October 2025 arXiv papers — page 154

Xiang Ma, Litian Xu, Lexin Fang, Caiming Zhang

Cross-modal alignment is an important multi-modal task, aiming to bridge the semantic gap between different modalities. The most reliable fundamention for achieving this objective lies in the semantic consistency between matched pairs. Conventional methods implicitly assume embeddings contain solely semantic information, ignoring the impact of non-semantic i

Sadra Saremi, Amirhossein Ahmadkhan Kordbacheh

High-intensity laser plasma interactions create complex computational problems because they involve both fluid and kinetic regimes, which need models that maintain physical precision while keeping computational speed. The research introduces a machine learning-based three-dimensional hybrid fluid-particle-in-cell (PIC) system, which links relativistic plasma

Zhenyu Lu, Liupeng Li, Jinpeng Wang, Yan Feng

Existing works on reasoning segmentation either connect hidden features from a language model directly to a mask decoder or represent positions in text, which limits interpretability and semantic detail. To solve this, we present CoPRS, a Multi-modal Chain-of-Thought (MCoT)-based positional perception model that bridges language reasoning to segmentation thr

Yuko Kakikawa, Yoshiyuki Ninomiya

In the field of spatial data analysis, spatially varying coefficients (SVC) models, which allow regression coefficients to vary by region and flexibly capture spatial heterogeneity, have continued to be developed in various directions. Moreover, the Bayesian generalized fused lasso is often used as a method that efficiently provides estimation under the natu

Thomas Lamby, Samuel Nicolay

This article examines the Thomae function, a paradigmatic example of a function that is continuous on the irrationals and discontinuous elsewhere. Defined for a parameter $\theta>0$, it exhibits a rich self-similar structure and intriguing regularity properties. After revisiting its fundamental characteristics, we analyze its H\"older continuity, emphasizing

Junfei Shi, Haojia Zhang, Haiyan Jin, Junhuai Li

Polarimetric Synthetic Aperture Radar (PolSAR) covariance matrices and their extracted multi-features - such as scattering angle, entropy, texture, and boundary descriptors - provide complementary and physically interpretable information for image classification. Traditional fusion strategies typically concatenate these features or employ deep learning netwo

Dong Liu, Yanxuan Yu

We propose \textbf{Cognitive Load Traces} (CLTs) as a mid-level interpretability framework for deep models, inspired by Cognitive Load Theory in human cognition. CLTs are defined as symbolic, temporally varying functions that quantify model-internal resource allocation. Formally, we represent CLTs as a three-component stochastic process $(\mathrm{IL}_t, \mat

Hind Atbir, Farah Cherfaoui, Guillaume Metzler, Emilie Morvant

PAC generalization bounds on the risk, when expressed in terms of the expected loss, are often insufficient to capture imbalances between subgroups in the data. To overcome this limitation, we introduce a new family of risk measures, called constrained f-entropic risk measures, which enable finer control over distributional shifts and subgroup imbalances via

Jinbin Zhang, Nasib Ullah, Erik Schultheis, Rohit Babbar

Large output spaces, also referred to as Extreme multilabel classification (XMC), is a setting that arises, e.g., in large-scale tagging and product-to-product recommendation, and is characterized by the number of labels ranging from hundreds of thousands to millions. This means that the linear classification head, usually only a tiny fraction of the overall

Paloma Piot, José Ramom Pichel Campos, Javier Parapar

Hate speech poses a serious threat to social cohesion and individual well-being, particularly on social media, where it spreads rapidly. While research on hate speech detection has progressed, it remains largely focused on English, resulting in limited resources and benchmarks for low-resource languages. Moreover, many of these languages have multiple lingui

Brad Bebee, Ümit V. Çatalyürek, Olaf Hartig, Ankesh Khandelwal

We present the Poseidon engine behind the Neptune Analytics graph database service. Customers interact with Poseidon using the declarative openCypher query language, which enables requests that seamlessly combine traditional querying paradigms (such as graph pattern matching, variable length paths, aggregation) with algorithm invocations and has been syntact

Krystian Roslon, Maciej Czarnynoga, Sebastian Koryciak, Monika Kutyla

We present a development of the ALFRED framework that includes support for the IPbus protocol, created for the Fast Interaction Trigger (FIT) detector in the ALICE experiment at CERN. This modification resolves the incompatibility between the current GBT-based slow-control protocols and the FIT electronics, which is based on the IPbus. A compatibility layer,

Ilaria Vascotto, Alex Rodriguez, Alessandro Bonaita, Luca Bortolussi

The use of Artificial Intelligence (AI) models in real-world and high-risk applications has intensified the discussion about their trustworthiness and ethical usage, from both a technical and a legislative perspective. The field of eXplainable Artificial Intelligence (XAI) addresses this challenge by proposing explanations that bring to light the decision-ma

