February 2025 arXiv papers — page 18

Heng Lu, Chen Yang, Ce Zhang, YuBin Zhang

Manipulating two-dimensional materials occasionally results in crumpled membranes. Their complicated morphologies feature an abundance of folds, creases and wrinkles that make each crumpled membrane unique. Here, we prepare four nanomechanical resonators based on crumpled membranes of few-layer graphene and measure their static response and the spectrum of t

Keito Suzuki, Bang Du, Girish Krishnan, Kunyao Chen

3D part segmentation is still an open problem in the field of 3D vision and AR/VR. Due to limited 3D labeled data, traditional supervised segmentation methods fall short in generalizing to unseen shapes and categories. Recently, the advancement in vision-language models' zero-shot abilities has brought a surge in open-world 3D segmentation methods. While the

Aayush Dhakal, Srikumar Sastry, Subash Khanal, Adeel Ahmad

The choice of representation for geographic location significantly impacts the accuracy of models for a broad range of geospatial tasks, including fine-grained species classification, population density estimation, and biome classification. Recent works like SatCLIP and GeoCLIP learn such representations by contrastively aligning geolocation with co-located

Ronan Smith, Charlotte Thomas, Phan Nguyen, Arash Badiei

Objective: Endobronchial Valves are a minimally invasive treatment for emphysema. After bronchoscopic placement the valves reduce the flow of air into targeted areas of the lung, causing collapse, and allowing the remainder of the lung to function more effectively. Approach: X-ray Velocimetry is a novel method that uses X-ray images taken during a breath to

Peilin Wu, Xinlu Zhang, Wenhao Yu, Xingyu Liu

Recent advancements in Retrieval-Augmented Language Models (RALMs) have demonstrated their efficacy in knowledge-intensive tasks. However, existing evaluation benchmarks often assume a single optimal approach to leveraging retrieved information, failing to account for varying user needs. This paper introduces a novel evaluation framework that systematically

Shohei Kiryu, Kosuke Fukui, Atsushi Okamoto, Akihisa Tomita

In recent years, squeezed cat codes with resilience to specific types of loss have been proposed as a step toward realizing fault-tolerant optical quantum computers. However, error correction for squeezed cat codes requires a strong nonlinearity, which makes its implementation challenging with current technology. We propose a novel hybrid code that combines

Shuchang Zhou, Jiwei Wei, Shiyuan He, Yuyang Zhou

Prompt tuning has become a popular strategy for adapting Vision-Language Models (VLMs) to zero/few-shot visual recognition tasks. Some prompting techniques introduce prior knowledge due to its richness, but when learnable tokens are randomly initialized and disconnected from prior knowledge, they tend to overfit on seen classes and struggle with domain shift

R. Abbasi, M. Ackermann, J. Adams, S. K. Agarwalla

IceCube has observed a diffuse astrophysical neutrino flux over the energy region from a few TeV to a few PeV. At PeV energies, the spectral shape is not yet well measured due to the low statistics of the data. This analysis probes the gap between 1 PeV and 10 PeV by using high-energy downgoing muon neutrinos. To reject the large atmospheric muon background,

Meng-Lin Du, Feng-Kun Guo, Bing Wu

The validity range of the widely used traditional effective range expansion can be severely limited by the presence of a left-hand cut near the two-particle threshold. Such a left-hand cut emerges in two-particle scattering processes involving either a light particle exchange in the $t$-channel or a particle exchange with a mass slightly heavier than the mas

Nevidu Jayatilleke, Ruvan Weerasinghe, Nipuna Senanayake

The substantial growth of textual content in diverse domains and platforms has led to a considerable need for Automatic Text Summarization (ATS) techniques that aid in the process of text analysis. The effectiveness of text summarization models has been significantly enhanced in a variety of technical domains because of advancements in Natural Language Proce

Frederico P. Delgado, Frederico Simões, Leeor Kronik, Waldemar Kaiser

The spectacular performance of halide perovskites in optoelectronic devices is rooted in their tolerance to defects. Previous studies showed that defects in these materials generate shallow electronic states. However, how these shallow states persist amid the pronounced atomic dynamics on halide perovskite surfaces remains unknown. This work reveals that ele

Zhihua Duan, Jialin Wang

Integrating the structural inductive biases of Graph Neural Networks (GNNs) with the global contextual modeling capabilities of Transformers represents a pivotal challenge in graph representation learning. While GNNs excel at capturing localized topological patterns through message-passing mechanisms, their inherent limitations in modeling long-range depende

