May 2025 arXiv papers — page 16

Chan-Wei Hu, Yueqi Wang, Shuo Xing, Chia-Ju Chen

Large Vision-Language Models (LVLMs) have made remarkable strides in multimodal tasks such as visual question answering, visual grounding, and complex reasoning. However, they remain limited by static training data, susceptibility to hallucinations, and inability to verify claims against up-to-date, external evidence, compromising their performance in dynami

Benedek Kovács

The author, together with Nagy, studied the following problem on unavoidable intersections of given size in binary affine spaces. Given an $m$-element set $S\subseteq \mathbb{F}_2^n$, is there guaranteed to be a $[k,t]$-flat, that is, a $k$-dimensional affine subspace of $\mathbb{F}_2^n$ containing exactly $t$ points of $S$? Such problems can be viewed as ge

Tomáš Novák, Carlos Guerra-Yánez, Matěj Holubička, Josef Vojtěch

Polarization-sensitive receivers for single photons are of crucial importance in various applications within the fields of quantum communication and quantum sensing, and are more commonly implemented in free-space optics rather than in optical fibers. This is primarily due to the unpredictable and varying birefringence in single-mode optical fibers. We prese

Christopher Cappiello, Tansu Daylan

The search for dark matter is one of the crucial open problems in both particle physics and cosmology. If dark matter scatters with Standard Model particles, it could accumulate inside the Earth and begin to annihilate, producing heat within the Earth's core. While past work has been done on the effect that this heat would have once it reached the surface, w

Lokesh Krishna, Sheng Cheng, Junheng Li, Naira Hovakimyan

The deployment of robot controllers is hindered by modeling discrepancies due to necessary simplifications for computational tractability or inaccuracies in data-generating simulators. Such discrepancies typically require ad-hoc tuning to meet the desired performance, thereby ensuring successful transfer to a target domain. We propose a framework for automat

Yu He, Ellen Vitercik

Neural Algorithmic Reasoning (NAR) trains neural networks to simulate classical algorithms, enabling structured and interpretable reasoning over complex data. While prior research has predominantly focused on learning exact algorithms for polynomial-time-solvable problems, extending NAR to harder problems remains an open challenge. In this work, we introduce

Isaiah A. Moses, Chen Chen, Joan M. Redwing, Wesley F. Reinhart

The growth and characterization of materials using empirical optimization typically requires a significant amount of expert time, experience, and resources. Several complementary characterization methods are routinely performed to determine the quality and properties of a grown sample. Machine learning (ML) can support the conventional approaches by using hi

Hamidou Tembine, Tyrone E. Duncan, Bozenna Pasik-Duncan

We study the integration of Rosenblatt noise into stochastic systems, control theory, and mean-field-type game theory, addressing the limitations of traditional Gaussian and Markovian models. Empirical evidence from various domains, including water demand, e-commerce, power grid operations, wireless channels, and agricultural supply chains, demonstrates the

Yijun Yuan

Let $p\geq 3$ be a prime number and $K$ be a finite extension of $\mathbf{Q}_p$ with uniformizer $\pi_K$. In this article, we introduce two multivariable period rings $\mathbf{A}_{\mathfrak{F},K}^{\operatorname{np}}$ and $\mathbf{A}_{\mathfrak{F},K}^{\operatorname{np},\operatorname{c}}$ for the \'etale $(\varphi,\Gamma_{\mathfrak{F},K})$-modules of $p$-adic

Jiacheng Xie, Yang Yu, Ziyang Zhang, Shuai Zeng

Traditional Chinese Medicine (TCM), as an effective alternative medicine, has been receiving increasing attention. In recent years, the rapid development of large language models (LLMs) tailored for TCM has highlighted the urgent need for an objective and comprehensive evaluation framework to assess their performance on real-world tasks. However, existing ev