Guangyi Jia, Qizhe Cai, Chunqi Zheng, Xiaoying Zhou

Polariton canalization exhibits highly collimated and diffraction-free propagation characteristics in natural hyperbolic materials, holding great promise for molding the energy flow at nanoscale. Previously, the majority of canalizations are realized in phonon polaritons. Herein, we theoretically explore hyperbolic magnetoexciton polaritons (HMEPs) in van de

Roman A. Kononov, Nikita A. Pospelov, Konstantin V. Anokhin, Vladimir V. Nekorkin

Understanding how learning algorithms shape the computational strategies that emerge in neural networks remains a fundamental challenge in machine intelligence. While network architectures receive extensive attention, the role of the learning paradigm itself in determining emergent dynamics remains largely unexplored. Here we demonstrate that reinforcement l

Spencer W. Jolly

The electric field distributions and space-time singularity curves are computed for ultrashort pulsed Laguerre-Gaussian laser beams having spatial chirp. Due to the breaking of cylindrical symmetry by the spatial chirp, the singularities trace complicated curves in space-time, which also vary for different combinations of radial and vortical orders. Analytic

Jens Van Nooten, Andriy Kosar, Guy De Pauw, Walter Daelemans

Distance-based unsupervised text classification is a method within text classification that leverages the semantic similarity between a label and a text to determine label relevance. This method provides numerous benefits, including fast inference and adaptability to expanding label sets, as opposed to zero-shot, few-shot, and fine-tuned neural networks that

Thomas K. Bracht, Rachel N. Clark, Petros Androvitsaneas, Matthew Jordan

Mixing the fields generated by different light sources has emerged as a powerful approach for engineering non-Gaussian quantum states. Understanding and controlling the resulting photon statistics is useful for emerging quantum technologies that are underpinned by interference. In this work, we investigate intensity correlation functions arising from the int

Payam Jalili, Salar Ghadiri Alamdari, Bahram Jalili, Amirali Shateri

This research employs a local thermal non-equilibrium (LTNE) model to analyze the heat transfer phenomenon through a porous fin, considering natural convection and radiation effects. The infiltration velocity within the porous medium is evaluated using the Darcy model, and buoyancy effects are accounted for using the Boussinesq approximation. The Akbari-Ganj

N. Welikala, L. Miller, A. N. Taylor, G. Congedo

We measure galaxy structural properties and colour gradients using HST images to trace the evolution of galaxy components. We jointly fit 3D bulge and disk models to 2505 galaxies in GOODS-South across seven bands (bvizYJH) to IAB = 25.5, accounting for different component ellipticities and inclination-dependent dust extinction. Extinction strongly affects s

Corey Bacal Switzer

We prove that for every tower $\mathcal T$ there are $\aleph_1$-dense $A$ and $B$ so that any ``reasonable" forcing notion $\mathbb{P}$ -- an adjective that includes all known ones -- for making $A$ and $B$ isomorphic will add a pseudointersection for the tower. This shows in particular that $\mathsf{MA}_{\aleph_1}(\sigma{\rm -centered})$ holds in all known

Suraj Goel, Bohnishikha Ghosh, Mehul Malik

Qudits have proven to be a powerful resource for quantum information processing, offering enhanced channel capacities, improved robustness to noise, and highly efficient implementations of quantum algorithms. The encoding of photonic qudits in transverse-spatial degrees of freedom has emerged as a versatile tool for quantum information processing, allowing a

Sebastian Schlütter, Tomislav Maras, Alexander Dotterweich, Nico Piatkowski

Combinatorial optimization with a smooth and convex objective function arises naturally in applications such as discrete mean-variance portfolio optimization, where assets must be traded in integer quantities. Although optimal solutions to the associated smooth problem can be computed efficiently, existing adiabatic quantum optimization methods cannot levera

Semih Esenlik, Yaojun Wu, Zhaobin Zhang, Ye-Kui Wang

JPEG AI is an emerging learning-based image coding standard developed by Joint Photographic Experts Group (JPEG). The scope of the JPEG AI is the creation of a practical learning-based image coding standard offering a single-stream, compact compressed domain representation, targeting both human visualization and machine consumption. Scheduled for completion

Jiale Meng, Shuqi Tang, Steven M. Wise, Zhenlin Guo

We develop a matrix-free Full Approximation Storage (FAS) multigrid solver based on staggered finite differences and implemented on GPU in MATLAB. To enhance performance, intermediate variables are reused, and an X-shape Multi-Color Gauss-Seidel (X-MCGS) smoother is introduced, which eliminates conditional branching by partitioning the grid into four submatr

Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic

Large language Models (LLMs) have shown remarkable proficiency in code generation tasks across various programming languages. However, their outputs often contain subtle but critical vulnerabilities, posing significant risks when deployed in security-sensitive or mission-critical systems. This paper introduces TypePilot, an agentic AI framework designed to e

Sai Xu, Yanan Du

This article presents a wireless neural processing architecture (WiNPA), providing a novel perspective for accelerating edge inference of deep neural network (DNN) workloads via joint optimization of wireless and computing resources. WiNPA enables fine-grained integration of wireless communication and edge computing, bridging the research gap between wireles

Bahram Jalili, Salar Ghadiri Alamdari, Payam Jalili, Davood Domiri Ganji

A viscous, incompressible, micropolar bio-nanofluid flowing across a stretching sheet in three dimensions while being driven to convect several slip boundaries in the presence of a magnetic field was studied. With the assistance of the relevant transformations, a mathematical model is presented. The finite difference method numerically solves the converted n

Alistair Brash, Junyi Lu, Bruce Stephen, Blair Brown

Limited visibility of distribution network power flows at the low voltage level presents challenges to both distribution network operators from a planning perspective and distribution system operators from a congestion management perspective. More representative loads are required to support meaningful analysis of LV substations; otherwise, such analysis ris

Weilong Chen, Franz Görlich, Paul Fuchs, Julija Zavadlav

Coarse-graining (CG) enables molecular dynamics (MD) simulations of larger systems and longer timescales that are otherwise infeasible with atomistic models. Machine learning potentials (MLPs), with their capacity to capture many-body interactions, can provide accurate approximations of the potential of mean force (PMF) in CG models. Current CG MLPs are typi

Gan Luo, Arshia M. Jacob, Marco Padovani, Daniele Galli

Methylidyne (CH) has long been considered a reliable tracer of molecular gas in the low-to-intermediate extinction range. Although extended CH 3.3 GHz emission is commonly observed in diffuse and translucent clouds, observations in cold, dense clumps are rare. In this work, we conducted high-sensitivity CH observations toward 27 PGCCs with the Arecibo 305m t

Nikhel Gupta

The rapid growth of large-scale radio surveys, generating over 100 petabytes of data annually, has created a pressing need for automated data analysis methods. Recent research has explored the application of machine learning techniques to address the challenges associated with detecting and classifying radio galaxies, as well as discovering peculiar radio so

Gautier Dagan, Frank Keller, Alex Lascarides

An agent facing a planning problem can use answers to how-to questions to reduce uncertainty and fill knowledge gaps, helping it solve both current and future tasks. However, their open ended nature, where valid answers to "How do I X?" range from executable actions to high-level descriptions of X's sub-goals, makes them challenging for AI agents to ask, and

Chuke Chen, Biao Luo, Nan Li, Boxiang Wang

The rapid expansion of scientific data has widened the gap between analytical capability and research intent. Existing AI-based analysis tools, ranging from AutoML frameworks to agentic research assistants, either favor automation over transparency or depend on manual scripting that hinders scalability and reproducibility. We present ARIA (Automated Research

Byron Alexander Jacobs, Aqeel Morris, Ifthakaar Shaik, Frando Lin

Sperm DNA fragmentation (SDF) is a critical parameter in male fertility assessment that conventional semen analysis fails to evaluate. This study presents the validation of a novel artificial intelligence (AI) tool designed to detect SDF through digital analysis of phase contrast microscopy images, using the terminal deoxynucleotidyl transferase dUTP nick en

Mohammad Karami, Mostafa Jalali, Fatemeh Ghassemi

Time series anomaly detection is critical for modern digital infrastructures, yet existing methods lack systematic cross-domain evaluation. We present a comprehensive forecasting-based framework unifying classical methods (Holt-Winters, SARIMA) with deep learning architectures (LSTM, Informer) under a common residual-based detection interface. Our modular pi

Zhijian Zhou, Xunye Tian, Liuhua Peng, Chao Lei

To adapt kernel two-sample and independence testing to complex structured data, aggregation of multiple kernels is frequently employed to boost testing power compared to single-kernel tests. However, we observe a phenomenon that directly maximizing multiple kernel-based statistics may result in highly similar kernels that capture highly overlapping informati

Mohammad Zeqi Yasin

Do industrial "superstars" help others up or crowd them out? We examine the relationship between the spillovers of superstar firms (those with the top market share in their industry) and the productivity dynamics in Indonesia. Employing data on Indonesian manufacturing firms from 2001 to 2015, we find that superstar exposures in the market raise both the pro