Kehan Sheng, Frank A. M. Tuyttens, Marina A. G. von Keyserlingk

Generative AI (e.g., ChatGPT) is increasingly integrated into people's daily lives. While it is known that AI perpetuates biases against marginalized human groups, their impact on non-human animals remains understudied. We found that ChatGPT's text-to-image model (DALL-E 3) introduces a strong bias toward romanticizing livestock farming as dairy cows on past

Weiqi Wang, Zhiyi Tian, An Liu, Shui Yu

With the increasing prevalence of Web-based platforms handling vast amounts of user data, machine unlearning has emerged as a crucial mechanism to uphold users' right to be forgotten, enabling individuals to request the removal of their specified data from trained models. However, the auditing of machine unlearning processes remains significantly underexplor

Elkhan Ismayilzada, MD Khalequzzaman Chowdhury Sayem, Yihalem Yimolal Tiruneh, Mubarrat Tajoar Chowdhury

Significant advancements have been achieved in the realm of understanding poses and interactions of two hands manipulating an object. The emergence of augmented reality (AR) and virtual reality (VR) technologies has heightened the demand for real-time performance in these applications. However, current state-of-the-art models often exhibit promising results

Genghua Dong, Henrik Boström, Michalis Vazirgiannis, Roman Bresson

Most techniques for explainable machine learning focus on feature attribution, i.e., values are assigned to the features such that their sum equals the prediction. Example attribution is another form of explanation that assigns weights to the training examples, such that their scalar product with the labels equals the prediction. The latter may provide valua

C. -J. David Lin, Ed Bennett, Niccolò Forzano, Deog Ki Hong

Investigation of composite Higgs models (CHMs) is of importance in contemporary particle physics. In this article, we present lattice computations of the chimera baryon masses in $Sp(4)$ gauge theory with two and three Dirac flavours of hyperquarks (beyond the Standard Model fermions coupled to the $Sp(4)$ gauge fields) in the fundamental and antisymmetric r

Jisoo Lee, Tamim Ahmed, Thanassis Rikakis, Pavan Turaga

Rehabilitation is essential and critical for post-stroke patients, addressing both physical and cognitive aspects. Stroke predominantly affects older adults, with 75% of cases occurring in individuals aged 65 and older, underscoring the urgent need for tailored rehabilitation strategies in aging populations. Despite the critical role therapists play in evalu

Che Hyun Lee, Heeseung Kim, Jiheum Yeom, Sungroh Yoon

We propose EdiText, a controllable text editing method that modifies the reference text to desired attributes at various scales. We integrate an SDEdit-based editing technique that allows for broad adjustments in the degree of text editing. Additionally, we introduce a novel fine-level editing method based on self-conditioning, which allows subtle control of

Yankun Huang, Qihang Lin, Yangyang Xu

In this paper, we investigate how structural properties of the constraint system impact the oracle complexity of smooth non-convex optimization problems with convex inequality constraints over a simple polytope. In particular, we show that, under a local error bound condition with exponent $d\in[1,2]$ on constraint functions, an inexact Moreau envelope Lagra

Chen Gao, Kai-Ming Ho, Renata M. Wentzcovitch, Yang Sun

Metastable phases can lead to multistep nucleation processes, influencing the liquid-to-solid transition in various systems. In this study, we investigate the homogeneous nucleation of iron's crystalline phases under Earth's inner core conditions, employing two previously developed interatomic potentials. We compare the thermodynamic and kinetic properties o

Yeunhwan Lim, Jeremy W. Holt

We investigate the influence of the nuclear symmetry energy and its density slope parameter on the neutron dripline and neutron star properties using a semi-classical liquid drop model (LDM) and energy density functionals constrained by chiral effective field theory. To analyze finite nuclei and mass tables, the nuclear symmetry energy at saturation density

Qinxia Wang, Yukang Liang, Zhihui Wang, Shijun Guan

It has been demonstrated that the Rydberg criticality in a many-body atomic system can enhance the measurement sensitivity of the microwave electric field by increasing the Fisher information. In our previous work, we proposed and experimentally verified that the Fisher information near the critical point can be increased by more than two orders of magnitude

Kiranmayee Janardhan, Christy Bobby T

Brain tumor diagnosis is a challenging task for clinicians in the modern world. Among the major reasons for cancer-related death is the brain tumor. Gliomas, a category of central nervous system (CNS) tumors, encompass diverse subregions. For accurate diagnosis of brain tumors, precise segmentation of brain images and quantitative analysis are required. A fu

