December 2024 arXiv papers — page 72

Zhipeng Wang, Rui Sun, Elizabeth Lui, Tuo Zhou

The rapid advancement of AI has underscored critical challenges in its development and implementation, largely due to centralized control by a few major corporations. This concentration of power intensifies biases within AI models, resulting from inadequate governance and oversight mechanisms. Additionally, it limits public involvement and heightens concerns

Takeru Utsugi, Nobuhiro Kusuno, Takuma Kuno, Noriyuki Lee

Temperature rise of qubits due to heating is a critical issue in large-scale quantum computers based on quantum-dot (QD) arrays. This leads to shorter coherence times, induced readout errors, and increased charge noise. Here, we propose a simple thermal circuit model to describe the heating effect on silicon QD array structures. Noting that the QD array is a

Ami M. Shirai, Yuta Murotani, Tomohiro Fujimoto, Natsuki Kanda

Sixfold-degenerate valleys in Si have attracted considerable attention for valleytronics application. Using optical pump-terahertz (THz) probe spectroscopy, we study the dynamics of valley polarization in bulk Si(001) at room temperature. Linearly polarized pump pulses excite electrons and holes with asymmetric distributions in momentum space, leading to in-

Xiaoyu Hu, Zhenhua Lin

Posterior drift refers to changes in the relationship between responses and covariates while the distributions of the covariates remain unchanged. In this work, we explore functional linear regression under posterior drift with transfer learning. Specifically, we investigate when and how auxiliary data can be leveraged to improve the estimation accuracy of t

K. S. Babu, Shaikh Saad

The Zee-Babu model is an economical framework for neutrino mass generation as two-loop quantum corrections. In this work, we present a UV completion of this model by embedding it into an $SU(5)$ unified framework. Interestingly, we find that loop-induced contributions to neutrino masses arising from colored scalars are just as important as those from color-n

Jintao Huang, Yiu-ming Cheung, Chi-man Vong, Wenbin Qian

Partial label learning (PLL) is a complicated weakly supervised multi-classification task compounded by class imbalance. Currently, existing methods only rely on inter-class pseudo-labeling from inter-class features, often overlooking the significant impact of the intra-class imbalanced features combined with the inter-class. To address these limitations, we

Nilanjana Kumar

The main aim of the the Large Hadron Collider (LHC) experiments is to search for exotic particles with masses in the TeV range as predicted by Beyond Standard Model (BSM) theories. However, there is no hint of BSM around TeV scale so far. Hence, it is possible that the exotic particles are heavier and larger centre of mass energy is needed to observe them. A

Shunlin Lu, Jingbo Wang, Zeyu Lu, Ling-Hao Chen

The scaling law has been validated in various domains, such as natural language processing (NLP) and massive computer vision tasks; however, its application to motion generation remains largely unexplored. In this paper, we introduce a scalable motion generation framework that includes the motion tokenizer Motion FSQ-VAE and a text-prefix autoregressive tran

Aloke Paul

The correlation between intrinsic and tracer diffusion coefficients considering the molar volume of the diffusing elements and cross phenomenological constants of Onsager contributing to the vacancy wind effect in ternary and multicomponent systems. Manning established this correlation assuming constant molar volume. The difference in data calculated conside

Kepu Zhang, Weijie Yu, Sunhao Dai, Jun Xu

In this paper, we propose CitaLaw, the first benchmark designed to evaluate LLMs' ability to produce legally sound responses with appropriate citations. CitaLaw features a diverse set of legal questions for both laypersons and practitioners, paired with a comprehensive corpus of law articles and precedent cases as a reference pool. This framework enables LLM

Ye Zhu, Xiaowen Gong

Federated reinforcement learning (FRL) has emerged as a promising paradigm, enabling multiple agents to collaborate and learn a shared policy adaptable across heterogeneous environments. Among the various reinforcement learning (RL) algorithms, the actor-critic (AC) algorithm stands out for its low variance and high sample efficiency. However, little to noth

Cuiyun Gao, Xing Hu, Shan Gao, Xin Xia

With the advent of large language models (LLMs) in the artificial intelligence (AI) area, the field of software engineering (SE) has also witnessed a paradigm shift. These models, by leveraging the power of deep learning and massive amounts of data, have demonstrated an unprecedented capacity to understand, generate, and operate programming languages. They c