Ye min Thant, Methawee Nukunudompanich, Chu-Chen Chueh, Manabu Ihara

Dedicated analog neurocomputing circuits are promising for high-throughput, low power consumption applications of machine learning (ML) and for applications where implementing a digital computer is unwieldy (remote locations; small, mobile, and autonomous devices, extreme conditions, etc.). Neural networks (NN) implemented in such circuits, however, must con

Zitao Wang, Zhimin Zhao, Michael W. Godfrey

Foundation Models (FMs), such as OpenAI's GPT, are fundamentally transforming the practice of software engineering by enabling the development of \emph{FMware} -- applications and infrastructures built around these models. FMware systems now support tasks such as code generation, natural-language interaction, knowledge integration, and multi-modal content cr

Zhuochen Yang, Kar Wai Fok, Vrizlynn L. L. Thing

Large language models have gained widespread attention recently, but their potential security vulnerabilities, especially privacy leakage, are also becoming apparent. To test and evaluate for data extraction risks in LLM, we proposed CoSPED, short for Consistent Soft Prompt targeted data Extraction and Defense. We introduce several innovative components, inc

Mariusz Tarnopolski

I report on the discovery of 34 new quasi-periodic oscillations (QPOs) in the prompt light curves of long gamma-ray bursts (GRBs) from the Swift/BAT catalog: with one or more constant leading periods, as well as several chirping signals. This is the largest homogenously identified sample or GRB QPOs to date. The presence of QPOs suggests the existence of cha

Pablo Amster, Andrés Rivera, John A. Arredondo

The main purpose of this paper is to analyze the dynamics of the system of time-delay differential equations (DDEs) \begin{equation*} \begin{split} \dot{T}(t)&=T(t) f(t,T(t))-\gamma E(t)T(t),\\ \dot{E}(t)&=\sigma+ \frac{pE(t)T(t-\tau_1)}{g+a T(t-\tau_1)}-\frac{mE(t)T(t-\tau_2)}{g+a T(t-\tau_2)}-\eta E(t), \end{split} \end{equation*} where $T=T(t)$ and $E=E(t

Yingnan Liu, Rui Qiao, Mong Li Lee, Wynne Hsu

Test-time adaptation aims to improve model robustness under distribution shifts by adapting models with access to unlabeled target samples. A primary cause of performance degradation under such shifts is the model's reliance on features that lack a direct causal relationship with the prediction target. We introduce Test-time Adaptation by Causal Trimming (TA

G. Kaur, M. Bilicki, S. Bellstedt, E. Tempel

The Wide-Area VISTA Extragalactic Survey (WAVES) on the 4-metre Multi-Object Spectroscopic Telescope (4MOST) includes two flux-limited subsurveys with very high (95\%) completeness requirements: Wide over $\sim\!1200$ deg$^2$ and Deep over $\sim\!65$ deg$^2$. Both are $Z$-band selected, respectively as $Z<21.1$ and $Z<21.25$ mag, and additionally redshift-li

Jia Wang, Ziyu Zhao, Tingjuntao Ni, Zhongyu Wei

Large language models (LLMs) show strong potential for simulating human social behaviors and interactions, yet lack large-scale, systematically constructed benchmarks for evaluating their alignment with real-world social attitudes. To bridge this gap, we introduce SocioBench-a comprehensive benchmark derived from the annually collected, standardized survey d

Justin Tan, Nengji Zhou, Yang Zhao

The ground state properties and quantum phase transitions of sub-Ohmic spin-boson models are investigated using the multiple Davydov D2 Ansatz in conjunction with the variational principle. Three variants of the model are studied: (i) a single bath with diagonal coupling, (ii) two independent baths with diagonal and off-diagonal couplings, and (iii) a single

Guangzhi Sun, Yixuan Li, Xiaodong Wu, Yudong Yang

Long-duration streaming video understanding is fundamental for future AI agents, yet remains limited by ineffective long-term memory. We introduce video-SALMONN S, a memory-enhanced streaming audio-visual large language model that processes over 3-hour videos at 1 FPS and 360p resolution, outperforming strong non-streaming models under the same memory budget

Qiyi Tong, Olivia Nocentini, Marta Lagomarsino, Kuanqi Cai

Facial Landmark Detection (FLD) in thermal imagery is critical for applications in challenging lighting conditions, but it is hampered by the lack of rich visual cues. Conventional cross-modal solutions, like feature fusion or image translation from RGB data, are often computationally expensive or introduce structural artifacts, limiting their practical depl

