October 2025 arXiv papers — page 80

Ying Dai, Wei Yu Chen

This paper presents a novel training-free framework for open-vocabulary image segmentation and object recognition (OVSR), which leverages EfficientNetB0, a convolutional neural network, for unsupervised segmentation and CLIP, a vision-language model, for open-vocabulary object recognition. The proposed framework adopts a two stage pipeline: unsupervised imag

Tian Xia, Zihan Ma, Xinlong Wang, Qing Liu

Decoding images from fMRI often involves mapping brain activity to CLIP's final semantic layer. To capture finer visual details, many approaches add a parameter-intensive VAE-based pipeline. However, these approaches overlook rich object information within CLIP's intermediate layers and contradicts the brain's functionally hierarchical. We introduce BrainMCL

Yuwei Guo, Zihan Zhao, Xiaowei Liu, Xiangning Yu

Multi-agent simulation based on LLMs has increasingly emerged as a new paradigm for exploring complex social phenomena and validating theoretical hypotheses. However, traditional experimental design in the social sciences relies heavily on interdisciplinary expert knowledge, involving cumbersome procedures and high technical barriers. While LLM-driven agents

Anirudh Ganesh, Nitin Sood

The Open Data Protocol (OData) provides a standardized approach for building and consuming RESTful APIs with rich query capabilities. Despite its power and maturity, OData adoption remains confined primarily to enterprise environments, particularly within Microsoft and SAP ecosystems. This paper analyzes the key barriers preventing wider OData adoption and i

Ewelina Gajewska, Arda Derbent, Jaroslaw A Chudziak, Katarzyna Budzynska

In this paper, we investigate how personalising Large Language Models (Persona-LLMs) with annotator personas affects their sensitivity to hate speech, particularly regarding biases linked to shared or differing identities between annotators and targets. To this end, we employ Google's Gemini and OpenAI's GPT-4.1-mini models and two persona-prompting methods:

Juncheng Wang, Lei Shang, Ziqi Liu, Wang Lu

Crowd localization plays a crucial role in visual scene understanding towards predicting each pedestrian location in a crowd, thus being applicable to various downstream tasks. However, existing approaches suffer from significant performance degradation due to discrepancies in head scale distributions (scale shift) between training and testing data, a challe

Panagiotis Agrafiotis, Begüm Demir

Accurate, detailed, and regularly updated bathymetry, coupled with complex semantic content, is essential for under-mapped shallow-water environments facing increasing climatological and anthropogenic pressures. However, existing approaches that derive either depth or seabed classes from remote sensing imagery treat these tasks in isolation, forfeiting the m

Alberto Baccini

This article challenges the conventional reading of Francis Ysidro Edgeworth by reconstructing his intellectual project of unifying the moral sciences through mathematics. The contribution he made in the first phase of his writing, culminating in \textit{Mathematical Psychics}, aimed to reconfigure utilitarianism as an exact science, grounding it in psychoph

Usama Antuley, Shahbaz Siddiqui, Sufian Hameed, Waqas Arif

The rapid evolution of smart cities has increased the reliance on intelligent interconnected services to optimize infrastructure, resources, and citizen well-being. Agentic AI has emerged as a key enabler by supporting autonomous decision-making and adaptive coordination, allowing urban systems to respond in real time to dynamic conditions. Its benefits are

Kadri Hacioglu, Manjunath K E, Andreas Stolcke

We propose integration of reasoning into speech large language models (speechLLMs) for the end-to-end slot-filling task. Inspired by the recent development of reasoning LLMs, we use a chain-of-thought framework to decompose the slot-filling task into multiple reasoning steps, create a reasoning dataset and apply the supervised fine-tuning strategy to a speec

Junjie Song, Yiwen Liu, Dapeng Li, Yin Sun

Text summarization is a crucial task that requires the simultaneous optimization of multiple objectives, including consistency, coherence, relevance, and fluency, which presents considerable challenges. Although large language models (LLMs) have demonstrated remarkable performance, enhanced by reinforcement learning (RL), few studies have focused on optimizi

Loay Abdelrazek, Leyli Karaçay, Marin Orlic

As networks move toward the next-generation 6G, Intent-based Management (IbM) systems are increasingly adopted to simplify and automate network management by translating high-level intents into low-level configurations. Within these systems, agents play a critical role in monitoring current state of the network, gathering data, and enforcing actions across t

