May 2023 arXiv papers — page 97

Chong Yu, Tao Chen, Zhongxue Gan, Jiayuan Fan

The transformer extends its success from the language to the vision domain. Because of the stacked self-attention and cross-attention blocks, the acceleration deployment of vision transformer on GPU hardware is challenging and also rarely studied. This paper thoroughly designs a compression scheme to maximally utilize the GPU-friendly 2:4 fine-grained struct

Amos Okomayin, Tosin Ige

Ambient intelligence refers to technological enhanced electronic environments which are both responsive and sensitive to the presence of people within their environment. Environments that are integrated with ambient intelligence tends to adapt to the needs of individuals within the environment in an unobtrusive manner in such a way as to enhance everyday lif

Svetlana Boyarchenko, Sergei Levendorskiĭ

We derive several sets of sufficient conditions for applicability of the new efficient numerical realization of the inverse $Z$-transform. For large $n$, the complexity of the new scheme is dozens of times smaller than the complexity of the trapezoid rule. As applications, pricing of European options and single barrier options with discrete monitoring are co

Yunkang Cao, Xiaohao Xu, Chen Sun, Yuqi Cheng

We present a novel framework, i.e., Segment Any Anomaly + (SAA+), for zero-shot anomaly segmentation with hybrid prompt regularization to improve the adaptability of modern foundation models. Existing anomaly segmentation models typically rely on domain-specific fine-tuning, limiting their generalization across countless anomaly patterns. In this work, inspi

Matteo Ippoliti

We study classical shadows protocols based on randomized measurements in $n$-qubit entangled bases, generalizing the random Pauli measurement protocol ($n = 1$). We show that entangled measurements ($n\geq 2$) enable nontrivial and potentially advantageous trade-offs in the sample complexity of learning Pauli expectation values. This is sharply illustrated b

Xuehai He, Weixi Feng, Tsu-Jui Fu, Varun Jampani

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified in text prompts, can we leverage the powerful representations learned by pre-trained diffusion models for discriminative

Yihong Fan, Zach Cresswell, Yifei Yang, Wei Jiang

Topological semimetal materials have become a research hotspot due to their intrinsic strong spin-orbit coupling which leads to large charge-to-spin conversion efficiency and novel transport behaviors. In this work, we have observed a bilinear magnetoelectric resistance (BMER) of up to 0.1 nm2A-1Oe-1 in a singlelayer of sputtered semimetal Pt3Sn at room temp

Liyang Yang

Let $F$ be a number field, $\pi$ either a unitary cuspidal automorphic representation of $\mathrm{GL}(2)/F$ or a unitary Eisenstein series, and $\chi$ a unitary Hecke character of analytic conductor $C(\chi).$ We develop a regularized relative trace formula to prove a refined hybrid subconvex bound for $L(1/2,\pi\times\chi).$ In particular, we obtain the Bur

Han Qi, Yue Wang, Li Zhu

Non-stationary multi-armed bandit (NS-MAB) problems have recently received significant attention. NS-MAB are typically modelled in two scenarios: abruptly changing, where reward distributions remain constant for a certain period and change at unknown time steps, and smoothly changing, where reward distributions evolve smoothly based on unknown dynamics. In t

L. Mashonkina, A. Arentsen, D. S. Aguado, A. Smogorzhevskii

Well-studied very metal-poor (VMP, [Fe/H] < -2 ) stars in the inner Galaxy are few in number, and they are of special interest because they are expected to be among the oldest stars in the MilkyWay. We present high-resolution spectroscopic follow-up of the carbon-enhanced metal-poor (CEMP) star Pristine_184237.56-260624.5 (hereafter Pr184237) identified in t

Qianli Ma, Zhen Liu, Zhenjing Zheng, Ziyang Huang

Time-Series Mining (TSM) is an important research area since it shows great potential in practical applications. Deep learning models that rely on massive labeled data have been utilized for TSM successfully. However, constructing a large-scale well-labeled dataset is difficult due to data annotation costs. Recently, pre-trained models have gradually attract

Cosimo Bambi

General relativity is one of the pillars of modern physics. For decades, the theory has been mainly tested in the weak field regime with experiments in the Solar System and radio observations of binary pulsars. Until 2015, the strong field regime was almost completely unexplored. Thanks to new observational facilities, the situation has dramatically changed

Taolin Zhang, Sunan He, Dai Tao, Bin Chen

In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks. However, when extended to point cloud data, existing works mainly focus on building task-specific models, and fail to extract universal 3D vision-

