May 2023 arXiv papers — page 77

Siyu Chen, Jing Na, Yingbo Huang

Although persistent excitation is often acknowledged as a sufficient condition to exponentially converge in the field of adaptive parameter estimation, it must be noted that in practical applications this may be unguaranteed. Recently, more attention has turned to another relaxed condition, i.e., finite excitation. In this paper, for a class of nominal nonli

E. O. Angüner

Cosmic rays (CRs) are charged particles that arrive at Earth isotropically from all directions and interact with the atmosphere. The presence of a spectral knee feature seen in the CR spectrum at $\sim$3 PeV energies is an evidence that astrophysical objects within our Galaxy, which are known as 'Galactic PeVatrons', are capable of accelerating particles to

Didar Zowghi, Francesca da Rimini

To date, there has been little concrete practical advice about how to ensure that diversity and inclusion considerations should be embedded within both specific Artificial Intelligence (AI) systems and the larger global AI ecosystem. In this chapter, we present a clear definition of diversity and inclusion in AI, one which positions this concept within an ev

Janosch Rieger, Kyria Wawryk

Reachable sets of nonlinear control systems can in general only be approximated numerically, and these approximations are typically very expensive to compute. In this paper, we explore a strategy for choosing the temporal and spatial discretizations of Euler's method for reachable set computation in a non-uniform way to improve the performance of the method.

Haoning Wu, Erli Zhang, Liang Liao, Chaofeng Chen

The proliferation of in-the-wild videos has greatly expanded the Video Quality Assessment (VQA) problem. Unlike early definitions that usually focus on limited distortion types, VQA on in-the-wild videos is especially challenging as it could be affected by complicated factors, including various distortions and diverse contents. Though subjective studies have

Tasdiqul Islam, Engin Arslan

Conventional Quantum Key Distribution (QKD) requires the transmission of multiple qubits equivalent to the length of the key. As quantum networks are still in their infancy thus, they are expected to have a limited capacity, necessitating too many qubit transmissions for QKD might limit the effective use of limited network bandwidth of quantum networks. To a

Feng Yan, Weixin Luo, Yujie Zhong, Yiyang Gan

Existing end-to-end Multi-Object Tracking (e2e-MOT) methods have not surpassed non-end-to-end tracking-by-detection methods. One potential reason is its label assignment strategy during training that consistently binds the tracked objects with tracking queries and then assigns the few newborns to detection queries. With one-to-one bipartite matching, such an

Yutong Zhou

We propose a cyclic generative adversarial network with spatial-wise and channel-wise attention modules for text-to-image synthesis. To accurately depict and design scenes with multiple occluded objects, we design a pre-trained ordering recovery model and a generative adversarial network to predict layout and composite novel box lunch presentations. In the e

Xinlu Zhang, Shiyang Li, Xianjun Yang, Chenxin Tian

Large language models (LLMs) demonstrate remarkable medical expertise, but data privacy concerns impede their direct use in healthcare environments. Although offering improved data privacy protection, domain-specific small language models (SLMs) often underperform LLMs, emphasizing the need for methods that reduce this performance gap while alleviating priva

Gustav Nilsson, Alejandro D. Owen Aquino, Samuel Coogan, Daniel K. Molzahn

The ongoing electrification of the transportation fleet will increase the load on the electric power grid. Since both the transportation network and the power grid already experience periods of significant stress, joint analyses of both infrastructures will most likely be necessary to ensure acceptable operation in the future. To enable such analyses, this p

Sitaram Ramakrishnan, Tatsuya Yamakawa, Ryohei Oishi, Yasuyuki Shimura

Single crystals of non-centrosymmetric $s$-wave superconductor LaPt$_{0.88}$Si$_{1.12}$ have been grown by the Czochralski (Cz) technique, whose crystal structure is described by the space group $I4{_1}md$ at ambient conditions. The inter-site mixing between platinum and silicon is confirmed by both single-crystal x-ray diffraction (SXRD) and electron probe

Masanori Hirano, Masahiro Suzuki, Hiroki Sakaji

This study constructed a Japanese chat dataset for tuning large language models (LLMs), which consist of about 8.4 million records. Recently, LLMs have been developed and gaining popularity. However, high-performing LLMs are usually mainly for English. There are two ways to support languages other than English by those LLMs: constructing LLMs from scratch or