Levin Maier, Francesco Ruscelli

In this article, we investigate \emph{right-invariant magnetic systems} on half-Lie groups, which consist of a strong right-invariant Riemannian metric and a right-invariant closed two-form. The main examples are groups of $H^s$ or $C^k$ diffeomorphisms of compact manifolds. In this setting, we define \emph{Ma\~n\'e's critical value} on the universal cover f

Changbo Wu, Zhuolong Yu, Gongming Zhao, Hongli Xu

Collective communication (CC) is critical for scaling distributed machine learning (DML). The predictable traffic patterns of DML present a great opportunity for applying optical network technologies. Optical networks with reconfigurable topologies promise high bandwidth and low latency for collective communications. However, existing approaches face inheren

Hai-jie Yuan, Heng Zhang, Fei Yin

Handwritten signature verification is a crucial aspect of identity authentication, with applications in various domains such as finance and e-commerce. However, achieving high accuracy in signature verification remains challenging due to intra-user variability and the risk of forgery. This paper introduces a novel approach for dynamic signature verification:

P. Chakraborty, G. Kornakov, A. Kisiel, Yu. M. Sinyukov

Emission asymmetries between pions and kaons reflect the role of the hadronic phase in the cooling of a droplet of deconfined strongly-interacting matter. This study compares results from two models at the same collision energy of $\sqrt{s_{\mathrm{NN}}}=5.02$ TeV to investigate how interactions in the hadronic phase affect particle emission. The first model

Shou Yoshikawa

We introduce a new criterion providing a sufficient condition for a hypersurface in an unramified regular local ring to be perfectoid pure. The criterion is formulated in terms of an explicitly computable sequence of integers, called the splitting-order sequence. Our main theorem shows that if all entries of the sequence are at most $p-1$, then the hypersurf

Fan Xu, Xinyu Hu, Zhenghan Yu, Li Lin

The increasing reliance on natural language generation (NLG) models, particularly large language models, has raised concerns about the reliability and accuracy of their outputs. A key challenge is hallucination, where models produce plausible but incorrect information. As a result, hallucination detection has become a critical task. In this work, we introduc

Suraka Bhattacharjee, Koushik Mandal, Supurna Sinha

We study the decoherence of an anisotropic anharmonic oscillator in a magnetic field, coupled to a bath of harmonic oscillators at high and low temperatures. We solve the anharmonic oscillator problem using perturbative techniques and derive the non-Markovian master equation in the weak coupling limit. The anharmonicity parameter {\alpha} enhances decoherenc

Kailin Jiang, Hongbo Jiang, Ning Jiang, Zhi Gao

Large Multimodal Models encode extensive factual knowledge in their pre-trained weights. However, its knowledge remains static and limited, unable to keep pace with real-world developments, which hinders continuous knowledge acquisition. Effective knowledge injection thus becomes critical, involving two goals: knowledge adaptation (injecting new knowledge) a

Jinwu Hu, Zihao Lian, Zhiquan Wen, Chenghao Li

Reinforcement Learning enables agents to learn optimal behaviors through interactions with environments. However, real-world environments are typically non-stationary, requiring agents to continuously adapt to new tasks and changing conditions. Although Continual Reinforcement Learning facilitates learning across multiple tasks, existing methods often suffer

Zenghui Fan, Runyu Ma, Stefano Chesi, Congjun Wu

Loop currents have been proposed in various superconductors and recently confirmed in kagome materials, raising a fundamental question regarding their intrinsic connection to superconductivity. Here, we study a sign-problem-free bilayer $t-J_{\perp}-V$ model hosting a spontaneous interlayer loop-current parent state, and explore the interplay between loop-cu

Iman Rahmani, Saman Yazdannik, Morteza Tayefi, Jafar Roshanian

The performance of deep reinforcement learning agents is fundamentally constrained by their neural network architecture, a choice traditionally made through expensive hyperparameter searches and then fixed throughout training. This work investigates whether online, adaptive architecture optimization can escape this constraint and outperform static designs. W

Piotr Dyszewski, Tamara Mika

We investigate multivariate regular variation in the context of time-homogeneous Markov chains on general vector spaces and in random coefficient linear models. In the first part, we show that the regular variation of the stationary distribution can be derived from that of the innovations, provided that the chain satisfies a certain monotonicity condition wi

M. Ohishi, I. Nagai, R. Oda, H. Yanagihara

This paper deals with the GMANOVA model with a matrix of polynomial basis functions as a within-individual design matrix. The model involves two model selection problems: the selection of explanatory variables and the selection of the degrees of the polynomials. The two problems can be uniformly addressed by hierarchically incorporating zeros into the vector