Lingfeng Shen, Weiting Tan, Boyuan Zheng, Daniel Khashabi

With growing capabilities of large language models, prompting them has become the dominant way to access them. This has motivated the development of strategies for automatically selecting effective language prompts. In this paper, we introduce prompt flatness, a new metric to quantify the expected utility of a language prompt. This metric is inspired by flat

Brett McInnes

The fact that AdS black hole interior geometries are time-dependent presents two challenges: first, to holographic duality (the boundary matter tends to equilibrate, often very quickly), and, second, to the idea that wormholes can be traversable (the wormhole geometry is dynamic, and the wormhole is apt to collapse too quickly for traversal to be possible).

Pavle V. M. Blagojevic, Nikola Sadovek

A decade ago two groups of authors, Karasev, Hubard and Aronov, and Blagojevi\'c and Ziegler, have shown that the regular convex partitions of a Euclidean space into $n$ parts yield a solution to the generalised Nandakumar and Ramana-Rao conjecture when $n$ is a prime power. This was obtained by parametrising the space of regular equipartitions of a given co

David J. Warne, Oliver J. Maclaren, Elliot J. Carr, Matthew J. Simpson

Likelihood profiling is an efficient and powerful frequentist approach for parameter estimation, uncertainty quantification and practical identifiablity analysis. Unfortunately, these methods cannot be easily applied for stochastic models without a tractable likelihood function. Such models are typical in many fields of science, rendering these classical app

Tingting Wu, Xiao Ding, Minji Tang, Hao Zhang

Large-scale datasets in the real world inevitably involve label noise. Deep models can gradually overfit noisy labels and thus degrade model generalization. To mitigate the effects of label noise, learning with noisy labels (LNL) methods are designed to achieve better generalization performance. Due to the lack of suitable datasets, previous studies have fre

Ayomide Owoyemi, Emmanuel Nnaemeka, Temitope O. Benson, Ronald Ikpe

The uptake of health insurance has been poor in Nigeria, a significant step to improving this includes improved awareness, access to information and tools to support decision making. Artificial intelligence (AI) based recommender systems have gained popularity in helping individuals find movies, books, music, and different types of products on the internet i

Zengyi Du, Hui Li, Genda Gu, Ahbay N. Pasupathy

Traditionally, X-ray scattering techniques have been used to detect the breaking of the structural symmetry of the lattice, which accompanies a periodic displacement of the atoms associated with charge density wave (CDW) formation in the cuprate pseudogap states. Similarly, the Spectroscopic Imaging Scanning Tunneling Microscopy (SI-STM) has visualized the s

Elham Kiyani, Khemraj Shukla, George Em Karniadakis, Mikko Karttunen

We propose a framework and an algorithm to uncover the unknown parts of nonlinear equations directly from data. The framework is based on eXtended Physics-Informed Neural Networks (X-PINNs), domain decomposition in space-time, but we augment the original X-PINN method by imposing flux continuity across the domain interfaces. The well-known Allen-Cahn equatio

Dehao Xu, Jianchun Wang, Shiyi Chen

The wall cooling effect on the spectra and structures of thermodynamic variables are investigated in hypersonic turbulent boundary layers. The density and temperature can be divided into the acoustic and entropic modes based on the Kovasznay decomposition. The intensities of the pressure and the acoustic modes of density and temperature attain the maximum va

Zhengyang Chen, Bing Han, Shuai Wang, Yanmin Qian

This paper proposes a novel Attention-based Encoder-Decoder network for End-to-End Neural speaker Diarization (AED-EEND). In AED-EEND system, we incorporate the target speaker enrollment information used in target speaker voice activity detection (TS-VAD) to calculate the attractor, which can mitigate the speaker permutation problem and facilitate easier mod

Yue Yu, Yuchen Zhuang, Rongzhi Zhang, Yu Meng

With the development of large language models (LLMs), zero-shot learning has attracted much attention for various NLP tasks. Different from prior works that generate training data with billion-scale natural language generation (NLG) models, we propose a retrieval-enhanced framework to create training data from a general-domain unlabeled corpus. To realize th

Alexander Perry, Laura Pertusi, Xiaolei Zhao

We study moduli spaces of stable objects in Enriques categories by exploiting their relation to moduli spaces of stable objects in associated K3 categories. In particular, we settle the nonemptiness problem for moduli spaces of stable objects in the Kuznetsov components of several interesting classes of Fano varieties, and deduce the nonemptiness of fixed lo