Alice Pelosse, Elisabeth Guazzelli, Matthieu Roché

This review article examines the complex dynamics of thin-film flows of granular suspensions spreading over rigid solid substrates with free air interfaces. Such systems feature an involved coupling of the free-surface dynamics with the flow and microstructure of the suspension. In particular, we develop two canonical thin-film situations: drop spreading and

Zexu Sun, Yongcheng Zeng, Erxue Min, Heyang Gao

Contemporary progress in large language models (LLMs) has revealed notable inferential capacities via reinforcement learning (RL) employing verifiable reward, facilitating the development of O1 and R1-like reasoning models. Directly training from base models with RL is called zero-RL. However, previous works rely upon activating LLMs' inherent capacities thr

Yu Lei, Xiaoming Shi, Sihan Yan, Qinghua Zhang

Relaxor ferroelectric thin films are recognized for their ultrahigh power density, rendering them highly promising for energy storage applications in electrical and electronic systems. However, achieving high energy storage performance with chemically homogeneous, environmentally friendly and compositionally stable materials remains challenging. In this work

Luca Vota, Luisa Errichiello

Despite the importance of this variable in the macroeconomic context, current research on job insecurity remains mainly confined to its non-systemic dimension. The research aim of this paper is to identify the short-run and long-run macroeconomic determinants of job insecurity in the presence of asymmetric information between public and private agents, infor

Cheng Gong, Chunyu Qiang, Tianrui Wang, Yu Jiang

Cross-lingual emotional text-to-speech (TTS) aims to produce speech in one language that captures the emotion of a speaker from another language while maintaining the target voice's timbre. This process of cross-lingual emotional speech synthesis presents a complex challenge, necessitating flexible control over emotion, timbre, and language. However, emotion

Pedro E. Gória Silva, Eduardo S. Lima, Jules M. Moualeu, Mohamed Korium

The advent of the fifth-generation technology promises to bring about more vertical applications and emerging services that include vehicular networks and intelligent transportation systems (ITSs). To achieve their vision of real-time and safetyapplications, vehicular networks rely on short-range to medium-range communications. One emerging technology that a

Rongjie Zhu, Cong Zhang, Zhiguang Cao

While large language models (LLMs) are increasingly used as automated heuristic designers for vehicle routing problems (VRPs), current state-of-the-art methods predominantly rely on prompting massive, general-purpose models like GPT-4. This work challenges that paradigm by demonstrating that a smaller, specialized LLM, when meticulously fine-tuned, can gener

Vendulka Humlová

Ultra-peripheral collisions of heavy ions provide a unique environment to study the gluon structure of nuclei through photon-induced reactions. In particular, the incoherent photoproduction of J/$\psi$ vector meson is sensitive to event-by-event fluctuations of the gluon field at nucleon and subnucleonic scales. We report new ALICE measurement of incoherent

Andrea Marinoni, Sai Shivareddy, Pietro Lio', Weisi Lin

The steady growth of artificial intelligence (AI) has accelerated in the recent years, facilitated by the development of sophisticated models such as large language models and foundation models. Ensuring robust and reliable power infrastructures is fundamental to take advantage of the full potential of AI. However, AI data centres are extremely hungry for po

Yaqi Zhao, Xiaochen Wang, Li Dong, Wentao Zhang

Numerosity remains a challenge for state-of-the-art text-to-image generation models like FLUX and GPT-4o, which often fail to accurately follow counting instructions in text prompts. In this paper, we aim to study a fundamental yet often overlooked question: Can diffusion models inherently generate the correct number of objects specified by a textual prompt

Incheol Baek, Yon Dohn Chung

Local Differential Privacy (LDP) addresses significant privacy concerns in sensitive data collection. In this work, we focus on numerical data collection under LDP, targeting a significant gap in the literature: existing LDP mechanisms are optimized for either a very small ($|\Omega| \in \{2, 3\}$) or infinite output spaces. However, no generalized method fo

Hao Tang, Shengfeng He, Jing Qin

Few-shot learning (FSL) addresses the challenge of classifying novel classes with limited training samples. While some methods leverage semantic knowledge from smaller-scale models to mitigate data scarcity, these approaches often introduce noise and bias due to the data's inherent simplicity. In this paper, we propose a novel framework, Synergistic Knowledg

Vasudevarao Allu, Alan P Jose

In a recent paper, Zhou, Ponnusamy, and Rasila [Math. Nachr. (2025)] have established that the conformal deformations, with parameter $\epsilon>0$, of a Gromov hyperbolic space via Busemann functions are uniform spaces for sufficiently small $\epsilon$. In this paper, we demonstrate that if two proper, roughly starlike Gromov hyperbolic spaces are roughly is