Bang Wu, Xu-Jie Wang, Li Liu, Guoqi Huang

Resonant excitation is an essential tool in the development of semiconductor quantum dots (QDs) for quantum information processing. One central challenge is to enable a transparent access to the QD signal without post-selection information loss. A viable path is through cavity enhancement, which has successfully lifted the resonantly scattered field strength

Yannan Nellie Wu, Po-An Tsai, Saurav Muralidharan, Angshuman Parashar

Due to complex interactions among various deep neural network (DNN) optimization techniques, modern DNNs can have weights and activations that are dense or sparse with diverse sparsity degrees. To offer a good trade-off between accuracy and hardware performance, an ideal DNN accelerator should have high flexibility to efficiently translate DNN sparsity into

Chia-Chien Hung, Lukas Lange, Jannik Strötgen

Intermediate training of pre-trained transformer-based language models on domain-specific data leads to substantial gains for downstream tasks. To increase efficiency and prevent catastrophic forgetting alleviated from full domain-adaptive pre-training, approaches such as adapters have been developed. However, these require additional parameters for each lay

Yuxuan Ding, Chunna Tian, Haoxuan Ding, Lingqiao Liu

The Stable Diffusion model is a prominent text-to-image generation model that relies on a text prompt as its input, which is encoded using the Contrastive Language-Image Pre-Training (CLIP). However, text prompts have limitations when it comes to incorporating implicit information from reference images. Existing methods have attempted to address this limitat

Hao Chen, Ankit Shah, Jindong Wang, Ran Tao

Learning with reduced labeling standards, such as noisy label, partial label, and multiple label candidates, which we generically refer to as \textit{imprecise} labels, is a commonplace challenge in machine learning tasks. Previous methods tend to propose specific designs for every emerging imprecise label configuration, which is usually unsustainable when m

June-Young Kim

Transition generalized parton distributions have emerged as a novel tool for studying the quantum chromodynamics (QCD) structure of resonances. They provide an integrated picture of the transition form factors and the transition parton distribution functions. In this study, we delve into the angular momentum (AM) properties for the $N\to \Delta$ transition a

Mridweeka Singh, Devendra. K. Sahu, Raya Dastidar, Barnabas Barna

We present the optical photometric and spectroscopic analysis of two type Iax SNe 2018cni and 2020kyg. SN 2018cni is a bright type Iax SN (M$_{V,peak}$ = $-$17.81$\pm$0.21 mag) whereas SN 2020kyg (M$_{V,peak}$ = $-$14.52$\pm$0.21 mag) is a faint one. We derive $^{56}$Ni mass of 0.07 and 0.002 M${_\odot}$, ejecta mass of 0.48 and 0.14 M${_\odot}$ for SNe 2018

Shwetank Choudhary, CR Karthik, Punuru Sri Lakshmi, Sumit Kumar

Over the past few years, audio classification task on large-scale dataset such as AudioSet has been an important research area. Several deeper Convolution-based Neural networks have shown compelling performance notably Vggish, YAMNet, and Pretrained Audio Neural Network (PANN). These models are available as pretrained architecture for transfer learning as we

De Cheng, Xiaojian Huang, Nannan Wang, Lingfeng He

Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset, which is crucial for practical applications in video surveillance systems. The key to essentially address the USL-VI-ReID task is to solve the cross-modality data association problem for further het

Bingsheng Yao, Ishan Jindal, Lucian Popa, Yannis Katsis

Real-world domain experts (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning techniques, such as Active Learning (AL), that aim to support human annotators mostly focus on the label while neglecting the natural language explanation of a data point. This work p

Seraphina Goldfarb-Tarrant, Björn Ross, Adam Lopez

Sentiment analysis (SA) systems are widely deployed in many of the world's languages, and there is well-documented evidence of demographic bias in these systems. In languages beyond English, scarcer training data is often supplemented with transfer learning using pre-trained models, including multilingual models trained on other languages. In some cases, eve

Huadai Liu, Rongjie Huang, Xuan Lin, Wenqiang Xu

Text-to-speech(TTS) has undergone remarkable improvements in performance, particularly with the advent of Denoising Diffusion Probabilistic Models (DDPMs). However, the perceived quality of audio depends not solely on its content, pitch, rhythm, and energy, but also on the physical environment. In this work, we propose ViT-TTS, the first visual TTS model wit

Hanyin Shao, Jie Huang, Shen Zheng, Kevin Chen-Chuan Chang

The advancement of large language models (LLMs) brings notable improvements across various applications, while simultaneously raising concerns about potential private data exposure. One notable capability of LLMs is their ability to form associations between different pieces of information, but this raises concerns when it comes to personally identifiable in