Yihao Huang, Felix Juefei-Xu, Qing Guo, Jie Zhang

Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, they also present an exploitable avenue for high accessible backdoor attacks. This paper investigates a critical and unexplored aspect of text-to-image (T2I) diffusion models - thei

Bhavna, Ashish Kumar Pandey, Anastassiya Semenova

The rotation modified Kadomtsev Petviashvili equation which is also known as the Kadomtsev Petviashvili Ostrovsky equation, describes the gradual wave field diffusion in the transverse direction to the direction of the propagation of the wave in a rotating frame of reference. This equation is a generalization of the Ostrovsky equation additionally having wea

Pavel Avdeyev, Chenlai Shi, Yuhao Tan, Kseniia Dudnyk

Designing biological sequences is an important challenge that requires satisfying complex constraints and thus is a natural problem to address with deep generative modeling. Diffusion generative models have achieved considerable success in many applications. Score-based generative stochastic differential equations (SDE) model is a continuous-time diffusion m

Jumman Hossain, Rajib Chandra Das, Md. Ruhul Amin, Md. Saiful Islam

There have thousands of crimes are happening daily all around. But people keep statistics only few of them, therefore crime rates are increasing day by day. The reason behind can be less concern or less statistics of previous crimes. It is much more important to observe the previous crime statistics for general people to make their outing decision and police

Jiin Woo, Gauri Joshi, Yuejie Chi

When the data used for reinforcement learning (RL) are collected by multiple agents in a distributed manner, federated versions of RL algorithms allow collaborative learning without the need for agents to share their local data. In this paper, we consider federated Q-learning, which aims to learn an optimal Q-function by periodically aggregating local Q-esti

Zheyu Zhang, Tianping Zhang, Jian Li

Gradient Boosting Decision Tree (GBDT) has achieved remarkable success in a wide variety of applications. The split finding algorithm, which determines the tree construction process, is one of the most crucial components of GBDT. However, the split finding algorithm has long been criticized for its bias towards features with a large number of potential split

Bin Fang, Bo Li, Shuang Wu, Tianyi Zheng

Artificial Intelligence (AI) is making a profound impact in almost every domain. One of the crucial factors contributing to this success has been the access to an abundance of high-quality data for constructing machine learning models. Lately, as the role of data in artificial intelligence has been significantly magnified, concerns have arisen regarding the

Lars Tyge Nielsen

Ito's Lemma implies that if $W$ is a Wiener process and $f$ is a twice continuously differentiable function, then the process $f(W)$ is the sum of a time integral and an Ito integral. The Ito integrand is not necessarily locally square integrable. This note provides a counterexample.

Majid Kheybari, Osama R. Bilal

Various two-dimensional fabrication methods, such as deposition, etching, milling, laser cutting, and water jetting, suffer from asymmetry between the top and the bottom surface of fabricated parts. Such asymmetry is usually undesirable and can compromise functionality, or at least add uncertainty to fabricated components. The common practice is to assume sy

Jingjing Guo

Precisely forecasting the excess returns of an asset (e.g., Tesla stock) is beneficial to all investors. However, the unpredictability of market dynamics, influenced by human behaviors, makes this a challenging task. In prior research, researcher have manually crafted among of factors as signals to guide their investing process. In contrast, this paper view

Tsz Wai Ko, Jonas A. Finkler, Stefan Goedecker, Jörg Behler

In recent years, significant progress has been made in the development of machine learning potentials (MLPs) for atomistic simulations with applications in many fields from chemistry to materials science. While most current MLPs are based on environment-dependent atomic energies, the limitations of this locality approximation can be overcome, e.g., in fourth

Bin Fang, Bo Li, Shuang Wu, Ran Yi

The unauthorized use of personal data for commercial purposes and the clandestine acquisition of private data for training machine learning models continue to raise concerns. In response to these issues, researchers have proposed availability attacks that aim to render data unexploitable. However, many current attack methods are rendered ineffective by adver

Andrea Montanari

Diffusions are a successful technique to sample from high-dimensional distributions. The target distribution can be either explicitly given or learnt from a collection of samples. They implement a diffusion process whose endpoint is a sample from the target distribution. The drift of the diffusion process is typically represented as a neural network. Stochas