Kamyar Barakati, Yu Liu, Hiroshi Funakubo, Sergei V. Kalinin

Domain-wall dynamics in ferroelectric materials are strongly position-dependent since each polar interface is locked into a unique local microstructure. This necessitates spatially resolved studies of the wall-pinning using scanning-probe microscopy techniques. The pinning centers and preexisting domain walls are usually sparse within image plane, precluding

Jiashun Liu, Zihao Wu, Johan Obando-Ceron, Pablo Samuel Castro

Deep reinforcement learning (RL) agents frequently suffer from neuronal activity loss, which impairs their ability to adapt to new data and learn continually. A common method to quantify and address this issue is the tau-dormant neuron ratio, which uses activation statistics to measure the expressive ability of neurons. While effective for simple MLP-based a

Jonathan Panuelos, Eitan Grinspun, David Levin

We present a novel discretization of coupled compressible fluid and thin deformable structures that provides sufficient and necessary leakproofness by preserving the path connectedness of the fluid domain. Our method employs a constrained Voronoi-based spatial partitioning combined with Godunov-style finite-volume time integration. The fluid domain is discre

Chris Mingard, Lukas Seier, Niclas Göring, Andrei-Vlad Badelita

Deep neural networks are renowned for their ability to generalise well across diverse tasks, even when heavily overparameterized. Existing works offer only partial explanations (for example, the NTK-based task-model alignment explanation neglects feature learning). Here, we provide an end-to-end, analytically tractable case study that links a network's induc

Sean Foley, Hong Nguyen, Jihwan Lee, Sudarsana Reddy Kadiri

Although many previous studies have carried out multimodal learning with real-time MRI data that captures the audio-visual kinematics of the vocal tract during speech, these studies have been limited by their reliance on multi-speaker corpora. This prevents such models from learning a detailed relationship between acoustics and articulation due to considerab

Andrew Cornfeld, Ashley Miller, Mercedes Mora-Figueroa, Kurt Samuels

Television networks face high financial risk when making programming decisions, often relying on limited historical data to forecast episodic viewership. This study introduces a machine learning framework that integrates natural language processing (NLP) features from over 25000 television episodes with traditional viewership data to enhance predictive accur

Hailiang Liu, Zhongming Wang, Peimeng Yin

In earlier work [H. Liu and Z. Wang, J. Comput. Phys., 328(2017)], an arbitrary high-order conservative and energy-dissipative direct discontinuous Galerkin (DDG) scheme was developed. Although this scheme enforced solution positivity using cell averages as reference values, it lacked a theoretical guarantee for the positivity of those cell averages. In this

Shi Qiru

This paper proposes a hypothetical model for the dual role of respiratory aerosols and inflammatory exudates in the dynamics and progression of SARS-CoV-2 lung infection. Starting from a new paradigm in infectious disease transmission, we reflect on the often-overlooked role of physical transmission media within the host individual. The hypothesis posits tha

Daniel Gerth, Kirk M. Soodhalter

We consider iterative methods for solving linear ill-posed problems with compact operator and right-hand side only available via noise-polluted measurements. Conjugate gradients (CG) applied to the normal equations with an appropriate stopping rule and CG applied to the system solving for a Tikhonov-regularized solution (CGT) $(A^\ast A + c I_{\mathcal{X}})

Yilong Wang, Tianxiang Zhao, Zongyu Wu, Suhang Wang

Graph neural networks (GNNs) have shown great ability for node classification on graphs. However, the success of GNNs relies on abundant labeled data, while obtaining high-quality labels is costly and challenging, especially for newly emerging domains. Hence, unsupervised domain adaptation (UDA), which trains a classifier on the labeled source graph and adap

Elpiniki Maria Lygizou, Mónika Farsang, Radu Grosu

Transformers excel across a large variety of tasks but remain susceptible to corrupted inputs, since standard self-attention treats all query-key interactions uniformly. Inspired by lateral inhibition in biological neural circuits and building on the recent use by the Differential Transformer's use of two parallel softmax subtraction for noise cancellation,