Heeseung Kim, Che Hyun Lee, Sangkwon Park, Jiheum Yeom

Recent advancements in multi-turn voice interaction models have improved user-model communication. However, while closed-source models effectively retain and recall past utterances, whether open-source models share this ability remains unexplored. To fill this gap, we systematically evaluate how well open-source interaction models utilize past utterances usi

Ashkan Soleymani, Behrooz Tahmasebi, Stefanie Jegelka, Patrick Jaillet

We study the statistical-computational trade-offs for learning with exact invariances (or symmetries) using kernel regression. Traditional methods, such as data augmentation, group averaging, canonicalization, and frame-averaging, either fail to provide a polynomial-time solution or are not applicable in the kernel setting. However, with oracle access to the

Anthony Etim, Jakub Szefer

Adversarial attacks on machine learning models often rely on small, imperceptible perturbations to mislead classifiers. Such strategy focuses on minimizing the visual perturbation for humans so they are not confused, and also maximizing the misclassification for machine learning algorithms. An orthogonal strategy for adversarial attacks is to create perturba

Nathan Roll

Large language models (LLMs) showcase increasingly impressive English benchmark scores, however their performance profiles remain inconsistent across multilingual settings. To address this gap, we introduce PolyPrompt, a novel, parameter-efficient framework for enhancing the multilingual capabilities of LLMs. Our method learns a set of trigger tokens for eac

Hugo Lyons Keenan, Sarah Erfani, Christopher Leckie

Effective out-of-distribution (OOD) detection is crucial for the safe deployment of machine learning models in real-world scenarios. However, recent work has shown that OOD detection methods are vulnerable to adversarial attacks, potentially leading to critical failures in high-stakes applications. This discovery has motivated work on robust OOD detection me

Xingyu Qiu, Mengying Yang, Xinghua Ma, Fanding Li

In image generation, Schr\"odinger Bridge (SB)-based methods theoretically enhance the efficiency and quality compared to the diffusion models by finding the least costly path between two distributions. However, they are computationally expensive and time-consuming when applied to complex image data. The reason is that they focus on fitting globally optimal

Riku Higa

We propose a construction of lattices from codes corresponding to lattices of type $A_n$, $D_n$ and $E_n$. This construction is a generalization of construction A of lattices from $p$-ary codes corresponding to a lattice of type $A_{p-1}$. Moreover, we introduce some examples of application of lattices from the construction to Hilbert modular form.

Pei-Yau Weng, Minh Hoang, Lam M. Nguyen, My T. Thai

Fine-tuning pre-trained models is a popular approach in machine learning for solving complex tasks with moderate data. However, fine-tuning the entire pre-trained model is ineffective in federated data scenarios where local data distributions are diversely skewed. To address this, we explore integrating federated learning with a more effective prompt-tuning

Jiaxing Li, Lin Jiang, Zeqi Ma, Kaihang Jiang

Deep online cross-modal hashing has gained much attention from researchers recently, as its promising applications with low storage requirement, fast retrieval efficiency and cross modality adaptive, etc. However, there still exists some technical hurdles that hinder its applications, e.g., 1) how to extract the coexistent semantic relevance of cross-modal d

Yang Liu, Zinan Zheng, Jiashun Cheng, Fugee Tsung

Accurate Subseasonal-to-Seasonal (S2S) climate forecasting is pivotal for decision-making including agriculture planning and disaster preparedness but is known to be challenging due to its chaotic nature. Although recent data-driven models have shown promising results, their performance is limited by inadequate consideration of geometric inductive biases. Us

Jinhao Pan, Chahat Raj, Ziyu Yao, Ziwei Zhu

Large Language Models (LLMs) often exhibit social biases inherited from their training data. While existing benchmarks evaluate bias by term-based mode through direct term associations between demographic terms and bias terms, LLMs have become increasingly adept at avoiding biased responses, leading to seemingly low levels of bias. However, biases persist in

Luis Suarez, Maria K. Cameron, William F. Fagan, Doron Levy

We propose a predator-prey model with an age-structured predator population that exhibits a functional role reversal. The structure of the predator population in our model embodies the ecological concept of an "ontogenetic niche shift," in which a species' functional role changes as it grows. This structure adds complexity to our model but increases its biol

Taiqiang Wu, Chenchen Ding, Wenyong Zhou, Yuxin Cheng

Low-rank adaptation (LoRA) is a predominant parameter-efficient finetuning method for adapting large language models (LLMs) to downstream tasks. Meanwhile, Compute-in-Memory (CIM) architectures demonstrate superior energy efficiency due to their array-level parallel in-memory computing designs. In this paper, we propose deploying the LoRA-finetuned LLMs on t

Takuma Byakuno

In this paper, we prove the $\ell^\infty$ product space of two bounded subspaces of the Gromov-Hausdorff space can be isometrically embedded into the Gromov-Hausdorff space.