Ibuki Terashima, Tetsuo Hyodo

We study the properties of the hadron-hadron potentials and quark-antiquark potentials from the viewpoint of the channel coupling. We demonstrate that, for finite quark masses, the coupling to the two-hadron continuum induces the imaginary part of the quark-antiquark potential, in contrast to the string-breaking phenomena in the static limit. It is also show

Zequn Liu, Wei Zhang, Yingce Xia, Lijun Wu

Generative pre-trained Transformer (GPT) has demonstrates its great success in natural language processing and related techniques have been adapted into molecular modeling. Considering that text is the most important record for scientific discovery, in this paper, we propose MolXPT, a unified language model of text and molecules pre-trained on SMILES (a sequ

Dajun Zhang, Akhil Polamarasetty, Muhammad Osama Shahid, Bhuvana Krishnaswamy

Real-time, low-cost, and wireless mechanical vibration monitoring is necessary for industrial applications to track the operation status of equipment, environmental applications to proactively predict natural disasters, as well as day-to-day applications such as vital sign monitoring. Despite this urgent need, existing solutions, such as laser vibrometers, c

Jinzheng He, Jinglin Liu, Zhenhui Ye, Rongjie Huang

We are interested in a challenging task, Realistic-Music-Score based Singing Voice Synthesis (RMS-SVS). RMS-SVS aims to generate high-quality singing voices given realistic music scores with different note types (grace, slur, rest, etc.). Though significant progress has been achieved, recent singing voice synthesis (SVS) methods are limited to fine-grained m

Pablo Bhowmik, Firdavs Rakhmonov

Let $E\subset\mathbb{F}_q^d$ and $\lVert \cdot \rVert:\mathbb{F}_q^d\to \mathbb{F}_q$ defined as $\lVert \alpha\rVert:= \alpha_1^2+\dots+\alpha_d^2$ if $\alpha=(\alpha_1,\dots,\alpha_d)\in \mathbb{F}_q^d$, where $\mathbb{F}_q^d$ is the $d$-dimensional vector space over the finite field $\mathbb{F}_q$ with $q$ elements. Let $k\geq 1$ and $A$ is a nonempty sub

Avani Tanna, Michael Saxon, Amr El Abbadi, William Yang Wang

Voice conversion (VC) models have demonstrated impressive few-shot conversion quality on the clean, native speech populations they're trained on. However, when source or target speech accents, background noise conditions, or microphone characteristics differ from training, quality voice conversion is not guaranteed. These problems are often left unexamined i

Zhenhailong Wang, Ansel Blume, Sha Li, Genglin Liu

Action knowledge involves the understanding of textual, visual, and temporal aspects of actions. We introduce the Action Dynamics Benchmark (ActionBench) containing two carefully designed probing tasks: Action Antonym and Video Reversal, which targets multimodal alignment capabilities and temporal understanding skills of the model, respectively. Despite rece

Enping Zhou, Yong Gao, Yurui Zhou, Xiaoyu Lai

The equilibrium configuration of a solid strange star in the final inspiral phase with another compact object is generally discussed, and the starquake-related issue is revisited, for a special purpose to understand the precursor emission of binary compact star merger events (e.g., that of GRB211211A). As the binary system inspirals inward due to gravitation

Yinglun Xu, Gagandeep Singh

We propose the first black-box targeted attack against online deep reinforcement learning through reward poisoning during training time. Our attack is applicable to general environments with unknown dynamics learned by unknown algorithms and requires limited attack budgets and computational resources. We leverage a general framework and find conditions to en

Xian Shi, Haoneng Luo, Zhifu Gao, Shiliang Zhang

Estimating confidence scores for recognition results is a classic task in ASR field and of vital importance for kinds of downstream tasks and training strategies. Previous end-to-end~(E2E) based confidence estimation models (CEM) predict score sequences of equal length with input transcriptions, leading to unreliable estimation when deletion and insertion er

Xin-Ye Li, Jiang-Tian Xue, Zheng Xie, Ming Li

Code generation aims to automatically generate source code from high-level task specifications, which can significantly increase productivity of software engineering. Recently, approaches based on large language models (LLMs) have shown remarkable code generation abilities on simple tasks. However, generate code for more complex tasks, such as competition-le

Qian Li, Li Wang

We provide an European option pricing formula written in the form of an infinite series of Black Scholes type terms under double Levy jumps model, where both the interest rate and underlying price are driven by Levy process. The series solution converges with a radius of convergence, and it is complemented by some numerical experiments to demonstrate its spe