Fan Xu, Huixuan Zhang, Zhenliang Zhang, Jiahao Wang

Current large language models (LLMs) often suffer from hallucination issues, i,e, generating content that appears factual but is actually unreliable. A typical hallucination detection pipeline involves response decomposition (i.e., claim extraction), query generation, evidence collection (i.e., search or retrieval), and claim verification. However, existing

Mengyuan Chen, Chengjun Dai, Xinyang Dong, Chengzhe Feng

We present Dingtalk DeepResearch, a unified multi agent intelligence framework for real world enterprise environments, delivering deep research, heterogeneous table reasoning, and multimodal report generation.

Ping Zhou, Meiyu Si, Yuanjie Bi, Illya Drebot

The MeV Gamma-Gamma Collider would provide a direct experimental platform for elastic light-by-light scattering ($\gamma\gamma \to \gamma\gamma$) and the Breit-Wheeler process with two real photons ($\gamma\gamma \to e^+e^-$). A Monte Carlo code, the Genie Background Evaluation Tool (GBET), has been developed to fully simulate two successive inverse Compton

Shreyan Banerjee, Aasifa Rounak, Cathal Hoare, Denis Dowling

This study is the first application of spiking neural networks (SNNs) for anomaly detection in the Laser Powder Bed Fusion (LPBF) additive manufacturing process. The neural networks were used to identify print processing anomalies generated by dropping of laser energy during the printing of individual layers in a Ti-6Al-4V alloy lattice structures. Associate

Hirotaka Onuki, Teppei Takamatsu, Shou Yoshikawa

We introduce the notion of quasi-$F$-splitting in mixed characteristic and study Kodaira-type vanishing on quasi-$F$-splitting varieties. As an application, we prove a Kodaira-type vanishing on lifts of rational double point (RDP) del Pezzo surfaces.

Byung-Kwan Lee, Ryo Hachiuma, Yong Man Ro, Yu-Chiang Frank Wang

Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel and efficient training algorithm designed to create powerful, lightweight VLMs. RIL distinctively combines the strengths

Pattravadee de Favereau de Jeneret, Ioannis Diamantis

This study investigates whether Topological Data Analysis (TDA) can provide additional insights beyond traditional statistical methods in clustering currency behaviours. We focus on the foreign exchange (FX) market, which is a complex system often exhibiting non-linear and high-dimensional dynamics that classical techniques may not fully capture. We compare

Chirag Padubidri, Pranesh Velmurugan, Andreas Lanitis, Andreas Kamilaris

Monitoring species distribution is vital for conservation efforts, enabling the assessment of environmental impacts and the development of effective preservation strategies. Traditional data collection methods, including citizen science, offer valuable insights but remain limited in coverage and completeness. Species Distribution Modelling (SDM) helps addres

Petar Radanliev

Problem Space: AI Vulnerabilities and Quantum Threats Generative AI vulnerabilities: model inversion, data poisoning, adversarial inputs. Quantum threats Shor Algorithm breaking RSA ECC encryption. Challenge Secure generative AI models against classical and quantum cyberattacks. Proposed Solution Collaborative Penetration Testing Suite Five Integrated Compon

Simone Celora, Andrea Tonini, Francesco Regazzoni, Luca Dede'

In this work, we develop patient-specific cardiocirculatory models with the aim of building Digital Twins for hypertension. In particular, in our pathophysiology-based framework, we consider both 0D cardiocirculatory models and a 3D-0D electromechanical model. The 0D model, which consists of an RLC circuit, is studied in two variants, with and without capill

Ziheng Deng, Xue Liu, Jiantong Jiang, Yankai Li

The Viterbi algorithm is a key operator for structured sequence inference in modern data systems, with applications in trajectory analysis, online recommendation, and speech recognition. As these workloads increasingly migrate to resource-constrained edge platforms, standard Viterbi decoding remains memory-intensive and computationally inflexible. Existing m

Abdollah Rahimi, Mehdi Jafari Shahbazzadeh, Amid Khatibi

Wireless Body Area Networks (WBANs) have gained significant attention due to their applications in healthcare monitoring, sports, military communication, and remote patient care. These networks consist of wearable or implanted sensors that continuously collect and transmit physiological data, requiring efficient and reliable communication. However, WBANs fac