Gaiane Panina, Timur Shamazov, Maksim Turevskii

The Milnor-Wood inequality states that if a (topological) oriented circle bundle over an orientable surface of genus $g$ has a smooth transverse foliation, then the Euler class of the bundle satisfies $$|\mathcal{E}|\leq 2g-2.$$ We give a new proof of the inequality based on a (previously proven by the authors) local formula which computes $\mathcal{E}$ from

Noriyoshi Fukaya

We study uniqueness and nondegeneracy of ground states for nonlinear scalar field equations in two dimensions with a point interaction at the origin. It is known that the all ground states are radial, positive, and decreasing functions. In this paper we prove the uniqueness of positive radial solutions by a method of Poho\v{z}aev identities. As a corollary,

Masaki Iwaya, Kazuya Kobayashi, Soichiro Morisaki, Kenta Hotokezaka

We derive an analytical form of the joint prior of effective spin parameters, $\chi_\mathrm{eff}$ and $\chi_\mathrm{p}$, assuming an isotropic and uniform-in-magnitude spin distribution. This is a vital factor in performing hierarchical Bayesian inference for studying the population properties of merging compact binaries observed with gravitational waves. In

M. Anzorena, E. de la Fuente, K. Fujita, R. Garcia

The Tibet AS$\gamma$ experiment successfully detected sub-PeV $\gamma$-rays from the Crab nebula using a Surface Array and underground muon detector. Considering this, we are building in Bolivia a new experiment to explore the Southern Hemisphere, looking for the origins of cosmic rays in our Galaxy. The name of this project is Andes Large area PArticle dete

Barak Budnick, Ofer Biham, Eytan Katzav

Analytical results are presented for the structure of networks that evolve via a preferential-attachment-random-deletion (PARD) model in the regime of overall network growth and in the regime of overall contraction. The phase transition between the two regimes is studied. At each time step a node addition and preferential attachment step takes place with pro

Saad Bin Mansoor

Invariant integration of vectors and tensors over manifolds was introduced around fifty years ago by V.N. Folomeshkin, though the concept has not attracted much attention among researchers. Although it is a sophisticated concept, the operation of the invariant integration of vectors is actually required to correctly solve some problems in mechanics. Two such

Xiaoning Dong, Wenbo Hu, Wei Xu, Tianxing He

Large language models (LLMs) have made significant advancements across various tasks, but their safety alignment remain a major concern. Exploring jailbreak prompts can expose LLMs' vulnerabilities and guide efforts to secure them. Existing methods primarily design sophisticated instructions for the LLM to follow, or rely on multiple iterations, which could

Goncalo Araujo-Regado, Philipp A. Hoehn, Francesco Sartini, Bilyana Tomova

Boundaries in gauge theory and gravity give rise to symmetries and charges at both finite and asymptotic distance. Due to their structural similarities, it is often held that soft modes are some kind of asymptotic limit of edge modes. Here, we show in Maxwell theory that there is an arguably more interesting relationship between the asymptotic symmetries and

Min Wang, Xin Huang, Guoqing Zhou, Qifeng Guo

Neural Radiance Fields (NeRFs) have demonstrated prominent performance in novel view synthesis. However, their input heavily relies on image acquisition under normal light conditions, making it challenging to learn accurate scene representation in low-light environments where images typically exhibit significant noise and severe color distortion. To address

Gui Wang, Yuexiang Li, Wenting Chen, Meidan Ding

Small lesions play a critical role in early disease diagnosis and intervention of severe infections. Popular models often face challenges in segmenting small lesions, as it occupies only a minor portion of an image, while down\_sampling operations may inevitably lose focus on local features of small lesions. To tackle the challenges, we propose a {\bf S}mall

Kamorudeen A. Amuda, Almustapha A. Wakili

This study introduces a federated learning-based approach to predict HER2 status from hematoxylin and eosin (HE)-stained whole slide images (WSIs), reducing costs and speeding up treatment decisions. To address label imbalance and feature representation challenges in multisite datasets, a point transformer is proposed, incorporating dynamic label distributio

Alexander Yosifov, Aditya Iyer, Daniel Ebler, Vlatko Vedral

Quantum homogenization is a reservoir-based quantum state approximation protocol, which has been successfully implemented in state transformation on quantum hardware. In this work we move beyond that and propose the homogenization as a novel platform for quantum state stabilization and information protection. Using the Heisenberg exchange interactions formal

Leo van Nierop

In particle physics, the fundamental forces are subject to symmetries called gauge invariance. It is a redundancy in the mathematical description of any physical system. In this article I will demonstrate that the transformer architecture exhibits the same properties, and show that the default representation of transformers has partially, but not fully remov