Jie Song, Guanwen Fang, Yizhou Gu, Zesen Lin

How the environment influences the most massive galaxies is still unclear. To explore the environmental effects on morphology and star formation in the most massive galaxies at high redshift, we select galaxies with stellar mass $\log(M_{\star}/M_{\odot})>11$ at $0.5<z<2.5$ in the COSMOS-DASH field, which is the largest field with near-infrared photometrical

Shihao Xia, Youlin Wang, Minglong Lv, Jincan Chen

To investigate the impact of fractional parameter on the thermodynamic behaviors of quantum systems, we incorporate fractional quantum mechanics into the cycle of a quantum Stirling heat engine and examine the influence of fractional parameter on the regeneration and efficiency. We propose a novel approach to control the thermodynamic cycle that leverages th

Gaurav N. Gadbail, Himanshu Chaudhary, Amine Bouali, P. K. Sahoo

We study the $f(Q,T)$ gravity in the framework of Weyl geometry (known as Weyl-type $f(Q,T)$ gravity), where $Q$ denotes the non-metricity scalar, and $T$ denotes the energy-momentum tensor trace. In this work, we consider the $f(Q,T)$ model, which is defined as $f(Q,T)=\alpha Q^{m+1}+\frac{\beta}{6\kappa^2}T$ and investigating two scenarios: $(I)$ $m=0$ (li

Harsimrat Kaeley, Ye Qiao, Nader Bagherzadeh

Stock trend analysis has been an influential time-series prediction topic due to its lucrative and inherently chaotic nature. Many models looking to accurately predict the trend of stocks have been based on Recurrent Neural Networks (RNNs). However, due to the limitations of RNNs, such as gradient vanish and long-term dependencies being lost as sequence leng

Chaitanya Animesh, Manmohan Chandraker

In recent times, contrastive learning based loss functions have become increasingly popular for visual self-supervised representation learning owing to their state-of-the-art (SOTA) performance. Most of the modern contrastive learning methods generalize only to one positive and multiple negatives per anchor. A recent state-of-the-art, supervised contrastive

Dmitry Zverevich, A. V. Andreev, Alex Levchenko

We develop a theory of heat transfer induced by thermal charge fluctuations in two-dimensional electron double layers. We consider pristine systems comprised of identical layers, and focus on the regime of sufficiently high temperatures and interlayer distances $d$, where the relevant charge fluctuations may be described using the hydrodynamic approach. In t

Jintang Li, Sheng Tian, Ruofan Wu, Liang Zhu

The prevalence of large-scale graphs poses great challenges in time and storage for training and deploying graph neural networks (GNNs). Several recent works have explored solutions for pruning the large original graph into a small and highly-informative one, such that training and inference on the pruned and large graphs have comparable performance. Althoug

Daniel Olshansky, Ramiro Rodríguez Colmeiro

Relay Mining presents a scalable solution employing probabilistic mechanisms, crypto-economic incentives, and new cryptographic primitives to estimate and prove the volume of Remote Procedure Calls (RPCs) made from a client to a server. Distributed ledgers are designed to secure permissionless state transitions (writes), highlighting a gap for incentivizing

Liqin Qian, Minjia Shi, Wei Lu

In this paper, we give a new method answer to a recent conjecture proposed by Budaghyan, Calderini, Carlet, Davidova and Kaleyski about the equation $x^d+(x+1)^d=b$ in $\mathbb{F}_{q^4}$, where $n$ is a positive integer, $q=2^n$ and $d=q^3+q^2+q-1$. In particular, we directly determine the differential spectrum of this power function $x^d$ using methods diff

Peihua Ma, Yixin Wu, Ning Yu, Yang Zhang

Nutrition information is crucial in precision nutrition and the food industry. The current food composition compilation paradigm relies on laborious and experience-dependent methods. However, these methods struggle to keep up with the dynamic consumer market, resulting in delayed and incomplete nutrition data. In addition, earlier machine learning methods ov

Chandrika Kamath

Poincar\'e plots, also called Poincar\'e maps, are used by plasma physicists to understand the behavior of magnetically confined plasma in numerical simulations of a tokamak. These plots are created by the intersection of field lines with a two-dimensional poloidal plane that is perpendicular to the axis of the torus representing the tokamak. A plot is compo

Eduardo C. Cuansing

We study the effects of dilution to the critical properties of site-diluted Ising model in two dimensions using Monte Carlo simulations. Quenched disorder from the dilution is incorporated into the Ising model via random empty sites on the square lattice of Ising spins. Thermodynamic quantities such as the magnetization $M$ per spin, energy $E$ per spin, mag