Hetong Wang, Tiejun Lv, Yashuai Cao, Weicai Li

Reconfigurable intelligent surface (RIS) technology offers significant promise in enhancing wireless communication systems, but its dual-use potential also introduces substantial security risks. This survey explores the security implications of RIS in next-generation wireless networks. We first highlight the dual-use nature of RIS, demonstrating how its comm

Chen Liu, Wenfang Yao, Kejing Yin, William K. Cheung

Longitudinal multimodal data, including electronic health records (EHR) and sequential chest X-rays (CXRs), is critical for modeling disease progression, yet remains underutilized due to two key challenges: (1) redundancy in consecutive CXR sequences, where static anatomical regions dominate over clinically-meaningful dynamics, and (2) temporal misalignment

Leonid Pastur, Mira Shamis

This paper deals with the asymptotic behaviour of a widely used correlation characteristic in large quantum systems. The correlations are known as quantum entanglement, the characteristic is called entanglement entropy, and the system is an ideal gas of spinless lattice fermions. The system is determined by its one-body Hamiltonian. It is shown in EPS [18] t

Cheol-Hui Lee, Hwa-Yeon Lee, Min-Kyung Jung, Dong-Joo Kim

Missing or corrupted modalities are common in physiological signal-based medical applications owing to hardware constraints or motion artifacts. However, most existing methods assume the availability of all modalities, resulting in substantial performance degradation in the absence of any modality. To overcome this limitation, this study proposes PhysioME, a

Xiucheng Wang, Zien Wang, Nan Cheng, Wenchao Xu

The increase of bandwidth-intensive applications in sixth-generation (6G) wireless networks, such as real-time volumetric streaming and multi-sensory extended reality, demands intelligent multicast routing solutions capable of delivering differentiated quality-of-service (QoS) at scale. Traditional shortest-path and multicast routing algorithms are either co

Deqian Kong, Shi Feng, Jianwen Xie, Ying Nian Wu

We introduce a Markov Chain Monte Carlo (MCMC) algorithm that dramatically accelerates the simulation of quantum many-body systems, a grand challenge in computational science. State-of-the-art methods for these problems are severely limited by $O(N^3)$ computational complexity. Our method avoids this bottleneck, achieving near-linear $O(N \log N)$ scaling pe

Xinfeng Li, Dong Huang, Jie Li, Hongyi Cai

The autonomy and contextual complexity of LLM-based agents render traditional access control (AC) mechanisms insufficient. Static, rule-based systems designed for predictable environments are fundamentally ill-equipped to manage the dynamic information flows inherent in agentic interactions. This position paper argues for a paradigm shift from binary access

Dongkwan Lee, Junhoo Lee, Nojun Kwak

We introduce the Deep Edge Filter, a novel approach that applies high-pass filtering to deep neural network features to improve model generalizability. Our method is motivated by our hypothesis that neural networks encode task-relevant semantic information in high-frequency components while storing domain-specific biases in low-frequency components of deep f

Jiahui Lei, Kyle Genova, George Kopanas, Noah Snavely

This paper addresses the challenge of learning semantically and functionally meaningful 3D motion priors from real-world videos, in order to enable prediction of future 3D scene motion from a single input image. We propose a novel pixel-aligned Motion Map (MoMap) representation for 3D scene motion, which can be generated from existing generative image models

Ans Munir, Faisal Z. Qureshi, Mohsen Ali, Muhammad Haris Khan

Compositional Zero-Shot Learning (CZSL) is a critical task in computer vision that enables models to recognize unseen combinations of known attributes and objects during inference, addressing the combinatorial challenge of requiring training data for every possible composition. This is particularly challenging because the visual appearance of primitives is h

Thierry E Huillet

We show that the Sibuya distribution and its non-critical relatives are relevant in the context of the recursive generation of both simply generated and increasing critical trees' and forests' progenies. A special class of generalized Stirling numbers are at the heart of the analysis of the induced occupancy distributions. Asymptotic aspects of large forests

Junjie Lu, Yuliang Liu, Chaofeng Qu, Wei Shen

Current approaches for strengthening LLM reasoning tend to introduce a training bias toward human-like reasoning trajectories. In step-wise preference optimization, in particular, dependence on human or higher-capacity model annotations for intermediate steps limits exploration of alternative, non-human-like reasoning paths and thus constrains achievable per

Michel de Lara

We consider decision-making under incomplete information about an unknown state of nature. Utility acts (that is, utility vectors indexed by states of nature) and beliefs (probability distributions over the states of nature) are naturally paired by bilinear duality, giving the expected utility. With this pairing, an expected utility maximizer (DM) is charact