Fabo Feng, Guang-Yao Xiao, Hugh R. A. Jones, James S. Jenkins

The detection and constraint of the orbits of long-period giant planets is essential for enabling their further study through direct imaging. Recently, it has been highlighted that there are discrepancies between different orbital fitting solutions. We address these concerns by reanalyzing the data for HD 28185, GJ 229, HD 62364, HD 38529, 14 Her, eps Ind A,

Rodrigo M. Nunes, Ricardo L. S. Farias, William R. Tavares, Varese S. Timóteo

Evidences of vortical effects have been recently found by experiments in heavy ion collisions, instigating new insights into the phase diagram of quantum chromodynamics (QCD). Considering the effect of rotations, lattice QCD data shows that the temperatures for deconfinement and chiral symmetry restoration should increase with real angular velocity, and the

George T. Fleming, Graham D. Kribs, Ethan T. Neil, David Schaich

A new dark matter candidate is proposed that arises as the lightest baryon from a confining $SU(N)$ gauge theory which equilibrates with the Standard Model only through electroweak interactions. Surprisingly, this candidate can be as light as a few GeV. The lower bound arises from the intersection of two competing requirements: i) the equilibration sector of

Ran Lyu, Linhan Wang, Yanshen Sun, Hedanqiu Bai

Climate change is intensifying rainfall extremes, making high-resolution precipitation projections crucial for society to better prepare for impacts such as flooding. However, current Global Climate Models (GCMs) operate at spatial resolutions too coarse for localized analyses. To address this limitation, deep learning-based statistical downscaling methods o

Qimei Cui, Xiaohu You, Ni Wei, Guoshun Nan

With the growing demand for seamless connectivity and intelligent communication, the integration of artificial intelligence (AI) and sixth-generation (6G) communication networks has emerged as a transformative paradigm. By embedding AI capabilities across various network layers, this integration enables optimized resource allocation, improved efficiency, and

Qi Zheng, Zihao Yao, Yaying Zhang

Spatial-temporal forecasting is crucial and widely applicable in various domains such as traffic, energy, and climate. Benefiting from the abundance of unlabeled spatial-temporal data, self-supervised methods are increasingly adapted to learn spatial-temporal representations. However, it encounters three key challenges: 1) the difficulty in selecting reliabl

Yu Zhu, Bo Lei, Chunfeng Song, Wanli Ouyang

Elucidating the functional mechanisms of the primary visual cortex (V1) remains a fundamental challenge in systems neuroscience. Current computational models face two critical limitations, namely the challenge of cross-modal integration between partial neural recordings and complex visual stimuli, and the inherent variability in neural characteristics across

Xiaofei Huang, Wenting Chen, Jie Liu, Qisheng Lu

Medical report generation is crucial for clinical diagnosis and patient management, summarizing diagnoses and recommendations based on medical imaging. However, existing work often overlook the clinical pipeline involved in report writing, where physicians typically conduct an initial quick review followed by a detailed examination. Moreover, current alignme

Grgur Palle

In this thesis, we theoretically examine the pairing mechanisms and the identification of the pairing symmetry of unconventional superconductors whose normal states are correlated, multiband, or topological. In the first part, we investigate whether fluctuating intra-unit-cell loop currents can drive unconventional superconductivity. For general systems, we

Ashish Chouhan, Saifeldin Mandour, Michael Gertz

Exploring large-scale text corpora presents a significant challenge in biomedical, finance, and legal domains, where vast amounts of documents are continuously published. Traditional search methods, such as keyword-based search, often retrieve documents in isolation, limiting the user's ability to easily inspect corpus-wide trends and relationships. We prese

Shirui Bian, Zezhou Wang, Siyang Leng, Wei Lin

Early-warning signals of delicate design are always used to predict critical transitions in complex systems, which makes it possible to render the systems far away from the catastrophic state by introducing timely interventions. Traditional signals including the dynamical network biomarker (DNB), based on statistical properties such as variance and autocorre

Mendel Nguyen, Mithat Ünsal

We consider a class of 3d theories with a $\mathbb Z_n$ magnetic symmetry in which confinement is generated by charge $n$ clusters of monopoles. Such theories naturally arise in quantum antiferromagnets in 2+1, QCD-like theories on $\mathbb R^3 \times S^1$, and $U(1)$ lattice theory with restricted monopole sums. A confining string fractionates into $n$ stri