Borja Sierra Miranda, Thomas Studer

Most existing work on strategic reasoning simply adopts either an informed or an uninformed semantics. We propose a model where knowledge of strategies can be specified on a fine-grained level. In particular, it is possible to distinguish first-order, higher-order, and common knowledge of strategies. We illustrate the effect of higher-order knowledge of stra

Yatai Ji, Teng Wang, Yuying Ge, Zhiheng Liu

Discrete diffusion models have emerged as a promising direction for vision-language tasks, offering bidirectional context modeling and theoretical parallelization. However, their practical application is severely hindered by a train-inference discrepancy, which leads to catastrophic error cascades: initial token errors during parallel decoding pollute the ge

Yang Zhang, Rui Zhang, Jiaming Guo, Lei Huang

The remarkable progress of Large Language Models (LLMs) presents promising opportunities for Verilog code generation which is significantly important for automated circuit design. The lacking of meaningful functional rewards hinders the preference optimization based on Reinforcement Learning (RL) for producing functionally correct Verilog code. In this paper

Konstantinos A. Lizos, Leandros Maglaras, Elena Petrovik, Saied M. Abd El-atty

The increasing reliance on AI-driven 5G/6G network infrastructures for mission-critical services highlights the need for reliability and resilience against sophisticated cyber-physical threats. These networks are highly exposed to novel attack surfaces due to their distributed intelligence, virtualized resources, and cross-domain integration. This paper prop

Sujit Silas Armstrong Suthahar, Patrick Allard

Arsenic (As), a widespread environmental toxin, poses major health risks due to its inorganic forms (iAs), which are linked to cancer, cardiovascular disease, and endocrine disruption. Although its toxic effects have been extensively studied, the molecular mechanisms underlying arsenic-induced perturbations remain incompletely understood. This complexity ari

Michael Yuhas, Rajesh K. Ahir, Laksamana Vixell Tanjaya Hartono, Muhammad Dzaki Dwi Putranto

Operating fleets of electric vehicles (EVs) introduces several challenges, some of which are borne by the fleet operator, and some of which are borne by the power grid. To maximize short-term profit a fleet operator could always charge EVs at the maximum rate to ensure vehicles are ready to service ride demand. However, due to the stochastic nature of electr

Konstantinos Bacharidis, Antonis A. Argyros

Mistake analysis in procedural activities is a critical area of research with applications spanning industrial automation, physical rehabilitation, education and human-robot collaboration. This paper reviews vision-based methods for detecting and predicting mistakes in structured tasks, focusing on procedural and executional errors. By leveraging advancement

S. Takagi, Y. Aritomo, K. Nakajima, K. Okada

Kinetic energy of individual fission fragment for actinide nuclei is, for example, important for evaluating the prompt-neutron spectrum in the laboratory system. It is experimentally known that kinetic energy for each fragment is constant at about 100 MeV for light fragments and that for heavy fragments decreases linearly with mass number. Most of the theore

Sehyun Park, Jongjin Lee, Yunseop Shin, Ilsang Ohn

Deep ensembles deliver state-of-the-art, reliable uncertainty quantification, but their heavy computational and memory requirements hinder their practical deployments to real applications such as on-device AI. Knowledge distillation compresses an ensemble into small student models, but existing techniques struggle to preserve uncertainty partly because reduc

Kefeng Huang, Jonathon Pipe, Alice E. Martin, Tianyuan Wang

Chemistry laboratory automation aims to increase throughput, reproducibility, and safety, yet many existing systems still depend on frequent human intervention. Advances in robotics have reduced this dependency, but without a structured representation of the required skills, autonomy remains limited to bespoke, task-specific solutions with little capacity to

Liwen Zhang, Wei Si, Ke-ke Shang, Jiangli Zhu

As artificial intelligence-generated content (AIGC) reshapes knowledge acquisition, higher education faces growing inequities that demand systematic mapping and intervention. We map the AI divide in undergraduate education by combining network science with survey evidence from 301 students at Nanjing University, one of China's leading institutions in AI educ

Natalia P. Bondarenko

In this paper, we study differential operators associated with the formal expression $y''' + s(\sigma' y)' + s \sigma' y' + \kappa \sigma'' y$ with distribution coefficient $\sigma'' \in W_3^{-2}$, where $s$ and $\kappa$ are constants. The uniqueness theorems are proved for the inverse spectral problems that consist in the recovery of $\sigma$ from the Weyl-

Reza Esfandiarpoor, Vishwas Suryanarayanan, Stephen H. Bach, Vishal Chowdhary

Since the introduction of the Model Context Protocol (MCP), the number of available tools for Large Language Models (LLMs) has increased significantly. These task-specific tool sets offer an alternative to general-purpose tools such as web browsers, while being easier to develop and maintain than GUIs. However, current general-purpose agents predominantly re