Nidup Dorji, Sourav Das, Richard Stone, Alan R. Clough

This study examined the spatial-temporal dynamics of Emergency Examination Order or Authority (EE-O/A) admissions in Far Northern Queensland (FNQ) from 2009 to 2020, using 13,035 unique police records aggregated across 83 postcodes. A two-stage modelling framework was used: Lasso was used to identify a parsimonious set of socio economic and health-service co

Shuwei Chen, Jiajun Cui, Zhengqi Xu, Fan Zhang

Click-through rate (CTR) prediction, which models behavior sequence and non-sequential features (e.g., user/item profiles or cross features) to infer user interest, underpins industrial recommender systems. However, most methods face three forms of heterogeneity that degrade predictive performance: (i) Feature Heterogeneity persists when limited sequence sid

Toshio Oshima

We classify complex hyperplane arrangements $\mathcal A$ whose intersection posets $L(\mathcal A)$ satisfy $L(\mathcal A)=\pi_i^{-1}\circ\pi_i\bigl(L(\mathcal A)\bigr)$ for $i=1,\dots,n$. Here $\pi_i$ denotes the projection from $\mathbb C^n$ onto $\mathbb C^{n-1}$ defined by that forgets the coordinate $x_i$ of $(x_1,\dots,x_n)\in\mathbb C^n$, and $\pi_i\bi

Shumaila Javaid, Nasir Saeed

Electromagnetic (EM) communication is nearing its physical and thermodynamic limits, where further performance gains through spectrum optimization alone have become increasingly unsustainable. Finite bandwidth, propagation loss at higher frequencies, and the inherent trade-offs between energy and information constrain the scalability of 6G and beyond systems

Fengling Zhu, Boshi Liu, Jingyu Hua, Sheng Zhong

Multimodal Large Language Models (MLLMs) have achieved remarkable success in tasks such as image captioning, visual question answering, and cross-modal reasoning by integrating visual and textual modalities. However, their multimodal nature also exposes them to adversarial threats, where attackers can perturb either modality or both jointly to induce harmful

Lea J. Haeusel, Jonas Nitzler, Lea J. Köglmeier, Wolfgang A. Wall

Inverse analysis, such as model calibration, often suffers from a lack of informative data in complex real-world scenarios. The standard remedy, designing new experimental setups, is often costly and time-consuming, while readily available but seemingly useless data are ignored. This work proposes incorporating such data from additional physical fields into

Junxiang Wang, Han Zhang, Zehao Wang, Huaiyuan Chen

Effective rehabilitation methods are essential for the recovery of lower limb dysfunction caused by stroke. Nowadays, robotic exoskeletons have shown great potentials in rehabilitation. Nevertheless, traditional rigid exoskeletons are usually heavy and need a lot of work to help the patients to put them on. Moreover, it also requires extra compliance control

J. K. Singh, Sonal Aggarwal, Shaily, Hamid Shabani

In this paper, we investigate the latetime cosmic acceleration of the Quintessence model within the framework of Hoyle Narlikar Gravity (HNG), which incorporates a creation field. Using the Hubble tension as a function of the density parameter for matter, the density parameter for radiation, and the density parameter for dark energy in the covariant formulat

Noriyuki Abe

We study Braden-MacPherson sheaves on the moment graph associated to the set of of alcoves. We define an action of Soergel bimodules on the category of Braden-MacPherson sheaves. We also prove a certain stability of morphisms between Braden-MacPherson sheaves.

Bozhou Zhang, Nan Song, Jingyu Li, Xiatian Zhu

End-to-end autonomous driving methods aim to directly map raw sensor inputs to future driving actions such as planned trajectories, bypassing traditional modular pipelines. While these approaches have shown promise, they often operate under a one-shot paradigm that relies heavily on the current scene context, potentially underestimating the importance of sce

Xianlin Liu, Yan Gong, Bohao Li, Jiajing Huang

With the widespread adoption of Computer-Aided Design(CAD) drawings in engineering, architecture, and industrial design, the ability to accurately interpret and analyze these drawings has become increasingly critical. Among various subtasks, panoptic symbol spotting plays a vital role in enabling downstream applications such as CAD automation and design retr

Junhua Chen, Simon Mathis, Charles Harris, Kieran Didi

Generative modeling techniques such as Diffusion and Flow Matching have achieved significant successes in generating designable and diverse protein backbones. However, many current models are computationally expensive, requiring hundreds or even thousands of function evaluations (NFEs) to yield samples of acceptable quality, which can become a bottleneck in