Mingdeng Cao, Chong Mou, Ziyang Yuan, Xintao Wang

Consistent human-centric image and video synthesis aims to generate images or videos with new poses while preserving appearance consistency with a given reference image, which is crucial for low-cost visual content creation. Recent advances based on diffusion models typically rely on separate networks for reference appearance feature extraction and target vi

Touqeer Anwar Kashif, Janardhanraj Subburaj, Md Zafar Ali Khan, Aamir Farooq

Shock tubes have become indispensable tools for advancing research across diverse fields such as aerodynamics, astrophysics, chemical kinetics, and industrial applications. The present study examines shock velocity variations in double-diaphragm shock tubes and their impact on flow dynamics at the end of the shock tube. Experiments were conducted using heliu

Arash Peik, Mohammad Ali Zare Chahooki, Amin Milani Fard, Mehdi Agha Sarram

Organizing and managing cryptocurrency portfolios and decision-making on transactions is crucial in this market. Optimal selection of assets is one of the main challenges that requires accurate prediction of the price of cryptocurrencies. In this work, we categorize the financial time series into several similar subseries to increase prediction accuracy by l

Xiao Cui, Mo Zhu, Yulei Qin, Liang Xie

Knowledge distillation (KD) has become a prevalent technique for compressing large language models (LLMs). Existing KD methods are constrained by the need for identical tokenizers (i.e., vocabularies) between teacher and student models, limiting their versatility in handling LLMs of different architecture families. In this paper, we introduce the Multi-Level

Alex Mak, Shubham Sahoo, Shivani Pandey, Yidan Yue

Class imbalance and distributional differences in large datasets present significant challenges for classification tasks machine learning, often leading to biased models and poor predictive performance for minority classes. This work introduces two novel undersampling approaches: mutual information-based stratified simple random sampling and support points o

Sukrit Leelaluk, Cheng Tang, Valdemar Švábenský, Atsushi Shimada

Educational data mining (EDM) is a part of applied computing that focuses on automatically analyzing data from learning contexts. Early prediction for identifying at-risk students is a crucial and widely researched topic in EDM research. It enables instructors to support at-risk students to stay on track, preventing student dropout or failure. Previous studi

Emil Polisensky, Tracy E. Clarke, Simona Giacintucci, Wendy Peters

Accurate primary beam calibration is essential for precise brightness measurements in radio astronomy. The VLA Low-band Ionosphere and Transient Experiment (VLITE) faces challenges in calibration due to the offset Cassegrain optics used in its commensal observing system. This study aims to develop a novel calibration method to improve accuracy with no impact

Chen Ran, Zhang xiaowen

We denote a path on $t$ vertices as $P_t$ and a cycle on $t$ vertices as $C_t$. For two vertex-disjoint graphs $G_1$ and $G_2$, the {\em union} $G_1\cup G_2$ is the graph with $V(G_1\cup G_2)=V(G_1)\cup V(G_2)$ and $E(G_1\cup G_2)=E(G_1)\cup E(G_2)$. A {\em diamond} (resp. {\em gem}) is a graph consisting of a $P_3$ (resp. $P_4$) and a new vertex adjacent to

Yanqiao Deng, Minda Ma, Nan Zhou, Chenchen Zou

National carbon peak track and optimized provincial carbon allocations are crucial for mitigating regional inequality within the commercial building sector during China's transition to carbon neutrality. This study proposes a top-down model to evaluate carbon trajectories in operational commercial buildings up to 2060. Through Monte Carlo simulation, scenari

Runsheng Zhang, Shixiao Wang, Tianfang Xie, Shiyu Duan

This study presents a novel approach for intelligent user interaction interface generation and optimization, grounded in the variational autoencoder (VAE) model. With the rapid advancement of intelligent technologies, traditional interface design methods struggle to meet the evolving demands for diversity and personalization, often lacking flexibility in rea

Hiroyuki Chihara

We study the structure of normal operators of double fibration transforms with conjugate points. Examples of double fibration transforms include Radon transforms, $d$-plane transforms on the Euclidean space, geodesic X-ray transforms, light-ray transforms, and ray transforms defined by null bicharacteristics associated with real principal type operators. We

Shahrzad Haji Amin Shirazi, Xikui Wang, Michael J. Carey, Vassilis J. Tsotras

Within the dynamic world of Big Data, traditional systems typically operate in a passive mode, processing and responding to user queries by returning the requested data. However, this methodology falls short of meeting the evolving demands of users who not only wish to analyze data but also to receive proactive updates on topics of interest. To bridge this g