Zixun Huang, Cho-Ying Wu, Yuliang Guo, Xinyu Huang

3D Gaussian Splatting (3DGS) achieves an appealing balance between rendering quality and efficiency, but relies on approximating 3D Gaussians as 2D projections--an assumption that degrades accuracy, especially under generic large field-of-view (FoV) cameras. Despite recent extensions, no prior work has simultaneously achieved both projective exactness and re

Shane P. Kelly, Eric Kleinherbers, Yanyan Zhu, Yaroslav Tserkovnyak

Correlated emission of light offer a potential avenue for entanglement generation between atomic spins, with potential application for sensing and quantum memory. In this work, we investigate the conditions for the correlated emission by color centers into an electronic bath of conduction electrons. Unlike emission into bosonic modes, electrons can absorb en

Felipe Hauschild Grings, Gustavo Zanatta Bruno, Lucio Rene Prade, Cristiano Bonato Both

With 5G's rapid global uptake, demand for agile private networks has exploded. A defining beyond-5G capability is network slicing. 3GPP specifies three core slice categories, massive Machine-Type Communications (mMTC), enhanced Mobile Broadband (eMBB), and Ultra-Reliable Low-Latency Communications (URLLC), while ETSI's Zero-Touch Network and Service Manageme

Mikhail R. Gabdullin

Let $\omega^*(n) = \{d|n: d=p-1, \mbox{$p$ is a prime}\}$. We show that, for each integer $k\geq2$, $$ \sum_{n\leq x}\omega^*(n)^k \asymp x(\log x)^{2^k-k-1}, $$ where the implied constant may depend on $k$ only. This confirms a recent conjecture of Fan and Pomerance. Our proof uses a combinatorial identity for the least common multiple, viewed as a multipli

A. Geminardi, P. Esposito, G. Bernardi, M. Pilia

Context. The radio emission from magnetars is poorly understood and poorly characterized observationally, in particular for what concerns single pulses and sporadic events. The interest in it was boosted by the detection in 2020 of an extremely bright ms radio signal from the Galactic magnetar designated Soft Gamma Repeater (SGR) SGR J1935+2154, which occurr

Guangtao Zheng, Wenqian Ye, Aidong Zhang

Deep neural networks often develop spurious bias, reliance on correlations between non-essential features and classes for predictions. For example, a model may identify objects based on frequently co-occurring backgrounds rather than intrinsic features, resulting in degraded performance on data lacking these correlations. Existing mitigation approaches typic

Tanish Baranwal, Srihari Varada, Santanu Das, Mohammad R. Haider

In this article, we present a novel redundancy scheme to realize a fault-tolerant IoT structure for application in high-reliability systems. The proposed fault-tolerant structure uses a centralized data fusion block and triplicated IoT devices, along with software-based "digital twins", that duplicate the function of each of the sensors. In case of a fault i

Amro M. Farid, Amirreza Hosseini, John C. Little

A defining feature of twenty first century engineering challenges is their inherent complexity, demanding the convergence of knowledge across diverse disciplines. Establishing consistent methodological foundations for engineering systems remains a challenge -- one that both systems engineering and network science have sought to address. Model-based systems e

Amirreza Hosseini, Amro M. Farid

Megaprojects are large-scale, complex, and one-off engineering endeavors that require significant investments from a public or private sector. Such projects generally cost more than a billion dollars, take many years to develop and construct, involve stakeholders both in the public and private sectors, and impact millions of people. Most of the extant megapr

Tanish Baranwal, Arnab Das, Srihari Varada, Santanu Das

The growing adoption of IoT systems in industries like transportation, banking, healthcare, and smart energy has increased reliance on sensor networks. However, anomalies in sensor readings can undermine system reliability, making real-time anomaly detection essential. While a large body of research addresses anomaly detection in IoT networks, few studies fo

Zdzisław Brzeźniak, Tomasz Kosmala, Elżbieta Motyl, Paul Razafimandimby

In this paper we prove the existence of weak martingale solutions to the stochastic Navier-Stokes Equations driven by pure jump L\'evy processes. Our proof consists of two parts. In the first one, mostly classical, we recall a priori estimates, from the paper by the third named author, for solutions to suitable constructed Galerkin approximations and we use