Saurabh Chandra Kandpal, Kgalaletso P. Otukile, Shweta Jindal, Salini Senthil

The hydroperoxyalkyl radicals (.QOOH) are known to play a significant role in combustion and tropospheric processes, yet their direct spectroscopic detection remains challenging. In this study, we investigate molecular stereo-electronic effects influencing the kinetic and thermodynamic stability of a .QOOH along its formation path from the precursor, alkylpe

Fabio Ruetz, Nicholas Lawrance, Emili Hernández, Paulo Borges

Autonomous navigation in unstructured vegetated environments remains an open challenge. To successfully operate in these settings, ground vehicles must assess the traversability of the environment and determine which vegetation is pliable enough to push through. In this work, we propose a novel method that combines a high-fidelity and feature-rich 3D voxel r

Yoichiro Hisadome, Tianyi Wu, Jiawei Qin, Yusuke Sugano

Appearance-based gaze estimation has been actively studied in recent years. However, its generalization performance for unseen head poses is still a significant limitation for existing methods. This work proposes a generalizable multi-view gaze estimation task and a cross-view feature fusion method to address this issue. In addition to paired images, our met

Zhuo Li, Jingze Lu, Zhenduo Zhao, Wenchao Wang

Utilizing the large-scale unlabeled data from the target domain via pseudo-label clustering algorithms is an important approach for addressing domain adaptation problems in speaker verification tasks. In this paper, we propose a novel progressive subgraph clustering algorithm based on multi-model voting and double-Gaussian based assessment (PGMVG clustering)

Eduardo Vitral, Mattia Libralato, Kyle Kremer, Gary A. Mamon

Recent studies of nearby globular clusters have discovered excess dark mass in their cores, apparently in an extended distribution, and simulations indicate that this mass is composed mostly of white dwarfs (respectively stellar-mass black holes) in clusters that are core-collapsed (respectively with a flatter core). We perform mass-anisotropy modelling of t

Shipei Liu, Xiaoya Fan, Guowei Wu

Underwater acoustic target recognition (UATR) and localization (UATL) play important roles in marine exploration. The highly noisy acoustic signal and time-frequency interference among various sources pose big challenges to this task. To tackle these issues, we propose a multimodal approach to extract and fuse audio-visual-textual information to recognize an

Tomoya Asaba, Lang Peng, Takahiro Ono, Satoru Akutagawa

Continued advances in quantum technologies rely on producing nanometer-scale wires. Although several state-of-the-art nanolithographic technologies and bottom-up synthesis processes have been used to engineer such wires, critical challenges remain in growing uniform atomic-scale crystalline wires and constructing their network structures. Here we discover a

Ramy E. Ali

Cadambe and Lyu 2021 presents an erasure coding based algorithm called CausalEC that ensures causal consistency based on cross-object erasure coding. This note shows that the algorithm presented in Cadambe and Lyu 2021 and the main ideas behind it are in essence the same as the algorithm developed in Lyu, Cadambe, Ali and Urgaonkar 2018.

Dwaipayan Saha, Ananya Parashar

In this paper, we survey literature on prophet inequalities for subadditive combinatorial auctions. We give an overview of the previous best $O(\log \log m)$ prophet inequality as well as the preceding $O(\log m)$ prophet inequality. Then, we provide the constructive posted price mechanisms used in order to prove the two bounds. We mainly focus on the most r

Sihong Chen, Taisong Pan, Zhengcheng Mou, Bing-Zhong Wang

The active control of electromagnetically induced transparency (EIT) metamaterials (MM) has the potential to revolutionize communication networks without relying on quantum technology. However, current reconfigurable systems offer limited flexibility and have high fabrication costs and difficulties. In this study, we examine a classical EIT metamaterial and

Argha Debnath, Ayan Khan, Prasanta K Panigrahi

Recent inspection of liquid-like state in ultracold atomic gases due to the stabilization mechanism through the delicate balance between effective mean-field and beyond mean-field (BMF) interactions, has motivated us to study the modified/extended Gross-Pitaevskii (eGP) equation which includes the BMF contribution. In this article, we focus on variational an

Ajay Patel, Delip Rao, Ansh Kothary, Kathleen McKeown

Style representation learning builds content-independent representations of author style in text. Stylometry, the analysis of style in text, is often performed by expert forensic linguists and no large dataset of stylometric annotations exists for training. Current style representation learning uses neural methods to disentangle style from content to create