Jinpeng Wang, Niu Lian, Jun Li, Yuting Wang

Self-supervised video hashing (SSVH) is a practical task in video indexing and retrieval. Although Transformers are predominant in SSVH for their impressive temporal modeling capabilities, they often suffer from computational and memory inefficiencies. Drawing inspiration from Mamba, an advanced state-space model, we explore its potential in SSVH to achieve

Pei-Bin Chen, Junfeng Wang, Tian-Wen Cao, Mengting Shen

As one type of blue early-type galaxies, the evolutionary history and fate of star-forming lenticular galaxies (S0s) remain elusive. We selected 134 star-forming S0s from the SDSS-IV MaNGA survey and found that they have steep and warped size-mass relations, similar to quiescent S0s and red spirals, indicating that they may have similar gas dissipation scena

Teng Xiao, Yige Yuan, Huaisheng Zhu, Mingxiao Li

We study the problem of aligning large language models (LLMs) with human preference data. Contrastive preference optimization has shown promising results in aligning LLMs with available preference data by optimizing the implicit reward associated with the policy. However, the contrastive objective focuses mainly on the relative values of implicit rewards ass

Ziyang Li, Jiani Huang, Jason Liu, Felix Zhu

Foundation models have vast potential to enable diverse AI applications. The powerful yet incomplete nature of these models has spurred a wide range of mechanisms to augment them with capabilities such as in-context learning, information retrieval, and code interpreting. We propose Vieira, a declarative framework that unifies these mechanisms in a general so

Abdul Wahab, Muqaddar Abbas, Xiaosen Yang, Yuee Xie

In this research, we investigate second-order sideband generation (SSG) and slow-fast light using a hybrid system comprised of two coupled opto- and magnomechanical microspheres, namely a YIG sphere and a silica sphere. The YIG sphere hosts a magnon mode and a vibration mode induced by magnetostriction, whereas the silica sphere has an optical whispering gal

Yingzhou Mou, Yukio Hayashi

Local communities by concentration of nodes connected with short links are widely observed in spatial networks. However, how such structure affects robustness of connectivity against malicious attacks remains unclear. This study investigates the impact of local communities on the robustness by modeling planar infrastructure reveals that the robustness is wea

Datong Zhou

We study a non-exchangeable multi-agent system and rigorously derive a strong form of the mean-field limit. The convergence of the connection weights and the initial data implies convergence of large-scale dynamics toward a deterministic limit given by the corresponding extended Vlasov PDE, at any later time and any realization of randomness. This is establi

Sen Yang, Xiaofeng Li

Piezoelectric fast steering mirrors (PFSM) are widely utilized in beam precision-pointing systems but encounter considerable challenges in achieving high-precision tracking of fast trajectories due to nonlinear hysteresis and mechanical dual-axis cross-coupling. This paper proposes a model predictive control (MPC) approach integrated with a hysteresis invers

Jiayi Wu, Hengyi Cai, Lingyong Yan, Hao Sun

The emergence of Retrieval-augmented generation (RAG) has alleviated the issues of outdated and hallucinatory content in the generation of large language models (LLMs), yet it still reveals numerous limitations. When a general-purpose LLM serves as the RAG generator, it often suffers from inadequate response informativeness, response robustness, and citation

Shizhan Gong, Jingwei Zhang, Qi Dou, Farzan Farnia

Saliency maps are widely used in the computer vision community for interpreting neural network classifiers. However, due to the randomness of training samples and optimization algorithms, the resulting saliency maps suffer from a significant level of stochasticity, making it difficult for domain experts to capture the intrinsic factors that influence the neu

Huynh Anh N. Le, Yongquan Xue

We analyzed a sample of $\sim$113,000 galaxies ($\rm z < 0.3$) from the Sloan Digital Sky Survey, divided into star-forming, composite, Seyfert, and LINER types, to explore the relationships between UV-to-optical colors ($\rm u-r$), star formation rates (SFRs), specific star formation rates (sSFRs), stellar velocity dispersions ($\rm \sigma_{*}$), mass accre

Jared Popowski, Lucas Warma, Alicia Abarca Cifuentes, Petra Bleeker

Trichomes, specialized hair-like structures on the surfaces of many plants, play a crucial role in defense against herbivorous insects. We investigated the biomechanics of type VI glandular trichomes in cultivated tomato (Solanum lycopersicum) and its wild relative (Solanum habrochaites). Using micropipette force sensors and high-speed imaging, we uncovered