Agelos Georgakopoulos

In the aftermath of the Robertson--Seymour Graph Minor Theorem, Thomas conjectured that the countable graphs are well-quasi-ordered under the minor relation. We prove that this conjecture, when restricted to graphs with no infinite paths (rays), is equivalent to the statement that the finite graphs are better-quasi-ordered, another well-known open problem. E

Yoshiki Jikumaru

It is known that a shell membrane in equilibrium where a constant purely normal load $q_n$ acts on the membrane, and where the principal curvature lines coincide with the principal stress lines, forms an integrable system called a membrane O surface. This paper formulates the governing equations for membrane O surfaces of the 1st and 2nd kind, which are anal

Safa Ben Atitallah, Maha Driss, Wadii Boulila, Anis Koubaa

Alzheimer disease is a severe brain disorder that causes harm in various brain areas and leads to memory damage. The limited availability of labeled medical data poses a significant challenge for accurate Alzheimer disease detection. There is a critical need for effective methods to improve the accuracy of Alzheimer disease detection, considering the scarcit

Shubham Joshi

Objectives: This study aims to investigate the readability and understandability of bitwise operators in programming, with the main hypothesis that there will be a difference in the performance metrics (response time and error rate) between participants exposed to various bitwise operators related questions and those who are not. Participants: Participants i

Qing Zhao, Masaaki Kimura, Bo Zhou, Seung-heon Shin

We systematically investigate the size evolution of the di-neutron (2n), di-proton (2p), and deuteron (d) in 6He, 14Be, 17B, 6Be, 17Ne, and 6Li using microscopic calculations. Remarkably, all nucleon pairs exhibit a universal size compression at the nuclear surface, regardless of their species and binding energies. These features correspond to the BCS- and B

Lukas Hughes-Noehrer, Matthew J Parkes, Andrew Stewart, Anthony J Wilson

As computational analysis becomes increasingly more complex in health research, transparent sharing of analytical code is vital for reproducibility and trust. This practical guide, aligned to open science practices, outlines actionable recommendations for code sharing in healthcare research. Emphasising the FAIR (Findable, Accessible, Interoperable, Reusable

Nobline Yoo, Olga Russakovsky, Ye Zhu

Text-to-image (T2I) diffusion models have achieved strong performance in semantic alignment, yet they still struggle with generating the correct number of objects specified in prompts. Existing approaches typically incorporate auxiliary counting networks as external critics to enhance numeracy. However, since these critics must provide gradient guidance duri

Yuichi Honjo, Cedric Caremel, Ken Takaki, Yuta Noma

Wireless power transfer (WPT) with coupled resonators offers a promising solution for the seamless powering of electronic devices. Interactive design approaches that visualize the magnetic field and power transfer efficiency based on system geometry adjustments can facilitate the understanding and exploration of the behavior of these systems for dynamic appl

Smayan Agarwal, Aalok Thakkar

When does a deterministic computational model define a probability distribution? What are its properties? This work formalises and settles this stochasticity problem for weighted automata, and its generalisation cost register automata (CRA). We show that checking stochasticity is undecidable for CRAs in general. This motivates the study of the fully linear f

Saurabh Chauhan, Zeeshan Rasheed, Malik Abdul Sami, Kai-Kristian Kemell

This paper presents a system that uses Large Language Models (LLMs)-based agents to automate the API-first development of RESTful microservices. This system helps to create an OpenAPI specification, generate server code from it, and refine the code through a feedback loop that analyzes execution logs and error messages. The integration of log analysis enable

Zhang Nengbo, Ho Hann Woei

Accurate and efficient recognition of Micro Air Vehicle (MAV) motion is essential for enabling real-time perception and coordination in autonomous aerial swarm. However, most existing approaches rely on large, computationally intensive models that are unsuitable for resource-limited MAV platforms, which results in a trade-off between recognition accuracy and

Yun Kai Zhuang

Real-world image super-resolution (Real-ISR) must handle complex degradations and inherent reconstruction ambiguities. While generative models have improved perceptual quality, a key trade-off remains with computational cost. One-step diffusion models offer speed but often produce structural inaccuracies due to distillation artifacts. To address this, we pro