Ali Kazemi Arani, Triet Huynh Minh Le, Mansooreh Zahedi, Muhammad Ali Babar

This research conducted a systematic review of the literature on machine learning (ML)-based methods in the context of Continuous Integration (CI) over the past 22 years. The study aimed to identify and describe the techniques used in ML-based solutions for CI and analyzed various aspects such as data engineering, feature engineering, hyper-parameter tuning,

Thierno Ibrahima Cissé, Fatiha Sadat

This paper presents a spell checker and correction tool specifically designed for Wolof, an under-represented spoken language in Africa. The proposed spell checker leverages a combination of a trie data structure, dynamic programming, and the weighted Levenshtein distance to generate suggestions for misspelled words. We created novel linguistic resources for

Yi Zhong, Ke Yang

In this work, we address the localization problem of vector field in the chameleon braneworld and investigate the localization of various matter fields. The conditions for localizing the matter fields are determined. It is found that the zero modes of scalar, vector, and fermion fields can be successfully localized, yet the zero mode of Kalb-Ramond field can

Zhenrui Yue, Huimin Zeng, Yang Zhang, Lanyu Shang

With emerging topics (e.g., COVID-19) on social media as a source for the spreading misinformation, overcoming the distributional shifts between the original training domain (i.e., source domain) and such target domains remains a non-trivial task for misinformation detection. This presents an elusive challenge for early-stage misinformation detection, where

Yuxia Chen, Pengcheng Fang, Jianhui Yu, Xiaoling Zhong

High-resolution remote sensing (HRS) semantic segmentation extracts key objects from high-resolution coverage areas. However, objects of the same category within HRS images generally show significant differences in scale and shape across diverse geographical environments, making it difficult to fit the data distribution. Additionally, a complex background en

Mst. Bina Aktar, F. Parvin, A. K. M. Azharul Islam, S. H. Naqib

In this study, we have used density functional theory (DFT) based first-principles investigation of the physical properties of prospective NbAlB compound for the first time. From the analysis of the cohesive energy and enthalpy of formation, it was found that NbAlB is chemically stable. The physical properties of NbAlB have been compared and contrasted with

Ting Chen, Lala Li

We present FIT: a transformer-based architecture with efficient self-attention and adaptive computation. Unlike original transformers, which operate on a single sequence of data tokens, we divide the data tokens into groups, with each group being a shorter sequence of tokens. We employ two types of transformer layers: local layers operate on data tokens with

Rui Xue

Given a graph $G$, the graph $[G]$ obtained by adding, for each pair of vertices of $G$, a unique vertex adjacent to both vertices is called the binding graph of $G$. In this work, we show that the class of binding graphs is graph-isomorphism complete and that the stable partitions of binding graphs by the Weisfeiler-Lehman (WL) algorithm produce automorphis

Z. P. Wang, R. J. Lin, Z. Y. Zhao, P. M. Guo

To optimize flapping foil performance, the application of deep reinforcement learning (DRL) on controlling foil non-parametric motion is conducted in the present study. Traditional control techniques and simplified motions cannot fully model nonlinear, unsteady and high-dimensional foil-vortex interactions. A DRL-training framework based on Proximal Policy O

Wenlu Tang, Zicheng Liu

The application of machine learning models can be significantly impeded by the occurrence of distributional shifts, as the assumption of homogeneity between the population of training and testing samples in machine learning and statistics may not be feasible in practical situations. One way to tackle this problem is to use invariant learning, such as invaria

Tianle Wang, Lianghao Xia, Chao Huang

Social recommendation is gaining increasing attention in various online applications, including e-commerce and online streaming, where social information is leveraged to improve user-item interaction modeling. Recently, Self-Supervised Learning (SSL) has proven to be remarkably effective in addressing data sparsity through augmented learning tasks. Inspired

Jinjie Ni, Rui Mao, Zonglin Yang, Han Lei

Recent studies have revealed some issues of Multi-Head Attention (MHA), e.g., redundancy and over-parameterization. Specifically, the heads of MHA were originally designed to attend to information from different representation subspaces, whereas prior studies found that some attention heads likely learn similar features and can be pruned without harming perf

Brian Shin

In this article, we establish the compatibility between norms and transfers in motivic homotopy theory. More precisely, we construct norm functors for motivic spaces equipped with various flavours of transfer. This yields a norm monoidal refinement of the infinite $\mathbb{P}^1$-delooping machine of Elmanto-Hoyois-Khan-Sosnilo-Yakerson. We apply this refinem