Martin Wilhelm, Thilo Pionteck

Modern heterogeneous systems consist of many different processing units, such as CPUs, GPUs, FPGAs and AI units. A central problem in the design of applications in this environment is to find a beneficial mapping of tasks to processing units. While there are various approaches to task mapping, few can deal with high heterogeneity or applications with a high

Alon Eden, Vignesh Viswanathan, Yair Zick

We study a two-sided matching model where one side of the market (hospitals) has combinatorial preferences over the other side (doctors). Specifically, we consider the setting where hospitals have matroid rank valuations over the doctors, and doctors have either ordinal or cardinal unit-demand valuations over the hospitals. While this setting has been extens

Y. P. Chen, S. Zhang, L. Ji, S. N. Zhang

During thermonuclear bursts, it is suspected that {\bf the cooling of the corona by the burst emission} may be the cause of hard X-ray {\bf deficits}. Although this {\bf deficit} has been observed in nine sources, it has not been observed {\bf from} 4U~1608--52, a nearby prolific burster. Therefore, the authenticity and universality of the hard X-ray {\bf de

Juan Casanova

Difficulty estimation of Beat Saber maps is an interesting data analysis problem and valuable to the Beat Saber competitive scene. We present a simple algorithm that iteratively averages player skill and map difficulty estimations in a bipartite graph of players and maps, connected by scores, using scores only as input. This approach simultaneously estimates

Weilin Chen, Ruichu Cai, Jie Qiao, Yuguang Yan

Estimating causal effects under networked interference from observational data is a crucial yet challenging problem. Most existing methods mainly rely on the networked unconfoundedness assumption, which guarantees the identification of networked effects. However, this assumption is often violated due to the latent confounders inherent in observational data,

Yun-Ru Fan, Yue Luo, Kai Guo, Jin-Peng Wu

A fully connected quantum network with a wavelength division multiplexing architecture plays an increasingly pivotal role in quantum information technology. With such architecture, an entanglement-based network has been demonstrated in which an entangled photon-pair source distributes quantum entanglement resources to many users. Despite these remarkable adv

Di Liu, Teng Deng, Giljoo Nam, Yu Rong

Photorealistic 3D head avatar reconstruction faces critical challenges in modeling dynamic face-hair interactions and achieving cross-identity generalization, particularly during expressions and head movements. We present LUCAS, a novel Universal Prior Model (UPM) for codec avatar modeling that disentangles face and hair through a layered representation. Unl

Qiusi Zhan, Richard Fang, Henil Shalin Panchal, Daniel Kang

Large Language Model (LLM) agents exhibit remarkable performance across diverse applications by using external tools to interact with environments. However, integrating external tools introduces security risks, such as indirect prompt injection (IPI) attacks. Despite defenses designed for IPI attacks, their robustness remains questionable due to insufficient

Jialin Gong, Wei Sun, Yang Wu, Zhenzhou Guo

Despite the rapid progress in predicting 2D magnetic second-order topological insulators (SOTIs), effective strategies for manipulating their spin-polarized corner states remain largely unexplored. The interplay between ferroelectricity, chirality, magnetism, and topology presents an untapped opportunity for controlling these corner states. Here, we propose

Wenxuan Sun, Yequan Chen, Ruijie Xu, Wenzhuo Zhuang

Over the past decade, topological insulators have received enormous attention for their potential in energy-efficient spin-to-charge conversion, enabled by strong spin-orbit coupling and spin-momentum locked surface states. Despite extensive research, the spin-to-charge conversion efficiency, usually characterized by the spin Hall angle ({\theta}SH), remains

Minggui He, Yilun Liu, Shimin Tao, Yuanchang Luo

Despite recent breakthroughs in reasoning-enhanced large language models (LLMs) like DeepSeek-R1, incorporating inference-time reasoning into machine translation (MT), where human translators naturally employ structured, multi-layered reasoning chain-of-thoughts (CoTs), is yet underexplored. Existing methods either design a fixed CoT tailored for a specific

Abhilasha Dave, Cong Wang, James Russell, Ryan Herbst

We implement a specialized version of our SpeckleNN model for real-time speckle pattern classification in X-ray Single-Particle Imaging (SPI) using the SLAC Neural Network Library (SNL) on an FPGA. This hardware is optimized for inference near detectors in high-throughput X-ray free-electron laser (XFEL) facilities like the Linac Coherent Light Source (LCLS)