Xiaoyuan Zhang, Yizhe Huang, Chengdong Ma, Zhixun Chen

Designing adaptive mechanisms to align individual and collective interests remains a central challenge in artificial social intelligence. Existing methods often struggle with modeling heterogeneous agents possessing persistent latent traits (e.g., skills, preferences) and dealing with complex multi-agent system dynamics. These challenges are compounded by th

Anwar Ahmed Khan, Shama Siddiqui, Mehar Ullah, Indrakshi Dey

Sleep quality is an important indicator of the efficient cognitive function for high school teachers. Due to the high work stress and multi-tasking expectations, the teachers often face issues with their sleep quality and cognitive function, which has a clearly negative influence on their teaching abilities. In this work, we propose a unique but simple metho

Mingen Li, Houjian Yu, Yixuan Huang, Youngjin Hong

Long-horizon routing tasks of deformable linear objects (DLOs), such as cables and ropes, are common in industrial assembly lines and everyday life. These tasks are particularly challenging because they require robots to manipulate DLO with long-horizon planning and reliable skill execution. Successfully completing such tasks demands adapting to their nonlin

Shama Siddiqu, Indrakshi Dey

Vehicular Ad hoc Networks (VANETs) comprise of multi-priority hetero-genous nodes, both stationary and/or mobile. The data generated by these nodes may include messages relating to information, safety, entertainment, traffic management and emergency alerts. The data in the network needs dif-ferentiated service based on the priority/urgency. Media Access Cont

Penghao Wang, Yuhao Zhou, Mengxuan Wu, Panpan Zhang

State-space models (SSMs) have emerged as efficient alternatives to Transformers for sequence modeling, offering superior scalability through recurrent structures. However, their training remains costly and the ecosystem around them is far less mature than that of Transformers. Moreover, the structural heterogeneity between SSMs and Transformers makes it cha

Md Selim Reza, Sabrin Afroz, Mostafizer Rahman, Md Ashad Alam

Multi-omics data integration is crucial for understanding complex diseases, yet limited sample sizes, noise, and heterogeneity often reduce predictive power. To address these challenges, we introduce Omics-GAN, a Generative Adversarial Network (GAN)-based framework designed to generate high-quality synthetic multi-omics profiles while preserving biological r

Yuto Tomikawa, Masaki Uto

Difficulty-controllable question generation for reading comprehension has gained significant attention in the field of education as a fundamental tool for adaptive learning support. Although several neural question generation methods have recently succeeded in controlling difficulty, conventional approaches still face two major limitations. First, they canno

R. Can Aygun, Yehuda Afek, Anat Bremler-Barr, Leonard Kleinrock

With the goal of improving the security of Internet protocols, we seek faster, semi-automatic methods to discover new vulnerabilities in protocols such as DNS, BGP, and others. To this end, we introduce the LLM-Assisted Protocol Attack Discovery (LAPRAD) methodology, enabling security researchers with some DNS knowledge to efficiently uncover vulnerabilities

Wachara Fungwacharakorn, Gauvain Bourgne, Ken Satoh

Precedential constraint is one foundation of case-based reasoning in AI and Law. It generally assumes that the underlying set of precedents must be consistent. To relax this assumption, a generalized notion of the reason model has been introduced. While several argumentative explanation approaches exist for reasoning with precedents based on the traditional

Heng Xu, Zhiwei Yu, Chengze Du, Ying Zhou

Training Mixture-of-Experts (MoE) models introduces sparse and highly imbalanced all-to-all communication that dominates iteration time. Conventional load-balancing methods fail to exploit the deterministic topology of Rail architectures, leaving multi-NIC bandwidth underutilized. We present RailS, a distributed load-balancing framework that minimizes all-to

Marianna Molinari, Ilaria Angela Amantea, Marinella Quaranta, Guido Governatori

This study examines the performance of ChatGPT with an experiment in the legal domain. We compare the outcome with it a baseline using regular expressions (Regex), rather than focusing solely on the assessment against human performance. The study reveals that even if ChatGPT has access to the necessary knowledge and competencies, it is unable to assemble the

Mukul Lokhande, Narendra Singh Dhakad, Seema Chouhan, Akash Sankhe

Processing-in-memory (PIM) has emerged as the go to solution for addressing the von Neumann bottleneck in edge AI accelerators. However, state-of-the-art (SoTA) digital PIM approaches suffer from low compute density, primarily due to the use of bulky bit cells and transistor-heavy adder trees, which impose limitations on macro scalability and energy efficien

