g=g_0+g_1$ is a finite-dimensional restricted Lie superalgebra over an algebraically closed field $k$ of characteristic $p>2$. In this article, we propose a conjecture for maximal dimensions of irreducible modules over the universal enveloping algebra $U(g)$ of $g$, as a super generalization of the celebrated first Kac-Weisfeiler conjecture. It is d

Nikita A. Afimchenko, Aleksandr A. Shubin, Igor L. Zilberberg, Alexander P. Nemudry

The present work puts forward a concept that the thermostable O1s XPS peaks with energy of about 531 eV in negative charge-transfer SrFeO_{3-\delta} perovskite are determined by the peroxo-like oxygen species. The peroxo group forms via coupling two oxygen anions coordinated to iron cations with d^5\bar-under{L} (\bar-under{L}-oxygen electron hole) configura

Kezheng Xiong, Maoji Zheng, Qingshan Xu, Chenglu Wen

Point cloud registration, a fundamental task in 3D computer vision, has remained largely unexplored in cross-source point clouds and unstructured scenes. The primary challenges arise from noise, outliers, and variations in scale and density. However, neglected geometric natures of point clouds restricts the performance of current methods. In this paper, we p

Manato Sakai, Yasuhiro Yamaguchi

${T_{cc}(cc\bar{u}\bar{d})}^{+}$ has been reported by the LHCb experiment in 2022. The analysis using the Breit-Wigner parametrization found the small binding energy, $0.273$ MeV, which is measured from the threshold of $D^{*+}D^{0}$. In this paper, we consider $T_{cc}$ as a $DD^*$ hadronic molecule as a deuteron-like state. The one boson exchange model is e

Violet Xiang, Logan Cross, Jan-Philipp Fränken, Nick Haber

In real-world environments, autonomous agents rely on their egocentric observations. They must learn adaptive strategies to interact with others who possess mixed motivations, discernible only through visible cues. Several Multi-Agent Reinforcement Learning (MARL) methods adopt centralized approaches that involve either centralized training or reward-sharing

Siddhartha Sahi, Songhao Zhu

The Shimura operators are a certain distinguished basis for invariant differential operators on a Hermitian symmetric space. Answering a question of Shimura, Sahi and Zhang showed that the Harish-Chandra images of these operators are specializations of certain $BC$-symmetric interpolation polynomials that were defined by Okounkov. We consider the analogs of

Noriyuki Tonami, Wataru Kohno, Sakiko Mishima, Yumi Arai

Optical fiber sensing is a technology wherein audio, vibrations, and temperature are detected using an optical fiber; especially the audio/vibrations-aware sensing is called distributed acoustic sensing (DAS). In DAS, observed data, which is comprised of multichannel data, has suffered from severe noise levels because of the optical noise or the installation

Stephen Wu, Yu Otake, Daijiro Mizutani, Chang Liu

The integration of Large Language Models (LLMs) like ChatGPT into the workflows of geotechnical engineering has a high potential to transform how the discipline approaches problem-solving and decision-making. This paper delves into the innovative application of LLMs in geotechnical engineering, as explored in a hands-on workshop held in Tokyo, Japan. The eve

Affan Yasin, Rubia Fatima

The research introduces a novel plant disease detection model based on Convolutional Neural Networks (CNN) for plant image classification, marking a significant contribution to image categorization. The innovative training approach enables a streamlined and efficient system implementation. The model classifies two distinct plant diseases into four categories

Shun Muroga, Takashi Honda, Yasuaki Miki, Hideaki Nakajima

To meet the demands for more adaptable and expedient approaches to augment both research and manufacturing, we report an autonomous system using real-time in-situ characterization and an autonomous, decision-making processer based on an active learning algorithm. This system was applied to a plastic film forming system to highlight its efficiency and accurac

Naping Guo, Yi-Long Luo

The self-organized kinetic system for body attitude coordination (SOKB) was recently derived by Degond et al. (Math. Models Methods Appl. Sci. 27(6), 1005-1049, 2017). This system describe a new collective motion for multi-agents dynamics, where each agent is described by its position and body attitude: agents travel at a constant speed in a given direction

Hongwu Peng, Xi Xie, Kaustubh Shivdikar, MD Amit Hasan

In the acceleration of deep neural network training, the GPU has become the mainstream platform. GPUs face substantial challenges on GNNs, such as workload imbalance and memory access irregularities, leading to underutilized hardware. Existing solutions such as PyG, DGL with cuSPARSE, and GNNAdvisor frameworks partially address these challenges but memory tr

I. Bubanja, A. Bermudez Martinez, L. Favart, F. Guzman

The Parton Branching (PB) method describes the evolution of transverse momentum dependent (TMD) parton distributions, covering all kinematic regions from small to large transverse momenta kT. The small kT-region is very sensitive both to the contribution of the intrinsic motion of partons (intrinsic kT) and to the resummation of soft gluons taken into accoun

Danial Sharifrazi, Nouman Javed, Roohallah Alizadehsani, Prasad N. Paradkar

Mosquito-borne diseases present considerable risks to the health of both animals and humans. Aedes aegypti mosquitoes are the primary vectors for numerous medically important viruses such as dengue, Zika, yellow fever, and chikungunya. To characterize this mosquito neural activity, it is essential to classify the generated electrical spikes. However, no open

Shuailei Ma, Yuefeng Wang, Ying Wei, Jiaqi Fan

In this paper, we attempt to specialize the VLM model for OWOD tasks by distilling its open-world knowledge into a language-agnostic detector. Surprisingly, we observe that the combination of a simple \textbf{knowledge distillation} approach and the automatic pseudo-labeling mechanism in OWOD can achieve better performance for unknown object detection, even

Snigdha Ghosh, Nilanjan Chaudhuri, Sourav Sarkar, Pradip Roy

We explore the properties of neutral mesons within the context of a chirally imbalanced medium, employing the two-flavor Nambu--Jona-Lasinio model. The temperature dependence of the constituent quark mass at finite values of the chiral chemical potential (CCP) demonstrates the well-established phenomena of chiral catalysis at lower temperatures and inverse c

Ao Liu, Wenshan Li, Tao Li, Beibei Li

Graph neural networks (GNNs) have recently been shown to be vulnerable to adversarial attacks, where slight perturbations in the graph structure can lead to erroneous predictions. However, current robust models for defending against such attacks inherit the transductive limitations of graph convolutional networks (GCNs). As a result, they are constrained by

Kawisorn Kamtue, Jose M. F. Moura, Orathai Sangpetch, Paulo Garcia

While deep learning has been very successful in computer vision, real world operating conditions such as lighting variation, background clutter, or occlusion hinder its accuracy across several tasks. Prior work has shown that hybrid models -- combining neural networks and heuristics/algorithms -- can outperform vanilla deep learning for several computer visi