Chumeng Liang, Xiaoyu Wu

Diffusion Models (DMs) have empowered great success in artificial-intelligence-generated content, especially in artwork creation, yet raising new concerns in intellectual properties and copyright. For example, infringers can make profits by imitating non-authorized human-created paintings with DMs. Recent researches suggest that various adversarial examples

Mahdi Chehimi, Bernd Simon, Walid Saad, Anja Klein

Enabling quantum switches (QSs) to serve requests submitted by quantum end nodes in quantum communication networks (QCNs) is a challenging problem due to the heterogeneous fidelity requirements of the submitted requests and the limited resources of the QCN. Effectively determining which requests are served by a given QS is fundamental to foster developments

Yuta Mimura

Generative models excel in creating realistic images, yet their dependency on extensive datasets for training presents significant challenges, especially in domains where data collection is costly or challenging. Current data-efficient methods largely focus on GAN architectures, leaving a gap in training other types of generative models. Our study introduces

Haolan Zhan, Xuanli He, Qiongkai Xu, Yuxiang Wu

The burgeoning progress in the field of Large Language Models (LLMs) heralds significant benefits due to their unparalleled capacities. However, it is critical to acknowledge the potential misuse of these models, which could give rise to a spectrum of social and ethical dilemmas. Despite numerous preceding efforts centered around distinguishing synthetic tex

Chenjie Mao

We study learning optimal policies from a logged dataset, i.e., offline RL, with function approximation. Despite the efforts devoted, existing algorithms with theoretic finite-sample guarantees typically assume exploratory data coverage or strong realizable function classes, which is hard to be satisfied in reality. While there are recent works that successf

Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Anh Tuan Luu

Multimodal Review Helpfulness Prediction (MRHP) aims to rank product reviews based on predicted helpfulness scores and has been widely applied in e-commerce via presenting customers with useful reviews. Previous studies commonly employ fully-connected neural networks (FCNNs) as the final score predictor and pairwise loss as the training objective. However, F

Jinsong Chen, Chang Liu, Kaiyuan Gao, Gaichao Li

Graph Transformers, emerging as a new architecture for graph representation learning, suffer from the quadratic complexity on the number of nodes when handling large graphs. To this end, we propose a Neighborhood Aggregation Graph Transformer (NAGphormer) that treats each node as a sequence containing a series of tokens constructed by our proposed Hop2Token

Hong Liu, Zhaobiao Lv, Zhijian Ou, Wenbo Zhao

Energy-based language models (ELMs) parameterize an unnormalized distribution for natural sentences and are radically different from popular autoregressive language models (ALMs). As an important application, ELMs have been successfully used as a means for calculating sentence scores in speech recognition, but they all use less-modern CNN or LSTM networks. T

Haoran Yang, Deng Cai, Huayang Li, Wei Bi

We introduce a frustratingly simple, super efficient and surprisingly effective decoding method, which we call Frustratingly Simple Decoding (FSD), for neural text generation. The idea behind FSD is straightforward: we build an anti-LM based on previously generated text and use this anti-LM to penalize future generation of what has been generated. The anti-L

Kazumi Okuyama

We study the end of the world (EOW) brane in double scaled SYK (DSSYK) model. We find that the boundary state of EOW brane is a coherent state of the $q$-deformed oscillators and the associated orthogonal polynomial is the continuous big $q$-Hermite polynomial. In a certain scaling limit, the big $q$-Hermite polynomial reduces to the Whittaker function, whic

De Cheng, Lingfeng He, Nannan Wang, Shizhou Zhang

Unsupervised visible-infrared person re-identification (USL-VI-ReID) aims to match pedestrian images of the same identity from different modalities without annotations. Existing works mainly focus on alleviating the modality gap by aligning instance-level features of the unlabeled samples. However, the relationships between cross-modality clusters are not we

Weijie Gan, Shirin Shoushtari, Yuyang Hu, Jiaming Liu

Plug-and-play (PnP) prior is a well-known class of methods for solving imaging inverse problems by computing fixed-points of operators combining physical measurement models and learned image denoisers. While PnP methods have been extensively used for image recovery with known measurement operators, there is little work on PnP for solving blind inverse proble

Carlos Aguirre, Mark Dredze

Training supervised machine learning systems with a fairness loss can improve prediction fairness across different demographic groups. However, doing so requires demographic annotations for training data, without which we cannot produce debiased classifiers for most tasks. Drawing inspiration from transfer learning methods, we investigate whether we can util