Felipe Lara, Cristian Vega

We study non-convex delayed-noise online optimization problems by evaluating dynamic regret in the non-stationary setting when the loss functions are quasar-convex. In particular, we consider scenarios involving quasar-convex functions either with a Lipschitz gradient or weakly smooth and, for each case, we ensure bounded dynamic regret in terms of cumulativ

Mingxin Li, Yizhen Yu, Ning Wang, Zhigang Wang

Recently machine unlearning (MU) is proposed to remove the imprints of revoked samples from the already trained model parameters, to solve users' privacy concern. Different from the runtime expensive retraining from scratch, there exist two research lines, exact MU and approximate MU with different favorites in terms of accuracy and efficiency. In this paper

Wenhao He, Zhibin Lu

Inspired by the principle of equal probability proposed by Boltzmann in the 1870s, we establish a theoretical framework for the most probable distribution of meta-structures in materials. Furthermore, we validate the reliability of this theoretical framework based on statistical results of these meta-structures within randomly generated binary alloys. Finall

Diego Mollá, Qiongkai Xu, Zijie Zeng, Zhuang Li

The ALTA shared tasks have been running annually since 2010. In 2024, the purpose of the task is to detect machine-generated text in a hybrid setting where the text may contain portions of human text and portions machine-generated. In this paper, we present the task, the evaluation criteria, and the results of the systems participating in the shared task.

Kevin Eng, Jordan A. Awan, Nianqiao Phyllis Ju, Vinayak A. Rao

This paper serves as a reference and introduction to using the R package dapper. dapper encodes a sampling framework which allows exact Markov chain Monte Carlo simulation of parameters and latent variables in a statistical model given privatized data. The goal of this package is to fill an urgent need by providing applied researchers with a flexible tool to

O. Ivy Wong, A. F. Garon, M. J. Alger, L. Rudnick

Radio galaxies can extend far beyond the stellar component of their originating host galaxies, and their radio emission can consist of multiple discrete components. Furthermore, the apparent source structure will depend on survey sensitivity, resolution and the observing frequency. Associated discrete radio components and their originating host galaxy are ty

Yuzuki Arai, Sho Tsugawa

The emergence of large language models (LLMs) such as ChatGPT and Claude presents new challenges for philosophy of language, particularly regarding the nature of linguistic meaning and representation. While LLMs have traditionally been understood through distributional semantics, this paper explores Robert Brandom's inferential semantics as an alternative fo

David M. Bossens, Shanshan Feng, Yew-Soon Ong

As AI systems are integrated into social networks, there are AI safety concerns that AI-generated content may dominate the web, e.g. in popularity or impact on beliefs. To understand such questions, this paper proposes the Digital Ecosystem of Beliefs (Digico), the first evolutionary framework for controlled experimentation with multi-population interactions

Xin Yang, Omid Ardakanian

Sensor data collected by Internet of Things (IoT) devices can reveal sensitive personal information about individuals, raising significant privacy concerns when shared with semi-trusted service providers, as they may extract this information using machine learning models. Data obfuscation empowered by generative models is a promising approach to generate syn

Sophie Dvali, Caio Seguin, Richard Betzel, Andrew M. Leifer

The connectome describes the complete set of synaptic contacts through which neurons communicate. While the architecture of the $\textit{C. elegans}$ connectome has been extensively characterized, much less is known about the organization of causal signaling networks arising from functional interactions between neurons. Understanding how effective communicat

Di Fan, Renlei Jiang, Yunhao Wen, Chuanhou Gao

Treatment effect estimation from observational data has attracted significant attention across various research fields. However, many widely used methods rely on the unconfoundedness assumption, which is often unrealistic due to the inability to observe all confounders, thereby overlooking the influence of latent confounders. To address this limitation, rece

Ma Zhuoqi, Zhang Yixuan, You Zejun, Tian Long

Artistic image stylization aims to render the content provided by text or image with the target style, where content and style decoupling is the key to achieve satisfactory results. However, current methods for content and style disentanglement primarily rely on image supervision, which leads to two problems: 1) models can only support one modality for style

Kishu Gupta, Deepika Saxena, Rishabh Gupta, Jatinder Kumar

Cloud computing is flourishing at a rapid pace. Significant consequences related to data security appear as a malicious user may get unauthorized access to sensitive data which may be misused, further. This raises an alarm-ringing situation to tackle the crucial issue related to data security and proactive malicious user prediction. This article proposes a F

Chuang Lin, Bingbing Zhuang, Shanlin Sun, Ziyu Jiang

The recent advent of large-scale 3D data, e.g. Objaverse, has led to impressive progress in training pose-conditioned diffusion models for novel view synthesis. However, due to the synthetic nature of such 3D data, their performance drops significantly when applied to real-world images. This paper consolidates a set of good practices to finetune large pretra