Vishnu Ramineni, Balaji Shesharao Ingole, Nikhil Kumar Pulipeta, Balakrishna Pothineni

Modern healthcare facilities demand digital accessibility to guarantee equal access to telemedicine platforms, online pharmacy services, and health monitoring devices that can be worn or are handy. With the rising call for the implementation of robust digital healthcare solutions, people with disabilities encounter impediments in their endeavor of managing a

Matteo Menniti, Naëmi Leo, Pedro Villalba-González, Matteo Pancaldi

Multi-domain states of square artificial spin ice show a range of different morphologies ranging from simple stripe-like domains to more organically shaped coral domains. To model the relevant dynamics leading to the emergence of such diverse domain structures, simplified descriptions of the switching behavior of individual nanomagnets are necessary. In this

Yuexing Hao, Kumail Alhamoud, Hyewon Jeong, Haoran Zhang

Large Language Models (LLMs) have demonstrated remarkable performance on various medical question-answering (QA) benchmarks, including standardized medical exams. However, correct answers alone do not ensure correct logic, and models may reach accurate conclusions through flawed processes. In this study, we introduce the MedPAIR (Medical Dataset Comparing Ph

Vishnu Ramineni, Shivareddy Devarapalli, Balakrishna Pothineni, Prema Kumar Veerapaneni

Modern healthcare domain incorporates a feature of digital accessibility to ensure seamless flow of online services for the patients. However, this feature of digital accessibility poses a challenge particularly for patients with disabilities. To eradicate this issue and provide immersive and user-friendly experiences, evolving technologies like Augmented Re

Léo andéol, Luca Mossina, Adrien Mazoyer, Sébastien Gerchinovitz

Recent advances in object detectors have led to their adoption for industrial uses. However, their deployment in safety-critical applications is hindered by the inherent lack of reliability of neural networks and the complex structure of object detection models. To address these challenges, we turn to Conformal Prediction, a post-hoc predictive uncertainty q

Amel Gader, Alsayed Algergawy

Knowledge graph completion aims to address the gaps of knowledge bases by adding new triples that represent facts. The complexity of this task depends on how many parts of a triple are already known. Instance completion involves predicting the relation-tail pair when only the head is given (h, ?, ?). Notably, modern knowledge bases often contain entity descr

Vishnu Ramineni, Aditya Gupta, Balakrishna Pothineni, Isan Sahoo

The swift evolution of telehealth has revolutionized how medical professionals deliver healthcare services and boost convenience and accessibility. Yet, the Medicaid population encounters several impediments in utilizing facilities especially owing to poor internet connectivity, less awareness about digital platforms, and a shortage of assistive technologies

Bo Wu, Sid Wang, Yunhao Tang, Jia Ding

Reinforcement Learning (RL) has become the most effective post-training approach for improving the capabilities of Large Language Models (LLMs). In practice, because of the high demands on latency and memory, it is particularly challenging to develop an efficient RL framework that reliably manages policy models with hundreds to thousands of billions of param

Yasaman Jafari, Zixian Wang, Leon Bergen, Taylor Berg-Kirkpatrick

We investigate whether hidden states from Structured State Space Models (SSMs) can be merged post hoc to support downstream reasoning. Inspired by model souping, we study document souping, a strategy where documents are encoded independently, and their representations are pooled, via simple operations like averaging, into a single context state. This approac

Sergei S. Kuzmin, Ivan V. Dyakonov, Stanislav S. Straupe

We have developed an algorithm that constructs a model of a reconfigurable optical interferometer, independent of specific architectural constraints. The programming of unitary transformations on the interferometer's optical modes relies on either an analytical method for deriving the unitary matrix from a set of phase shifts or an optimization routine when