Peixin Zhu, Lisa J. Kewley, Ralph S. Sutherland

The photoionization model of narrow-line regions (NLRs) in active galactic nuclei (AGNs) has been investigated for decades. Many published models are restricted to simple linear scaling abundance relations, dust-free assumption, uniform AGN radiation field, and using one specific photoionization code, which restricts them from providing a satisfactory predic

Jie Yang, Chao-Kai Wen, Jing Xu, Hang Que

Simultaneous localization and mapping (SLAM) is a key technology that provides user equipment (UE) tracking and environment mapping services, enabling the deep integration of sensing and communication. The millimeter-wave (mmWave) communication, with its larger bandwidths and antenna arrays, inherently facilitates more accurate delay and angle measurements t

Wenyu Wang, Wu-Long Xu, Jin Min Yang, Rui Zhu

For the light relativistic dark matter (DM) boosted by high energy cosmic ray, its scattering cross section with the nucleon is sensitively dependent on the momentum-transfer and such an dependence is caused by the mediator in the scattering. For puffy DM particle with a size, the momentum-transfer dependence can also arise from the DM radius effect. All the

Margherita De Marzio, Amit Das, Jeffrey J. Fredberg, Dapeng Bi

The transition of an epithelial layer from a stationary, quiescent state to a highly migratory, dynamic state is required for wound healing, development, and regeneration. This transition, known as the unjamming transition (UJT), is responsible for epithelial fluidization and collective migration. Previous theoretical models have primarily focused on the UJT

Xiaoyan Li, Ryo Ikehata

We consider the total energy decay of the Cauchy problem for wave equations with a potential and an effective damping. We treat it in the whole one-dimensional Euclidean space. Fast energy decay is established with the help of potential. The proofs of main results rely on a multiplier method and modified techniques adopted in [8].

Qasim Ajao, Olukotun Oludamilare

Autonomous electric vehicles (AEVs) hold great promise for the future of automotive engineering, but safety remains a significant challenge in their development and commercialization. Therefore, conducting a comprehensive analysis of AEV development and reported accidents is crucial. This paper reviews the levels of automation in AEVs, their disengagement fr

Ali Rad

The overparameterization of variational quantum circuits, as a model of Quantum Neural Networks (QNN), not only improves their trainability but also serves as a method for evaluating the property of a given ansatz by investigating their kernel behavior in this regime. In this study, we shift our perspective from the traditional viewpoint of training in param

Yecheng Jason Ma, Kausik Sivakumar, Jason Yan, Osbert Bastani

Standard model-based reinforcement learning (MBRL) approaches fit a transition model of the environment to all past experience, but this wastes model capacity on data that is irrelevant for policy improvement. We instead propose a new "transition occupancy matching" (TOM) objective for MBRL model learning: a model is good to the extent that the current polic

Hye-young Kim, Minjin Choi, Sunkyung Lee, Eunseong Choi

Query reformulation is a key mechanism to alleviate the linguistic chasm of query in ad-hoc retrieval. Among various solutions, query reduction effectively removes extraneous terms and specifies concise user intent from long queries. However, it is challenging to capture hidden and diverse user intent. This paper proposes Contextualized Query Reduction (ConQ

Chuanxin Song, Hanbo Wu, Xin Ma

Exploring the semantic context in scene images is essential for indoor scene recognition. However, due to the diverse intra-class spatial layouts and the coexisting inter-class objects, modeling contextual relationships to adapt various image characteristics is a great challenge. Existing contextual modeling methods for scene recognition exhibit two limitati

Siyu Yuan, Jiangjie Chen, Xuyang Ge, Yanghua Xiao

The vital role of analogical reasoning in human cognition allows us to grasp novel concepts by linking them with familiar ones through shared relational structures. Despite the attention previous research has given to word analogies, this work suggests that Large Language Models (LLMs) often overlook the structures that underpin these analogies, raising ques

Zhenghao Zhang, Shengfan Zhang, Zhichao Wei, Zuozhuo Dai

The current state-of-the-art methods for unsupervised video object segmentation (UVOS) require extensive training on video datasets with mask annotations, limiting their effectiveness in handling challenging scenarios. However, the Segment Anything Model (SAM) introduces a new prompt-driven paradigm for image segmentation, offering new possibilities. In this