Jun Qi, Chao-Han Huck Yang, Pin-Yu Chen, Min-Hsiu Hsieh

Data encoding remains a fundamental bottleneck in quantum machine learning, where amplitude encoding of high-dimensional classical vectors into quantum states incurs exponential cost. In this work, we propose a pre-trained tensor-train (TT) encoding network (Pre-TT-Encoder) that significantly reduces the computational complexity of amplitude encoding while p

Jean-François Paquet

The Gubser solution to inviscid relativistic fluid dynamics is used to examine the role of transverse expansion on the energy spectrum of photons radiated by quark-gluon plasma. Transverse flow is shown to be a modest effect on the energy spectrum of photons as a whole, despite its large effect on rare high-energy photons produced at low temperatures. An exa

Xiongxiao Xu, Kaize Ding, Canyu Chen, Kai Shu

Graph anomaly detection has long been an important problem in various domains pertaining to information security such as financial fraud, social spam and network intrusion. The majority of existing methods are performed in an unsupervised manner, as labeled anomalies in a large scale are often too expensive to acquire. However, the identified anomalies may t

R. L. Lambo, G. K. Koyanagi, M. Horbatsch, R. Fournier

The local environment of a barium monofluoride (BaF) molecule embedded in a neon matrix is studied theoretically. The energy of the BaF-Ne triatomic system is calculated with a scalar relativistic Hamiltonian, using coupled-cluster theory at the CCSD(T) level for $1625$ positions of the Ne atom relative to the BaF molecule. The calculations are repeated with

Junyan Su, Qiulin Lin, Minghua Chen

We study the carbon footprint optimization (CFO) of a heavy-duty e-truck traveling from an origin to a destination across a national highway network subject to a hard deadline, by optimizing path planning, speed planning, and intermediary charging planning. Such a CFO problem is essential for carbon-friendly e-truck operations. However, it is notoriously cha

Nevin N. Weinberg, Niyousha Davachi, Reed Essick, Hang Yu

We study tidal dissipation in hot Jupiter host stars due to the nonlinear damping of tidally driven $g$-modes, extending the calculations of Essick & Weinberg (2016) to a wide variety of non-solar type hosts. This process causes the planet's orbit to decay and has potentially important consequences for the evolution and fate of hot Jupiters. Previous studies

Zelin Ying, Chen Li, Yu Dong, Qiuqiang Kong

The front-end is a critical component of English text-to-speech (TTS) systems, responsible for extracting linguistic features that are essential for a text-to-speech model to synthesize speech, such as prosodies and phonemes. The English TTS front-end typically consists of a text normalization (TN) module, a prosody word prosody phrase (PWPP) module, and a g

Zhaoyu Chen, Bo Li, Shuang Wu, Kaixun Jiang

Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human perception and deep neural networks with stealth and success. However, current works usually sacrifice unrestricted degrees and

Jorge Loría, Anindya Bhadra

From the classical and influential works of Neal (1996), it is known that the infinite width scaling limit of a Bayesian neural network with one hidden layer is a Gaussian process, when the network weights have bounded prior variance. Neal's result has been extended to networks with multiple hidden layers and to convolutional neural networks, also with Gauss

Ming-Yue Liu, Shu-Min Zhao, Yi-Tong Wang, Xi Wang

In this paper, we study the lepton flavor violating decays of the $l_j\rightarrow l_i \gamma\gamma$ (j=2, 3; i=1, 2) processes under the $U(1)_X$SSM. The $U(1)_X$SSM is the addition of three singlet new Higgs superfields and right-handed neutrinos to the minimal supersymmetric standard model (MSSM). Based on the latest experimental constraints of $l_j\righta

Bochao Liu, Pengju Wang, Weijia Guo, Yong Li

While generative models have proved successful in many domains, they may pose a privacy leakage risk in practical deployment. To address this issue, differentially private generative model learning has emerged as a solution to train private generative models for different downstream tasks. However, existing private generative modeling approaches face signifi

Yitong Li, Chang Liu, Jie Ma

Weakly supervised learning based on scribble annotations in target extraction of remote sensing images has drawn much interest due to scribbles' flexibility in denoting winding objects and low cost of manually labeling. However, scribbles are too sparse to identify object structure and detailed information, bringing great challenges in target localization an