Wei-Cheng Liao, Haoyu Liu, Weilun Tan, Josiah Keagy

Electrical transport measurements in heterostructures of antiferromagnetic Cr2O3 bulk crystals and a thin Pt layer exhibit sharp responses as the N\'eel vector of the Cr2O3 undergoes the spin-flop transition. This abrupt change can arise from several distinct mechanisms including magnetostriction, proximity-induced anomalous Hall, spin Hall anomalous Hall, a

Ziming Zhao, ChengAo Shen, Hanghang Tong, Dongjin Song

Transformer-based models have gained increasing attention in time series research, driving interest in Large Language Models (LLMs) and foundation models for time series analysis. As the field moves toward multi-modality, Large Vision Models (LVMs) are emerging as a promising direction. In the past, the effectiveness of Transformer and LLMs in time series ha

Sixu Li, Yang Zhou

This paper presents a framework grounded in the theory of describing function (DF) and incremental-input DF to theoretically analyze the nonlinear oscillatory response of automated vehicles (AVs) car-following (CF) amidst traffic oscillations, considering the limits of traffic state and control input. While prevailing approaches largely ignore these limits (

Kateryna Akhynko, Oleksandr Kosovan, Mykola Trokhymovych

This paper presents one of the top-performing solutions to the UNLP 2025 Shared Task on Detecting Manipulation in Social Media. The task focuses on detecting and classifying rhetorical and stylistic manipulation techniques used to influence Ukrainian Telegram users. For the classification subtask, we fine-tuned the Gemma 2 language model with LoRA adapters a

Numair Nadeem, Muhammad Hamza Asad, Saeed Anwar, Abdul Bais

Semantic segmentation of crops and weeds is crucial for site-specific farm management; however, most existing methods depend on labor intensive pixel-level annotations. A further challenge arises when models trained on one field (source domain) fail to generalize to new fields (target domain) due to domain shifts, such as variations in lighting, camera setup

Chenbin Pan, Wenbin He, Zhengzhong Tu, Liu Ren

The recent explosive interest in the reasoning capabilities of large language models, such as DeepSeek-R1, has demonstrated remarkable success through reinforcement learning-based fine-tuning frameworks, exemplified by methods like Group Relative Policy Optimization (GRPO). However, such reasoning abilities remain underexplored and notably absent in vision f

Jose A. Cobano, L. Merino, F. Caballero

This paper presents the FS-Planner, a fast graph-search planner based on a modified Lazy Theta* algorithm that exploits the analytical properties of Euclidean Distance Fields (EDFs). We introduce a new cost function that integrates an EDF-based term proven to satisfy the triangle inequality, enabling efficient parent selection and reducing computation time w

Sangwon Jung, Alex Oesterling, Claudio Mayrink Verdun, Sajani Vithana

Text-to-image (T2I) generative models can create vivid, realistic images from textual descriptions. As these models proliferate, they expose new concerns about their ability to represent diverse demographic groups, propagate stereotypes, and efface minority populations. Despite growing attention to the "safe" and "responsible" design of artificial intelligen

Bhavya Vasudeva, Jung Whan Lee, Vatsal Sharan, Mahdi Soltanolkotabi

Adam is the de facto optimization algorithm for several deep learning applications, but an understanding of its implicit bias and how it differs from other algorithms, particularly standard first-order methods such as (stochastic) gradient descent (GD), remains limited. In practice, neural networks (NNs) trained with SGD are known to exhibit simplicity bias

Akila Herath, Chen-Ching Liu, Junho Hong, Mansi Girdhar

A Cyber-Physical System (CPS) testbed serves as a powerful platform for testing and validating cyber intrusion detection and mitigation strategies in substations. This study presents the design and development of a CPS testbed that can effectively assess the real-time dynamics of a substation. Cyber attacks exploiting IEC 61850-based SV and GOOSE protocols a