Quanguo Zhang

In this paper, we study the nonexistence of global weak solutions for a wave equation with nonlinear memory and damping terms. We give an answer to an open problem posed in [M. D'Abbicco, A wave equation with structural damping and nonlinear memory, Nonlinear Differ. Equ. Appl. 21 (2014), 751-773]. Moreover, comparing with the existing results, our results d

Abdullah Khan, Rahul Nahar, Hao Chen, Gonzalo E. Constante Flores

Machine learning algorithms are increasingly being applied to fault detection and diagnosis (FDD) in chemical processes. However, existing data-driven FDD platforms often lack interpretability for process operators and struggle to identify root causes of previously unseen faults. This paper presents FaultExplainer, an interactive tool designed to improve fau

Ken Ueno, Makoto Kogo, Hiromi Kawatsu, Yohsuke Uchiumi

AI-agility, with which an organization can be quickly adapted to its business priorities, is desired even for the development and operations of generative AI (GenAI) applications. Especially in this paper, we discuss so-called GenAI Model-agility, which we define as the readiness to be flexibly adapted to base foundation models as diverse as the model provid

Yuta Kawakami, Jin Tian

Probabilities of causation (PoC) offer valuable insights for informed decision-making. This paper introduces novel variants of PoC-controlled direct, natural direct, and natural indirect probability of necessity and sufficiency (PNS). These metrics quantify the necessity and sufficiency of a treatment for producing an outcome, accounting for different causal

Kishu Gupta, Deepika Saxena, Rishabh Gupta, Ashutosh Kumar Singh

With the vigorous development of cloud computing, most organizations have shifted their data and applications to the cloud environment for storage, computation, and sharing purposes. During storage and data sharing across the participating entities, a malicious agent may gain access to outsourced data from the cloud environment. A malicious agent is an entit

Shu Shen, C. L. Philip Chen, Tong Zhang

Multimodal machine learning has achieved remarkable progress in many scenarios, but its reliability is undermined by varying sample quality. This paper finds that existing reliable multimodal classification methods not only fail to provide robust estimation of data quality, but also lack dynamic networks for sample-specific depth and parameters to achieve re

Chuan He

In this paper, we consider an unconstrained stochastic optimization problem where the objective function exhibits high-order smoothness. Specifically, we propose a new stochastic first-order method (SFOM) with multi-extrapolated momentum, in which multiple extrapolations are performed in each iteration, followed by a momentum update based on these extrapolat

Jihao Gu, Yingyao Wang, Meng Cao, Pi Bu

Direct Preference Optimization (DPO) has been demonstrated to be highly effective in mitigating hallucinations in Large Vision Language Models (LVLMs) by aligning their outputs more closely with human preferences. Despite the recent progress, existing methods suffer from two drawbacks: 1) Lack of scalable token-level rewards; and 2) Neglect of visual-anchore

Amandeep Kaur, James R. Wallace

Social media constitutes a rich and influential source of information for qualitative researchers. Although computational techniques like topic modelling assist with managing the volume and diversity of social media content, qualitative researcher's lack of programming expertise creates a significant barrier to their adoption. In this paper we explore how BE

Suwei Yang, Kuldeep S. Meel

Model counting is a fundamental task that involves determining the number of satisfying assignments to a logical formula, typically in conjunctive normal form (CNF). While CNF model counting has received extensive attention over recent decades, interest in Pseudo-Boolean (PB) model counting is just emerging partly due to the greater flexibility of PB formula

Chiang-Mei Chen, Rituparna Mandal, Nobuyoshi Ohta

We examine Friedmann-Lema\^itre-Robertson-Walker cosmology, incorporating quantum gravitational corrections through the functional renormalization group flow of the effective action for gravity. We solve the Einstein equation with quantum improved coupling perturbatively including the case with non-vanishing classical cosmological constant (CC) which was ove

Kunpeng Song, Tingbo Hou, Zecheng He, Haoyu Ma

In this paper, we introduce DirectorLLM, a novel video generation model that employs a large language model (LLM) to orchestrate human poses within videos. As foundational text-to-video models rapidly evolve, the demand for high-quality human motion and interaction grows. To address this need and enhance the authenticity of human motions, we extend the LLM f