Dazhuang He, Yiling Xie, Hao Sun

We study the process $D^0 \to \pi^+ \pi^- f_0(980),\ f_0 \to \pi^+ \pi^-$ by introducing the triangle mechanism, in which $f_0(980)$ is considered to be dynamically generated from the meson-meson interaction. For the total contribution of this process, the contribution of the triangular loop formed by $K^{*} \bar{K} K$ particles could generate a triangular s

Mengzhe Geng, Zengrui Jin, Tianzi Wang, Shujie Hu

A key challenge in dysarthric speech recognition is the speaker-level diversity attributed to both speaker-identity associated factors such as gender, and speech impairment severity. Most prior researches on addressing this issue focused on using speaker-identity only. To this end, this paper proposes a novel set of techniques to use both severity and speake

Mingwei Tang, Yubing Han, Danchen Jia, Qing Yang

Far-field chemical microscopy providing molecular electronic or vibrational fingerprint information opens a new window for the study of three-dimensional biological, material, and chemical systems. Chemical microscopy provides a nondestructive way of chemical identification without exterior labels. However, the diffraction limit of optics hindered it from di

Ruby Annette J, Aisha Banu, Sharon Priya S, Subash Chandran

Artificial Intelligence (AI) is playing a vital role in all aspects of technology including cyber security. Application of Conversational AI like the chatbots are also becoming very popular in the medical field to provide timely and immediate medical assistance to patients in need. As medical chatbots deal with a lot of sensitive information, the security of

Yefei He, Luping Liu, Jing Liu, Weijia Wu

Diffusion models have recently dominated image synthesis tasks. However, the iterative denoising process is expensive in computations at inference time, making diffusion models less practical for low-latency and scalable real-world applications. Post-training quantization (PTQ) of diffusion models can significantly reduce the model size and accelerate the sa

Xinyu Zhang, Kung-Sik Chan

Multivariate time series may be subject to partial structural changes over certain frequency band, for instance, in neuroscience. We study the change point detection problem with high dimensional time series, within the framework of frequency domain. The overarching goal is to locate all change points and delineate which series are activated by the change, o

Andres Diaz-Pinto, Pritesh Mehta, Sachidanand Alle, Muhammad Asad

Automatic segmentation of medical images is a key step for diagnostic and interventional tasks. However, achieving this requires large amounts of annotated volumes, which can be tedious and time-consuming task for expert annotators. In this paper, we introduce DeepEdit, a deep learning-based method for volumetric medical image annotation, that allows automat

Brendan Conway-Smith, Robert L. West

There have been increasing challenges to dual-system descriptions of System-1 and System-2, critiquing them as imprecise and fostering misconceptions. We address these issues here by way of Dennett's appeal to use computational thinking as an analytical tool, specifically we employ the Common Model of Cognition. Results show that the characteristics thought

Nianqi Hu, Huatang Tan

Cavity electromagnonics has increasingly emerged as a new platform for the fundamental study of quantum mechanics and quantum technologies. Since the coupling between the microwave field and magnon Kittle modes in current experiments is much weaker than their resonant frequencies, the anti-rotating terms in magnon-microwave-photon interaction can be neglecte

Peter Ochieng

The current monaural state of the art tools for speech separation relies on supervised learning. This means that they must deal with permutation problem, they are impacted by the mismatch on the number of speakers used in training and inference. Moreover, their performance heavily relies on the presence of high-quality labelled data. These problems can be ef

Hengfa Lu, Huihui Ye, Lawrence L. Wald, Bo Zhao

Magnetic Resonance (MR) Fingerprinting is an emerging multi-parametric quantitative MR imaging technique, for which image reconstruction methods utilizing low-rank and subspace constraints have achieved state-of-the-art performance. However, this class of methods often suffers from an ill-conditioned model-fitting issue, which degrades the performance as the

Yunsoo Ha, Sara Shashaani

Adaptive sampling with interpolation-based trust regions or ASTRO-DF is a successful algorithm for stochastic derivative-free optimization with an easy-to-understand-and-implement concept that guarantees almost sure convergence to a first-order critical point. To reduce its dependence on the problem dimension, we present local models with diagonal Hessians c

Xingchen Song, Di Wu, Binbin Zhang, Zhendong Peng

In this paper, we present ZeroPrompt (Figure 1-(a)) and the corresponding Prompt-and-Refine strategy (Figure 3), two simple but effective \textbf{training-free} methods to decrease the Token Display Time (TDT) of streaming ASR models \textbf{without any accuracy loss}. The core idea of ZeroPrompt is to append zeroed content to each chunk during inference, wh