Yunhai Hu, Zining Liu, Zhenyuan Dong, Tianfan Peng

Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models, particularly for real-time applications. While traditional optimization approaches like pruning and quantization often compromise model quality, recent advances in generation-refinement frameworks demonstrate that this trade-off can be significantly mitig

Mian Zhang, Shaun M. Eack, Zhiyu Zoey Chen

Applying large language models (LLMs) to assist in psycho-counseling is an emerging and meaningful approach, driven by the significant gap between patient needs and the availability of mental health support. However, current LLMs struggle to consistently provide effective responses to client speeches, largely due to the lack of supervision from high-quality

Xiao-Hang Luan, Bo-Lun Huang, Zhen-Zhao Tao, Yan Cui

The search for extraterrestrial intelligence (SETI) targeted searches aim to observe specific areas and objects to find possible technosignatures. Many SETI researches have focused on nearby stars and their planets in recent years. In this paper, we report a targeted SETI observations using the most sensitive L-band Five-hundred-meter Aperture Spherical radi

Ayano Okoso, Mingzhe Yang, Yukino Baba

Explanatory information helps users to evaluate the suggestions offered by AI-driven decision support systems. With large language models, adjusting explanation expressions has become much easier. However, how these expressions influence human decision-making remains largely unexplored. This study investigated the effect of explanation tone (e.g., formal or

Chengfeng zhang, Guo Chen, Yanfeng Zhang, Jie Zhang

The zig-zag Nitrogen (N) chain similar to the Ch-N structure has long been considered a potential high energy density structure. However, all previously predicted zig-zag N chain structures similar to Ch-N exhibit imaginary frequencies in their phonon spectra at 0 GPa. Here, we conducted a systematic investigation of P-N compounds using first-principles calc

Jiayue Lyu, Tianzhi Fang, Zhiheng Lin, Jingxue Han

The virtual synchronous generator (VSG), with the analogous nonlinear power-angle relationship to the synchronous generator (SG), has attracted much attention as a promising solution for converter-based power systems. In this paper, a large signal model of the grid-connected VSG is first established. The trajectory reversing method (TRM) is then introduced t

Fucai Lin, Chuan Liu

A topological space $(X, \tau)$ is said to be have an {\it $\omega^\omega$-base} if for each point $x\in X$ there exists a neighborhood base $\{U_{\alpha}[x]: \alpha\in\omega^\omega\}$ such that $U_{\beta}[x]\subset U_{\alpha}[x]$ for all $\alpha\leq\beta$ in $\omega^\omega$. In this paper, the characterization of a space $X$ is given such that the free Abel

Yukang Huo, Hao Tang

Recent advancements in Artificial Intelligence have led to the development of Multimodal Large Language Models (MLLMs). However, adapting these pre-trained models to dynamic data distributions and various tasks efficiently remains a challenge. Fine-tuning MLLMs for specific tasks often causes performance degradation in the model's prior knowledge domain, a p

Toan Tran, Ruixuan Liu, Li Xiong

Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is included in a model's training dataset, can serve as a foundation for broader privacy threats. Existing defenses designed for t

Yonatan Gizachew Achamyeleh, Shih-Yuan Yu, Gustavo Quirós Araya, Mohammad Abdullah Al Faruque

Industrial Control Systems (ICS) rely heavily on Programmable Logic Controllers (PLCs) to manage critical infrastructure, yet analyzing PLC executables remains challenging due to diverse proprietary compilers and limited access to source code. To bridge this gap, we introduce PLC-BEAD, a comprehensive dataset containing 2431 compiled binaries from 700+ PLC p

Florian Lehner

The weak cop number of infinite graphs can be seen as a coarse-geometric analogue to the cop number of finite graphs. We show that every vertex transitive graph with at least one thick end has infinite weak cop number. It follows that every connected, vertex transitive graph has weak cop number $1$ or $\infty$, answering a question posed by Lee, Mart\'inez-P

Yu Zhao, Songping Huang, Dongsheng Zhou, Zhaoyun Ding

Obtaining valuable information from massive data efficiently has become our research goal in the era of Big Data. Text summarization technology has been continuously developed to meet this demand. Recent work has also shown that transformer-based pre-trained language models have achieved great success on various tasks in Natural Language Processing (NLP). Ai