Amit Kumar, Vaibhav Shekhar

This manuscript proposes a generalized inverse for a dual matrix called dual Drazin generalized inverse (DDGI) which generalizes the notion of the dual group generalized inverse (DGGI). Under certain necessary and sufficient conditions, we establish the existence of the DDGI of a dual matrix of any index. Thereafter, we show that the DDGI is unique (whenever

Chu-Kuan Jiang, Yang-Fan Deng, Hongxiao Guo, Guang-Hao Chen

Harvesting organic matter from wastewater is widely applied to maximize energy recovery; however, it limits the applicability of secondary treatment for acceptable effluent discharge into surface water bodies. To turn this bottleneck issue into an opportunity, this study developed oxygen-induced thiosulfatE production duRing sulfATe reductiOn (EARTO) to prov

Jean Roland Ebende Penda, Stéphane Bouka, Guy Martial Nkiet

This paper deals with variable selection in multivariate linear regression model when the data are observations on a spatial domain being a grid of sites in $\mathbb{Z}^d$ with $d\geqslant 2$. We use a criterion that allows to characterize the subset of relevant variables as depending on two parameters, and we propose estimators for these parameters based on

Yifan Wang, Hehi Xie

In this paper, we propose a type of tensor-neural-network-based machine learning method to compute multi-eigenpairs of high dimensional eigenvalue problems without Monte-Carlo procedure. Solving multi-eigenvalues and their corresponding eigenfunctions is one of the basic tasks in mathematical and computational physics. With the help of tensor neural network

Kwang Ho Kim, Sihem Mesnager, Ye Bong Kim

A substitution box (S-box) in a symmetric primitive is a mapping $F$ that takes $k$ binary inputs and whose image is a binary $m$-tuple for some positive integers $k$ and $m$, which is usually the only nonlinear element of the most modern block ciphers. Therefore, employing S-boxes with good cryptographic properties to resist various attacks is significant.

Jyotsna Singh, M. Ibrahim Mirza

Neutrino masses are yet unknown. We discuss the present state of effective electron anti-neutrino mass from $\beta$ decay experiments; effective Majorana neutrino mass from neutrinoless double-beta decay experiments; neutrino mass squared differences from neutrino oscillation: solar, atmospheric, reactor and accelerator based experiments; sum of neutrino mas

Crane He Chen

We introduce a novel approach for measuring the total curvature at every triangle of a discrete surface. This method takes advantage of the relationship between per triangle total curvature and the Dirichlet energy of the Gauss map. This new tool can be used on both triangle meshes and point clouds and has numerous applications. In this study, we demonstrate

Yifeng Zheng, Shuangqing Xu, Songlei Wang, Yansong Gao

Vertical federated learning (VFL) has recently emerged as an appealing distributed paradigm empowering multi-party collaboration for training high-quality models over vertically partitioned datasets. Gradient boosting has been popularly adopted in VFL, which builds an ensemble of weak learners (typically decision trees) to achieve promising prediction perfor

Puwasala Gamakumara, Edgar Santos-Fernandez, Priyanga Dilini Talagala, Rob J. Hyndman

Time series often reflect variation associated with other related variables. Controlling for the effect of these variables is useful when modeling or analysing the time series. We introduce a novel approach to normalize time series data conditional on a set of covariates. We do this by modeling the conditional mean and the conditional variance of the time se

Chunxu Zhang, Guodong Long, Tianyi Zhou, Zijian Zhang

Federated recommendation system usually trains a global model on the server without direct access to users' private data on their own devices. However, this separation of the recommendation model and users' private data poses a challenge in providing quality service, particularly when it comes to new items, namely cold-start recommendations in federated sett

Hongbin Lin, Mingkui Tan, Yifan Zhang, Zhen Qiu

Source-free Unsupervised Domain Adaptation (SF-UDA) aims to adapt a well-trained source model to an unlabeled target domain without access to the source data. One key challenge is the lack of source data during domain adaptation. To handle this, we propose to mine the hidden knowledge of the source model and exploit it to generate source avatar prototypes. T

Sheng Chen, Ziyang Zhang

Let k be a number field. For a variety X over k that satisfies weak approximation with Brauer-Manin obstruction, we study the same property for smooth projective models of its symmetric products. Based on the same method, we also explore the property of weak approximation with Brauer-Manin obstruction for norm varieties.