Mengke Li, Yiu-ming Cheung, Yang Lu, Zhikai Hu

It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing methods have addressed this problem by reducing classifier bias, provided that the features obtained with long-tailed data

Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar, Dinesh Manocha

Biomedical Named Entity Recognition (BioNER) is the fundamental task of identifying named entities from biomedical text. However, BioNER suffers from severe data scarcity and lacks high-quality labeled data due to the highly specialized and expert knowledge required for annotation. Though data augmentation has shown to be highly effective for low-resource NE

Jianlong Zhou, Heimo Müller, Andreas Holzinger, Fang Chen

Large language models, e.g. ChatGPT are currently contributing enormously to make artificial intelligence even more popular, especially among the general population. However, such chatbot models were developed as tools to support natural language communication between humans. Problematically, it is very much a ``statistical correlation machine" (correlation

Peter Ochieng

This paper looks at the ability of large language models to participate in educational guided reading. We specifically, evaluate their ability to generate meaningful questions from the input text, generate diverse questions both in terms of content coverage and difficulty of the questions and evaluate their ability to recommend part of the text that a studen

Balayogi G, Kuppusamy K S

Persons with visual impairments have often been a soft target for cybercriminals, and they are more susceptible to cyber attacks in the digital environment. The attacks, as mentioned above, are because they are visually/aurally exposed to the other sighted users. Visually impaired computer users suffer from secrecy and privacy issues on digital platforms. Th

Yijing Lin, Zhipeng Gao, Hongyang Du, Dusit Niyato

As the Metaverse continues to grow, the need for efficient communication and intelligent content generation becomes increasingly important. Semantic communication focuses on conveying meaning and understanding from user inputs, while AI-Generated Content utilizes artificial intelligence to create digital content and experiences. Integrated Semantic Communica

Nathan Beck, Suraj Kothawade, Pradeep Shenoy, Rishabh Iyer

Deep neural networks have consistently shown great performance in several real-world use cases like autonomous vehicles, satellite imaging, etc., effectively leveraging large corpora of labeled training data. However, learning unbiased models depends on building a dataset that is representative of a diverse range of realistic scenarios for a given task. This

Jun Hong Lim, Kaibo He, Zeji Yi, Chen Hou

Rehabilitation training for patients with motor disabilities usually requires specialized devices in rehabilitation centers. Home-based multi-purpose training would significantly increase treatment accessibility and reduce medical costs. While it is unlikely to equip a set of rehabilitation robots at home, we investigate the feasibility to use the general-pu

A. Marsman, M. Horbatsch, E. A. Hessels

A full density-matrix simulation is performed for optical deflection of a barium monofluoride ($^{138}$Ba$^{19}$F) beam using the bichromatic force, which employs pairs of counter-propagating laser beams that are offset in frequency. We show that the force is sufficient to separate BaF molecules from the other products generated in a helium-buffer-gas-cooled

Xiaoguang Li, Qing Guo, Pingping Cai, Wei Feng

Shadow removal is to restore shadow regions to their shadow-free counterparts while leaving non-shadow regions unchanged. State-of-the-art shadow removal methods train deep neural networks on collected shadow & shadow-free image pairs, which are desired to complete two distinct tasks via shared weights, i.e., data restoration for shadow regions and identical

Zhizhen Ma, Zhuoran Li, Behrouz Movahhed Nouri, Ke Liu

Advances in opto-electronics are often led by discovery and development of materials featuring unique properties. Recently the material class of transparent conductive oxides (TCO) has attracted attention for active photonic devices on-chip. In particular Indium Tin Oxide (ITO) is found to have refractive index changes on the order of unity. This property ma

Dongjie Wang, Zhengzhang Chen, Yanjie Fu, Yanchi Liu

The task of root cause analysis (RCA) is to identify the root causes of system faults/failures by analyzing system monitoring data. Efficient RCA can greatly accelerate system failure recovery and mitigate system damages or financial losses. However, previous research has mostly focused on developing offline RCA algorithms, which often require manually initi

Yu Gui, Rina Foygel Barber, Cong Ma

Matrix completion aims to estimate missing entries in a data matrix, using the assumption of a low-complexity structure (e.g., low rank) so that imputation is possible. While many effective estimation algorithms exist in the literature, uncertainty quantification for this problem has proved to be challenging, and existing methods are extremely sensitive to m