Jun-Jie Zhang, Jiahao Song, Xiu-Cheng Wang, Fu-Peng Li

We uncover a phenomenon largely overlooked by the scientific community utilizing AI: neural networks exhibit high susceptibility to minute perturbations, resulting in significant deviations in their outputs. Through an analysis of five diverse application areas -- weather forecasting, chemical energy and force calculations, fluid dynamics, quantum chromodyna

Dylan Grigg, Steven Tingay, Steve Prabu, Marcin Sokolowski

With the low Earth orbit environment becoming increasingly populated with artificial satellites, rockets, and debris, it is important to understand the effects they have on radio astronomy. In this work, we undertake a multi-frequency, multi-epoch survey with two SKA-Low station prototypes located at the SKA-Low site, to identify and characterise radio frequ

Zihang Zhao, Wanlin Li, Yuyang Li, Tengyu Liu

Developing robotic hands that adapt to real-world dynamics remains a fundamental challenge in robotics and machine intelligence. Despite significant advances in replicating human hand kinematics and control algorithms, robotic systems still struggle to match human capabilities in dynamic environments, primarily due to inadequate tactile feedback. To bridge t

Luka Ugaya Mazza, Plinio Morita, James R. Wallace

Computational thematic analysis is rapidly emerging as a method of using large text corpora to understand the lived experience of people across the continuum of health care: patients, practitioners, and everyone in between. However, many qualitative researchers do not have the necessary programming skills to write machine learning code on their own, but also

Saumya Saxena, Blake Buchanan, Chris Paxton, Peiqi Liu

In Embodied Question Answering (EQA), agents must explore and develop a semantic understanding of an unseen environment to answer a situated question with confidence. This problem remains challenging in robotics, due to the difficulties in obtaining useful semantic representations, updating these representations online, and leveraging prior world knowledge f

Zihan Chang, Sheng Xiao, Shuibing He, Siling Yang

Existing work only effective on a given number of GPUs, often neglecting the complexities involved in manually determining the specific types and quantities of GPUs needed, which can be a significant burden for developers. To address this issue, we propose Frenzy, a memory-aware serverless computing method for heterogeneous GPU clusters. Frenzy allows users

Hongyu Du, Andrew Leroux

We propose two novel approaches for estimating time-varying effects of functional predictors within a linear functional Cox model framework. This model allows for time-varying associations of a functional predictor observed at baseline, estimated using penalized regression splines for smoothness across the functional domain and event time. The first approach

Zhendong Liu, Le Zhang, Bing Li, Yingjie Zhou

We address the challenge of WiFi-based temporal activity detection and propose an efficient Dual Pyramid Network that integrates Temporal Signal Semantic Encoders and Local Sensitive Response Encoders. The Temporal Signal Semantic Encoder splits feature learning into high and low-frequency components, using a novel Signed Mask-Attention mechanism to emphasiz

Yeo Jin Jung, Claire Donnat

We address the challenge of incorporating document-level metadata into topic modeling to improve topic mixture estimation. To overcome the computational complexity and lack of theoretical guarantees in existing Bayesian methods, we extend probabilistic latent semantic indexing (pLSI), a frequentist framework for topic modeling, by incorporating document-leve

Yabo Yin, Xiaofei Zhu, Wenshan Wang, Yihao Zhang

Multi-behavior recommendation (MBR) has garnered growing attention recently due to its ability to mitigate the sparsity issue by inferring user preferences from various auxiliary behaviors to improve predictions for the target behavior. Although existing research on MBR has yielded impressive results, they still face two major limitations. First, previous me

Junjie Zhou, Zheng Liu, Ze Liu, Shitao Xiao

Despite the rapidly growing demand for multimodal retrieval, progress in this field remains severely constrained by a lack of training data. In this paper, we introduce MegaPairs, a novel data synthesis method that leverages vision language models (VLMs) and open-domain images, together with a massive synthetic dataset generated from this method. Our empiric

Shange Tang, Jiayun Wu, Jianqing Fan, Chi Jin

Benign overfitting refers to the phenomenon where an over-parameterized model fits the training data perfectly, including noise in the data, but still generalizes well to the unseen test data. While prior work provides some theoretical understanding of this phenomenon under the in-distribution setup, modern machine learning often operates in a more challengi

Kunming Tang, Zhiguo Jiang, Jun Shi, Wei Wang

Gigapixel image analysis, particularly for whole slide images (WSIs), often relies on multiple instance learning (MIL). Under the paradigm of MIL, patch image representations are extracted and then fixed during the training of the MIL classifiers for efficiency consideration. However, the invariance of representations makes it difficult to perform data augme