Fan Jiang, Tom Drummond, Trevor Cohn

Recent approaches to multilingual open-domain question answering (MLODQA) have achieved promising results given abundant language-specific training data. However, the considerable annotation cost limits the application of these methods for underrepresented languages. We introduce a \emph{few-shot learning} approach to synthesise large-scale multilingual data

Hannah Cyberey, Yangfeng Ji, David Evans

Large language models (LLMs) are known to perpetuate stereotypes and exhibit biases. Various strategies have been proposed to mitigate these biases, but most work studies biases as a black-box problem without considering how concepts are represented within the model. We adapt techniques from representation engineering to study how the concept of "gender" is

Takumi Yonaiyama, Kazuhiro Sato

We study the performance of the linear consensus algorithm on strongly connected directed graphs using the linear quadratic (LQ) cost as a performance measure. In particular, we derive bounds on the LQ cost by leveraging effective resistance and reversiblization. Our results extend previous analyses-which were limited to reversible cases-to the nonreversible

Jyh-An Lee

Internet and digital technologies have facilitated copyright sharing in an unprecedented way, creating significant tensions between the free flow of information and the exclusive nature of intellectual property. Copyright owners, users, and online platforms are the three major players in the copyright system. These stakeholders and their relations form the m

Tao Huang, Yanxiang Ma, Shan You, Chang Xu

Masked autoencoders (MAEs) represent a prominent self-supervised learning paradigm in computer vision. Despite their empirical success, the underlying mechanisms of MAEs remain insufficiently understood. Recent studies have attempted to elucidate the functioning of MAEs through contrastive learning and feature representation analysis, yet these approaches of

Xinran Li, Xiaolu Wang, Chenjia Bai, Jun Zhang

In cooperative multi-agent reinforcement learning (MARL), well-designed communication protocols can effectively facilitate consensus among agents, thereby enhancing task performance. Moreover, in large-scale multi-agent systems commonly found in real-world applications, effective communication plays an even more critical role due to the escalated challenge o

Lei Huang, Peng-Fei Wang, Jian-Qi Zhang, Xin Zhou

Nonreciprocal entanglement, characterized by inherently robust operation, is a cornerstone for quantum information processing and communications. However, it remains a great challenge to achieve nonreciprocal entanglement characterized by stability and robustness against environmental fluctuations. Here, we propose a universal nonlinear mechanism to engineer

T. Forrest Kieffer, Michael Wall

The problem of filtering - propagation of states through stochastic differential equations (SDEs) and association of measurement data using Bayesian inference - in a state space which forms a Lie group is considered. Particular emphasis is given to concentrated Gaussians (CGs) as a parametric family of probability distributions to capture the uncertainty ass

Chi-Huan Tung, Sidney Yip, Guan-Rong Huang, Lionel Porcar

Small-angle neutron scattering (SANS) is a powerful technique for probing the nanoscale structure of materials. However, the fundamental limitations of neutron flux pose significant challenges for rapid, high-fidelity data acquisition required in many experiments. To circumvent this difficulty, we introduce a Bayesian statistical framework based on Gaussian

Manveer Singh Tamber, Suleman Kazi, Vivek Sourabh, Jimmy Lin

While the current state-of-the-art dense retrieval models exhibit strong out-of-domain generalization, they might fail to capture nuanced domain-specific knowledge. In principle, fine-tuning these models for specialized retrieval tasks should yield higher effectiveness than relying on a one-size-fits-all model, but in practice, results can disappoint. We sho

Bo-Xuan Li, Ziyin Song, Zhong Fang, Zhijun Wang

Various topological phases, including topological insulators, topological semimetals, and topological superconductors, along with the controllable topological phase transitions, have attracted considerable attention due to their promising applications in spintronics and quantum computing. In this work, we propose two distinct methods for manipulating topolog

Yiyang Mei, Matthew Sag

Whether and how to regulate AI is now a central question of governance. Across academic, policy, and international legal circles, the European Union is widely treated as the normative leader in this space. Its regulatory framework, anchored in the General Data Protection Regulation, the Digital Services and Markets Acts, and the AI Act, is often portrayed as

Mingsi Wang, Shuaiyin Yao, Chang Yue, Lijie Zhang

Given the need to evaluate the robustness of face recognition (FR) models, many efforts have focused on adversarial patch attacks that mislead FR models by introducing localized perturbations. Impersonation attacks are a significant threat because adversarial perturbations allow attackers to disguise themselves as legitimate users. This can lead to severe co