Kevin A. Fischer

This paper presents Reflective Linguistic Programming (RLP), a unique approach to conversational AI that emphasizes self-awareness and strategic planning. RLP encourages models to introspect on their own predefined personality traits, emotional responses to incoming messages, and planned strategies, enabling contextually rich, coherent, and engaging interact

Bowen Hu, Weiheng Yao, Sibo Qiao, Hieu Pham

In minimally-invasive brain surgeries with indirect and narrow operating environments, 3D brain reconstruction is crucial. However, as requirements of accuracy for some new minimally-invasive surgeries (such as brain-computer interface surgery) are higher and higher, the outputs of conventional 3D reconstruction, such as point cloud (PC), are facing the chal

Kwang Ho Kim, Sihem Mesnager, Chung Hyok Kim

Let $F(X)=X^{2^{2k}+2^k+1}$ be the power function over the finite field $\GF{2^{4k}}$ which is known as the Bracken-Leander function. In \cite{BCC10,BL10,CV20,Fu22,XY17}, it was proved that the number of solutions in $\GF{q^4}$ to the equation $F(X)+F(X+1)=b$ is in $\{0,2,4\}$ for any $b\in \GF{q^4}$ and the number of the $b$ giving $i$ solutions have been d

Hailiang Tang, Tisheng Zhang, Liqiang Wang, Guan Wang

The pose adjustment (PA) with a pose-only visual representation has been proven equivalent to the bundle adjustment (BA), while significantly improving the computational efficiency. However, the pose-only solution has not yet been properly considered in a tightly-coupled visual-inertial state estimator (VISE) with a normal configuration for real-time navigat

Binyan Jiang, Chenlei Leng, Ting Yan, Qiwei Yao

Dynamic network data analysis requires joint modelling individual snapshots and time dynamics. This paper proposes a new two-way heterogeneity model towards this goal. The new model equips each node of the network with two heterogeneity parameters, one to characterize the propensity of forming ties with other nodes and the other to differentiate the tendency

Rico K. L. Lo

Masked autoregressive flow (MAF) is a state-of-the-art non-parametric density estimation technique. It is based on the idea (known as a normalizing flow) that a simple base probability distribution can be mapped into a complicated target distribution that one wishes to approximate, using a sequence of bijective transformations. The denmarf package provides a

Zhenduo Zhao, Zhuo Li, Wenchao Wang, Pengyuan Zhang

This report describes our submission to track1 and track3 for VoxCeleb Speaker Recognition Challenge 2022(VoxSRC2022). Our best system achieves minDCF 0.1397 and EER 2.414 in track1, minDCF 0.388 and EER 7.030 in track3.

Abhinav Ramesh Kashyap, Thanh-Tung Nguyen, Viktor Schlegel, Stefan Winkler

Sentence representations are a critical component in NLP applications such as retrieval, question answering, and text classification. They capture the meaning of a sentence, enabling machines to understand and reason over human language. In recent years, significant progress has been made in developing methods for learning sentence representations, including

Lili Chen, Jingge Zhu, Jamie Evans

Graph Neural Networks (GNNs) have recently emerged as a promising approach to tackling power allocation problems in wireless networks. Since unpaired transmitters and receivers are often spatially distant, the distance-based threshold is proposed to reduce the computation time by excluding or including the channel state information in GNNs. In this paper, we

Michael Zanger-Tishler, Julian Nyarko, Sharad Goel

In designing risk assessment algorithms, many scholars promote a "kitchen sink" approach, reasoning that more information yields more accurate predictions. We show, however, that this rationale often fails when algorithms are trained to predict a proxy of the true outcome, as is typically the case. With such "label bias", one should exclude a feature if its

D. A. Pushin, C. Kapahi, A. E. Silva, D. G. Cory

The incorporation of structured light techniques into vision science has enabled more selective probes of polarization related entoptic phenomena. Diverse sets of stimuli have become accessible in which the spatially dependant optical properties can be rapidly controlled and manipulated. For example, past studies with human perception of polarization have de

Arjun Singh, Vitaly Petrov, Hichem Guerboukha, Innem V. A. K. Reddy

Terahertz (THz) band communications is envisioned as a key technology for future wireless standards. Substantial progress has been made in this field, with advances in hardware design, channel models, and signal processing. High-rate backhaul links operating at sub-THz frequencies have been experimentally demonstrated. However, there are inherent challenges

Tianyou Chen, Jin Xiao, Xiaoguang Hu, Guofeng Zhang

Camouflaged objects are typically assimilated into their backgrounds and exhibit fuzzy boundaries. The complex environmental conditions and the high intrinsic similarity between camouflaged targets and their surroundings pose significant challenges in accurately locating and segmenting these objects in their entirety. While existing methods have demonstrated