Huizai Yao, Sicheng Zhao, Shuo Lu, Hui Chen

Source-Free Object Detection (SFOD) enables knowledge transfer from a source domain to an unsupervised target domain for object detection without access to source data. Most existing SFOD approaches are either confined to conventional object detection (OD) models like Faster R-CNN or designed as general solutions without tailored adaptations for novel OD arc

Fabio Marco Monetti, Adam Lundström, Colin de Kwant, Magnus Gyllenskepp

Modular product design has become a strategic enabler for companies seeking to balance product variety, operational efficiency, and market responsiveness, making the alignment between modular architecture and manufacturing considerations increasingly critical. Modular Function Deployment (MFD) is a widely adopted method for defining modular product architect

Chi Zhang, Shihao Zhang, Mengmeng Zhang, Lin He

Insulating, atomically flat transition metal dichalcogenides (TMDs) like WSe2 are ideal substrates for probing intrinsic graphene properties. Conventionally, their influence on graphene's band structure is assumed negligible, particularly when small moire patterns form. Combining scanning tunneling microscopy/spectroscopy and theoretical analysis, we reveal

Harin Yoon, Dongwhan Kim, Changhoon Oh, Soojin Jun

In recent years, discussions on integrating Artificial Intelligence (AI) into UX design have intensified. However, the practical application of AI tools in design is limited by their operation within overly simplified scenarios, inherent complexity and unpredictability, and a general lack of relevant education. This study proposes an effective UXer-AI collab

Ya Li, WanRu Wang, Weizhe Qiao, Qizhou Wu

Duan-Lukin-Cirac-Zoller (DLCZ)-based multimodequantum networks rely on efficient spatial-to-fiber coupling, yetenvironmental perturbations compromise this performance. Wedevelop a cascaded adaptive feedback control system integratedinto the quantum entanglement source preparation path.Leveraging a power-feedback hillclimbing algorithm, itdynamically regulate

Yuxinyue Qian, Jun Liu

With the rapid development of artificial intelligence (AI) technology, socio-economic systems are entering a new stage of "human-AI co-creation." Building upon a previously established multi-level intelligent agent economic model, this paper conducts simulation-based comparisons of macroeconomic output evolution in China and the United States under different

Wonah Kim, Jeonghyeon Park, Dongsan Jun, Jungkyu Han

Disentangling complex causal relationships is important for accurate detection of anomalies. In multivariate time series analysis, dynamic interactions among data variables over time complicate the interpretation of causal relationships. Traditional approaches assume statistical independence between variables in unsupervised settings, whereas recent methods

Tianyi Tan, Yinan Zheng, Ruiming Liang, Zexu Wang

Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning. Learning-based approaches attempt to address this challenge with advanced generative models, removing the dependency on over-engineered architectures for representation fusion. However, brute-force implementation by simply stacking tra

Khaled Hariz, Sina Ober-Blöbaum, Fernando Jimenez

Lagrangian systems subject to fractional damping can be incorporated into a variational formalism. The construction can be made by doubling the state variables and introducing fractional derivatives \cite{JiOb2}. The main objective of this paper is to use the Runge-Kutta convolution quadrature (RKCQ) method for approximating fractional derivatives, combined

Chi Zhang, Quan Shen, Mengmeng Zhang, Zhiming Deng

The limited quantum yield of strained monolayer transition metal dichalcogenides grown by vapor-phase methods and during transfer-based stacking poses a fundamental challenge for their optoelectronic applications. Here, we introduce the concept of "entropy engineering" as a transformative strategy to selectively enhance light-matter interactions through cont

Stefan Gebhart, Lutz Schröder, Paul Wild

Fuzzy logic extends the classical truth values "true" and "false" with additional truth degrees in between. More specifically, fuzzy modal logics in this sense are given by a choice of fuzzy modalities and a fuzzy propositional base. It has been noted that fuzzy modal logics over the Zadeh base, which interprets disjunction as maximum, are often computationa

Andrada Iulia Prajescu, Roberto Confalonieri

Artificial Intelligence (AI) systems are increasingly deployed in legal contexts, where their opacity raises significant challenges for fairness, accountability, and trust. The so-called ``black box problem'' undermines the legitimacy of automated decision-making, as affected individuals often lack access to meaningful explanations. In response, the field of

Yi Zhang, Ming-Zhu Liu, Li-Sheng Geng

Inspired by the observation of the doubly charmed tetraquark state $T_{cc}$ at $pp$ collisions in the inclusive processes, we systematically investigate the production of doubly charmed tetraquark states in exclusive $B_c$ decays. In this work, we assume the $T_{cc}$ as a $DD^*$ bound state, and then predict the masses of its heavy quark spin symmetry partne