G. Zambito, G. Ferrando, M. Barelli, M. Ceccardi

Nanoscale tailoring of the optoelectronic response of 2D Transition Metal Dichalcogenides semiconductor layers (TMDs) has been achieved thanks to a novel strain engineering approach based on the grayscale thermal-Scanning Probe Lithography (t-SPL). This method allows the maskless nanofabrication of locally strained 2D MoS2-Au lateral heterojunction nanoarray

Kaiyuan Zhang, Zian Su, Pin-Yu Chen, Elisa Bertino

Large Language Model (LLM) agents show considerable promise for automating complex tasks using contextual reasoning; however, interactions involving multiple agents and the system's susceptibility to prompt injection and other forms of context manipulation introduce new vulnerabilities related to privacy leakage and system exploitation. This position paper a

Milena Weiershausen

Symplectic structures on higher objects like Lie groupoids have been studied for some time now, but not all of the proposed definitions are preserved under Morita equivalence of Lie groupoids, in turn giving rise to a consistent notion of symplectic stacks. Recently, this concept has been generalized to m-shifted symplectic forms on Lie n-groupoids, which ar

Matthew Raffel, Victor Agostinelli, Lizhong Chen

This paper discusses the construction, fine-tuning, and deployment of BeaverTalk, a cascaded system for speech-to-text translation as part of the IWSLT 2025 simultaneous translation task. The system architecture employs a VAD segmenter for breaking a speech stream into segments, Whisper Large V2 for automatic speech recognition (ASR), and Gemma 3 12B for sim

Cheng-Lin Wu, Hyomin Choi, Ivan V. Bajić

Advancements in text-to-image generative AI with large multimodal models are spreading into the field of image compression, creating high-quality representation of images at extremely low bit rates. This work introduces novel components to the existing multimodal image semantic compression (MISC) approach, enhancing the quality of the generated images in ter

Anjali Singh, Zhitong Guan, Soo Young Rieh

The growing use of Generative AI (GenAI) conversational search tools has raised concerns about their effects on people's metacognitive engagement, critical thinking, and learning. As people increasingly rely on GenAI to perform tasks such as analyzing and applying information, they may become less actively engaged in thinking and learning. This study examine

Jeffrey Yelton

We show under a mild hypothesis that given field elements $a_0, \dots, a_m \in K$, there always exists a degree-$m$ polynomial whose $n$th power whose degree-$jn$ coefficient is equal to $a_j$ for $0 \leq j \leq m$. We provide an alternate proof for the $n = 2$ case which is more constructive.

Guangchen Lan, Huseyin A. Inan, Sahar Abdelnabi, Janardhan Kulkarni

As the era of autonomous agents making decisions on behalf of users unfolds, ensuring contextual integrity (CI) -- what is the appropriate information to share while carrying out a certain task -- becomes a central question to the field. We posit that CI demands a form of reasoning where the agent needs to reason about the context in which it is operating. T

Alexandre Bonlarron, Florian Régin, Elisabetta De Maria, Jean-Charles Régin

Large Language Models (LLMs) excel at generating fluent text but struggle to enforce external constraints because they generate tokens sequentially without explicit control mechanisms. GenCP addresses this limitation by combining LLM predictions with Constraint Programming (CP) reasoning, formulating text generation as a Constraint Satisfaction Problem (CSP)

Bastien Anézo, Denis Arčon, Chris Ewels

The interaction between surface-lying nitrogen-substituted fullerenes (radical azafullerene, C$_{59}$N$^\bullet$) with sub-surface negative nitrogen-vacancy complexes (NV$^-$) in diamond is investigated using first principles calculations. We consider (2$\times$1) reconstructed (001) oriented diamond surfaces with both H- and F-surface termination. The charg

Diego Pollini, Bruna V. Guterres, Rodrigo S. Guerra, Ricardo B. Grando

The integration of Large Language Models (LLMs), such as GPT, in industrial robotics enhances operational efficiency and human-robot collaboration. However, the computational complexity and size of these models often provide latency problems in request and response times. This study explores the integration of the ChatGPT natural language model with the Robo