Naichung Conan Leung, Yunsong Wei

We observe that numerous symplectic resolutions can be expressed as intersections of twisted cotangent bundles. Additionally, their dual symplectic resolutions can be derived from intersections of dual twisted cotangent bundles. We determine the collection of fixed points for certain intersections that are Poisson slices, extending the computations of fixed

Yash Aggarwal

SMSS J0521-4351 is reportedly the most luminous quasar known to date, and assuming a mean radiative efficiency of 0.1, it is inferred to be the fastest-growing black hole, accreting approximately one solar mass per day. Assessing the implications of this assumption on the seed mass and inception time of J0529-4351, we show that the inferred accretion rate is

Soyoung Park, Sungsu Lim

Graph Neural Networks (GNNs) excel at learning from structured data, yet fairness in regression tasks remains underexplored. Existing approaches mainly target classification and representation-level debiasing, which cannot fully address the continuous nature of node-level regression. We propose FnRGNN, a fairness-aware in-processing framework for GNN-based n

Haiquan Zhao, Bei Xu

The spline adaptive filtering (SAF) algorithm-based information-theoretic learning has exhibited strong convergence performance in nonlinear system identification (NSI), establishing SAF as a promising framework for adaptive filtering. However, existing SAF-based methods suffer from performance degradation under generalized Gaussian noise (GGN) environment a

Jiwei Fu, Chunyu Yang

Metastasis is the leading cause of cancer-related mortality, yet most predictive models rely on shallow architectures and neglect patient-specific regulatory mechanisms. Here, we integrate classical machine learning and deep learning to predict metastatic potential across multiple cancer types. Gene expression profiles from the Cancer Cell Line Encyclopedia

Taras K. Oleksyk, Walter W. Wolfsberger, Karishma Chhugani, Yu-Ning Huang

Genomic approaches have revolutionized medical research, providing valuable insights into human physiology and disease. Despite major benefits from large collections of genomes, the lack of diversity in genomic data represents a significant challenge for advancing biomedical discovery and accessible health solutions worldwide. Establishing a national genomic

Chong Chen, Jiachi Chen, Lingfeng Bao, David Lo

Smart contract vulnerabilities, particularly improper Access Control that allows unauthorized execution of restricted functions, have caused billions of dollars in losses. GitHub hosts numerous smart contract repositories containing source code, documentation, and configuration files-these serve as intermediate development artifacts that must be compiled and

Jing-Wen Gao, Xiao-Song Yang

In this paper, we show that any finite simplicial complex is homeomorphic to the inverse limit of a sequence of finite posets, which is an extension of Claders result.

Yuanxi Li, Lei Yin

This study develops a comprehensive Artificial Intelligence (AI) Index with seven primary dimensions, designed for provincial-level and industry-specific analysis. We employ an anchor point method for data normalization, using fixed upper and lower bounds as benchmarks, and devise a hierarchical indicator weighting system that combines expert judgment with o

Yingtian Shi, Jinda Yang, Yuhan Wang, Yiwen Yin

The growing diversity of large language models (LLMs) means users often need to compare and combine outputs from different models to obtain higher-quality or more comprehensive responses. However, switching between separate interfaces and manually integrating outputs is inherently inefficient, leading to a high cognitive burden and fragmented workflows. To a

Danial Ebrahimzadeh, Sarah Sharif, Yaser Mike Banad

Predicting which hypothetical inorganic crystals can be experimentally realized remains a central challenge in accelerating materials discovery. SyntheFormer is a positive-unlabeled framework that learns synthesizability directly from crystal structure, combining a Fourier-transformed crystal periodicity (FTCP) representation with hierarchical feature extrac

Yuheng Wu, Xiangbo Gao, Quang Tau, Zhengzhong Tu

Collaborative perception enhances the reliability and spatial coverage of autonomous vehicles by sharing complementary information across vehicles, offering a promising solution to long-tail scenarios that challenge single-vehicle perception. However, the bandwidth constraints of vehicular networks make transmitting the entire feature map impractical. Recent

William J. Smith, Krystal Ruiz-Rocha, Kelly Holley-Bockelmann, Michela Mapelli

The growing number of binary black hole mergers detected through gravitational waves offers unprecedented insight into their underlying population, yet their astrophysical formation channels remain unresolved. We present a new method to distinguish binary black hole formation channels using their spatial clustering at cosmological scales. Employing the cosmo

Ziwei Wang, Jiayuan Su, Mengyu Zhou, Huaxing Zeng

Understanding and reasoning over complex spreadsheets remain fundamental challenges for large language models (LLMs), which often struggle with accurately capturing the complex structure of tables and ensuring reasoning correctness. In this work, we propose SheetBrain, a neuro-symbolic dual workflow agent framework designed for accurate reasoning over tabula