Fattoum Harrathi, Sami Mabrouk, Nasser Nawel, Sergei Silvestrov

A Malcev-Poisson algebra is a Malcev algebra together with a commutative associative algebra structure related by a Leibniz rule. In this paper, we introduce the notion of Malcev-Poisson bialgebra as an analogue of a Malcev bialgebra and establish the equivalence between matched pairs, Manin triples and Malcev-Poisson bialgebras. Moreover, we introduce a new

Shunkun Liang, Bin Li, Banglei Guan, Yang Shang

Vision-based pose estimation plays a crucial role in the autonomous navigation of flight platforms. However, the field of view and spatial resolution of the camera limit pose estimation accuracy. This paper designs a divergent multi-aperture imaging system (DMAIS), equivalent to a single imaging system to achieve simultaneous observation of a large field of

Jianning Chi, Zelan Li, Geng Lin, MingYang Sun

Weakly supervised segmentation methods can delineate thyroid nodules in ultrasound images efficiently using training data with coarse labels, but suffer from: 1) low-confidence pseudo-labels that follow topological priors, introducing significant label noise, and 2) low-rationality loss functions that rigidly compare segmentation with labels, ignoring discri

Linkun Zhou, Jian Li, Yadong Mo, Xiangyan Zhang

Autonomous interaction is crucial for the effective use of elderly care robots. However, developing universal AI architectures is extremely challenging due to the diversity in robot configurations and a lack of dataset. We proposed a universal architecture for the AI-ization of elderly care robots, called AoECR. Specifically, based on a nursing bed, we devel

Juntao Liang, Jun Hou, Weijun Zhang, Yong Wang

Achieving both efficiency and strong discriminative ability in lightweight visual tracking is a challenge, especially on mobile and edge devices with limited computational resources. Conventional lightweight trackers often struggle with robustness under occlusion and interference, while deep trackers, when compressed to meet resource constraints, suffer from

K. Utku Can, Joshua A. Crawford, Roger Horsley, Paul E. L. Rakow

We compute the Gross-Llewellyn Smith sum rule, i.e. the lowest odd moment of the parity-violating structure function, $F_3$, of the nucleon from a lattice QCD calculation of the Compton amplitude. Our calculations are performed on $48^3 \times 96$ lattices at the $SU(3)$ symmetric point for two lattice spacings. We extract the moments for several values of t

Doyoung Choi, Justin Lacini, Jinhyung Park, John Sheridan

We study the higher secant varieties of a smooth projective variety embedded in projective space. We prove that when the variety is a surface and the embedding line bundle is sufficiently positive, these varieties are normal with Du Bois singularities and the syzygies of their defining ideals are linear to the expected order. We show that the cohomology of t

Gustavo Amilcar Saldaña Moncada

This paper works as an appendix of the paper titled Geometry of Associated Quantum Vector Bundles and the Quantum Gauge Group and for paper titled Yang-Mills-Connes Theory and Quantum Principal SU(N)-Bundles. Here, we are going to prove four statements in the theory of quantum principal bundles:: 1) The universal differential envelope $\ast$--calculus of a m

Allen G. Rodrigo

The Hegselmann-Krause (HK) model of opinion dynamics describes how opinions held by individuals in a community change over time in response to the opinions of others and their access to the true value, T, to which these opinions relate. Here, I extend the simple HK model to incorporate an Artificially Intelligent (AI) Oracle that averages the opinions of mem

Yimin Zhu, Lincoln Linlin Xu

Data augmentation effectively addresses the imbalanced-small sample data (ISSD) problem in hyperspectral image classification (HSIC). While most methodologies extend features in the latent space, few leverage text-driven generation to create realistic and diverse samples. Recently, text-guided diffusion models have gained significant attention due to their a

Yimin Zhu, Linlin Xu

Although efficient extraction of discriminative spatial-spectral features is critical for hyperspectral images classification (HSIC), it is difficult to achieve these features due to factors such as the spatial-spectral heterogeneity and noise effect. This paper presents a Spatial-Spectral Diffusion Contrastive Representation Network (DiffCRN), based on deno

Guangfeng Jiang, Jun Liu, Yongxuan Lv, Yuzhi Wu

Outdoor LiDAR point cloud 3D instance segmentation is a crucial task in autonomous driving. However, it requires laborious human efforts to annotate the point cloud for training a segmentation model. To address this challenge, we propose a YoCo framework, which generates 3D pseudo labels using minimal coarse click annotations in the bird's eye view plane. It