Mingfei Lu, Mengjia Wu, Jiawei Xu, Weikai Li

As a key to accessing research impact, citation dynamics underpins research evaluation, scholarly recommendation, and the study of knowledge diffusion. Citation prediction is particularly critical for newborn papers, where early assessment must be performed without citation signals and under highly long-tailed distributions. We identify two key research gaps

Yimeng Zhang, Jiri Gesi, Ran Xue, Tian Wang

LLMs have recently demonstrated strong potential in simulating online shopper behavior. Prior work has improved action prediction by applying SFT on action traces with LLM-generated rationales, and by leveraging RL to further enhance reasoning capabilities. Despite these advances, current approaches rely on text-based inputs and overlook the essential role o

Dandan Chen, Siyu Yin

In 1984, Andrews introduced the family of partition functions \(c\phi_k(n)\), which counts the number of generalized Frobenius partitions of \(n\) with \(k\) colors. In previous work, we proved a conjecture on congruences for \(c\phi_6(n)\) modulo powers of 3. In this paper, we consider the \((6,0)\)-colored Frobenius partition functions \(c\psi_{6,0}(n)\).

Safa Ben Atitallah, Maha Driss, Henda Ben Ghezela

The Internet of Things (IoT) has recently proliferated in both size and complexity. Using multi-source and heterogeneous IoT data aids in providing efficient data analytics for a variety of prevalent and crucial applications. To address the privacy and security concerns raised by analyzing IoT data locally or in the cloud, distributed data analytics techniqu

Xuyuan Xiong, Pedro Chumpitaz-Flores, Kaixun Hua, Cheng Hua

Interpretable reinforcement learning policies are essential for high-stakes decision-making, yet optimizing decision tree policies in Markov Decision Processes (MDPs) remains challenging. We propose SPOT, a novel method for computing decision tree policies, which formulates the optimization problem as a mixed-integer linear program (MILP). To enhance efficie

Alok Dutta, Nilanjana Roy, Rhythm Sen, Sougata Dutta

This paper presents the design and implementation of a user-friendly, automated web application that simplifies and optimizes the web scraping process for non-technical users. The application breaks down the complex task of web scraping into three main stages: fetching, extraction, and execution. In the fetching stage, the application accesses target website

Behnam Agahi, Hamed Farbeh

With the growing use of embedded systems in various industries, the need for automated platforms for the development and deployment of customized Linux-based operating systems has become more important. This research was conducted with the aim of designing and implementing an integrated and reproducible infrastructure for the development, building, and testi

Chen Ma, Jing Jiao, Shuyu Liang, Junhu Fu

Foundation models for medical imaging demonstrate superior generalization capabilities across diverse anatomical structures and clinical applications. Their outstanding performance relies on substantial computational resources, limiting deployment in resource-constrained clinical environments. This paper presents TinyUSFM, the first lightweight ultrasound fo

Cancan Shao, Rixin Xie, Zhecun Shi, Linjun Wang

In our recent work (J. Phys. Chem. Lett. 2023, 14, 7680), we utilized the exact quantum dynamics results as references and proposed a general machine learning method to obtain the optimal decoherence time formula for surface hopping simulation. Here, we extend this strategy from one-dimensional systems to the much more intricate scenarios with multiple nucle

Dongming Jin, Zhi Jin, Xiaohong Chen, Zheng Fang

Cyber-physical systems (CPSs) are characterized by a deep integration of the information space and the physical world, which makes the extraction of requirements concerns more challenging. Some automated solutions for requirements concern extraction have been proposed to alleviate the burden on requirements engineers. However, evaluating the effectiveness of

Annan Yu, Danielle C. Maddix, Boran Han, Xiyuan Zhang

Time series foundation models (TSFMs) are a class of potentially powerful, general-purpose tools for time series forecasting and related temporal tasks, but their behavior is strongly shaped by subtle inductive biases in their design. Rather than developing a new model and claiming that it is better than existing TSFMs, e.g., by winning on existing well-esta

Hongyu Wang, Yizhi Zhang

This paper studies the structure of core sets under different similarity classes. We investigate the influence of factors of the minimal polynomial with different degrees on the structure of core sets. When $F$ is a finite field of prime order, we study the upper bound on the size of a non-core set in a similarity class in $M_n(F)$. We prove that as $|F|$ in