Yuan Bian, Min Liu, Yunqi Yi, Xueping Wang

Person re-identification (re-id) models are vital in security surveillance systems, requiring transferable adversarial attacks to explore the vulnerabilities of them. Recently, vision-language models (VLM) based attacks have shown superior transferability by attacking generalized image and textual features of VLM, but they lack comprehensive feature disrupti

Cong Liu, Xin-Ze Song, Zhi-Xi Wu, Guo-Yong Yuan

We investigate the collective signal response of two typical nonlinear dynamical models, the mean-field coupled overdamped bistable oscillators and the underdamped Duffing oscillators, with respect to both the additive Ornstein-Uhlenbeck noise and the weak periodical stimulus. Based on the linear response theory, we theoretically derive the dependences of th

Youbing Hu, Yun Cheng, Anqi Lu, Dawei Wei

The Vision Transformer (ViT) excels in global modeling but faces deployment challenges on resource-constrained devices due to the quadratic computational complexity of its attention mechanism. To address this, we propose the Semantic-Aware Clustering Vision Transformer (SAC-ViT), a non-iterative approach to enhance ViT's computational efficiency. SAC-ViT ope

Chao Zheng

Time-independent scattering methods are widely employed to analyze transport in non-Hermitian systems. Their application, however, rests on a critical yet often overlooked assumption: that an incident wave is a pure superposition of scattering states. In practice, any physically realistic, spatially localized wave packet will generally have a nonzero overlap

Rui Hu, Delai Qiu, Shuyu Wei, Jiaming Zhang

Omnimodal Large Language Models (OLLMs) have shown significant progress in integrating vision and text, but still struggle with integrating vision and audio, often exhibiting suboptimal performance when processing audio queries compared to text queries. This disparity is primarily due to insufficient alignment between vision and audio modalities during train

Xin Ye, Burhaneddin Yaman, Sheng Cheng, Feng Tao

Bird's-eye-view (BEV) representations play a crucial role in autonomous driving tasks. Despite recent advancements in BEV generation, inherent noise, stemming from sensor limitations and the learning process, remains largely unaddressed, resulting in suboptimal BEV representations that adversely impact the performance of downstream tasks. To address this, we

Zhihao Shi, Jie Wang, Zhiwei Zhuang, Xize Liang

Message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. For a sampled mini-batch of target nodes, the message passing process is divided into two parts: message passing between nodes within the batch (MP-IB) and message passing from nodes outside the batch to those within it (MP-OB). However, MP-OB recu

Junji Lin, Yi Zhang, Yunyue Pan, Yuli Chen

Detection and classification of pulmonary nodules is a challenge in medical image analysis due to the variety of shapes and sizes of nodules and their high concealment. Despite the success of traditional deep learning methods in image classification, deep networks still struggle to perfectly capture subtle changes in lung nodule detection. Therefore, we prop

Chen-Chen Zong, Sheng-Jun Huang

Active learning (AL), which iteratively queries the most informative examples from a large pool of unlabeled candidates for model training, faces significant challenges in the presence of open-set classes. Existing methods either prioritize query examples likely to belong to known classes, indicating low epistemic uncertainty (EU), or focus on querying those

Ashkan Jasour, Guglielmo Daddi, Masafumi Endo, Tiago S. Vaquero

Snake robots enable mobility through extreme terrains and confined environments in terrestrial and space applications. However, robust perception and localization for snake robots remain an open challenge due to the proximity of the sensor payload to the ground coupled with a limited field of view. To address this issue, we propose Blind-motion with Intermit

Huayu Huang, Banglei Guan, Yang Shang, Qifeng Yu

The motion measurement of point targets constitutes a fundamental problem in photogrammetry, with extensive applications across various engineering domains. Reconstructing a point's 3D motion just from the images captured by only a monocular camera is unfeasible without prior assumptions. Under limited observation conditions such as insufficient observations

Rundi Lu, Hao-En Li, Zhengwei Liu, Jin-Peng Liu

We generalize the Linear Combination of Hamiltonian Simulation (LCHS) formula [An, Liu, Lin, Phys. Rev. Lett. 2023] to simulate time-evolution operators in infinite-dimensional spaces, including scenarios involving unbounded operators. This extension, named Inf-LCHS for short, bridges the gap between finite-dimensional quantum simulations and the broader cla

Wenyuan Cheng, Zengyang Li, Peng Liang, Ran Mo

The advent of Autonomous Driving Systems (ADS) has marked a significant shift towards intelligent transportation, with implications for public safety and traffic efficiency. While these systems integrate a variety of technologies and offer numerous benefits, their security is paramount, as vulnerabilities can have severe consequences for safety and trust. Th