Aziz Kharoof, Cihan Okay

We develop a resource theory of contextuality within the framework of symmetric monoidal categories, extending recent simplicial approaches to quantum contextuality. Building on the theory of simplicial distributions, which integrates homotopy-theoretic structures with probability, we introduce event scenarios as a functorial generalization of presheaf-theor

Hidetaka Kamigaito, Ying Zhang, Jingun Kwon, Katsuhiko Hayashi

Transformers deliver outstanding performance across a wide range of tasks and are now a dominant backbone architecture for large language models (LLMs). Their task-solving performance is improved by increasing parameter size, as shown in the recent studies on parameter scaling laws. Although recent mechanistic-interpretability studies have deepened our under

Efrén López-Morales, Ulysse Planta, Gabriele Marra, Carlos González

Satellites are the backbone of several mission-critical services that enable our modern society to function, for example, GPS. For years, satellites were assumed to be secure because of their indecipherable architectures and the reliance on security by obscurity. However, technological advancements have made these assumptions obsolete, paving the way for pot

Laksh Patel, Neel Shanbhag

Distributed supply-chain optimization demands algorithms that can cope with unreliable communication, unbounded messaging delays, and geographically dispersed agents while still guaranteeing convergence with provable rates. In this work, we introduce DAPD-SCO (Distributed Asynchronous Primal-Dual Optimization for Supply-Chain Networks), a fully asynchronous

Nokimul Hasan Arif, Shadman Rabby, Md Hefzul Hossain Papon, Sabbir Ahmed

Visual hallucinations in Large Language Models (LLMs), where the model generates responses that are inconsistent with the visual input, pose a significant challenge to their reliability, particularly in contexts where precise and trustworthy outputs are critical. Current research largely emphasizes post-hoc correction or model-specific fine-tuning strategies

Agnideep Aich, Sameera Hewage, Md Monzur Murshed, Ashit Baran Aich

In this paper, we introduce the A2 Copula Spatial Bayesian Neural Network (A2-SBNN), a predictive spatial model designed to map coordinates to continuous fields while capturing both typical spatial patterns and extreme dependencies. By embedding the dual-tail novel Archimedean copula viz. A2 directly into the network's weight initialization, A2-SBNN naturall

Priya Kasimbeg, Vincent Roulet, Naman Agarwal, Sourabh Medapati

Despite major advances in methodology, hyperparameter tuning remains a crucial (and expensive) part of the development of machine learning systems. Even ignoring architectural choices, deep neural networks have a large number of optimization and regularization hyperparameters that need to be tuned carefully per workload in order to obtain the best results. I

Javier Conde, Miguel González, María Grandury, Gonzalo Martínez

The evaluation of LLMs has so far focused primarily on how well they can perform different tasks such as reasoning, question-answering, paraphrasing, or translating. For most of these tasks, performance can be measured with objective metrics, such as the number of correct answers. However, other language features are not easily quantified. For example, arous

Amanda Chan, Catherine Di, Joseph Rupertus, Gary Smith

Crowd work platforms like Amazon Mechanical Turk and Prolific are vital for research, yet workers' growing use of generative AI tools poses challenges. Researchers face compromised data validity as AI responses replace authentic human behavior, while workers risk diminished roles as AI automates tasks. To address this, we propose a hybrid framework using dig

ChengAo Shen, Wenchao Yu, Ziming Zhao, Dongjin Song

Time series, typically represented as numerical sequences, can also be transformed into images and texts, offering multi-modal views (MMVs) of the same underlying signal. These MMVs can reveal complementary patterns and enable the use of powerful pre-trained large models, such as large vision models (LVMs), for long-term time series forecasting (LTSF). Howev

Vaishnav Ramesh, Junliang Liu, Haining Wang, Md Jahidul Islam

A long-held challenge in no-reference image quality assessment (NR-IQA) learning from human subjective perception is the lack of objective generalization to unseen natural distortions. To address this, we integrate a novel Depth-Guided cross-attention and refinement (Depth-CAR) mechanism, which distills scene depth and spatial features into a structure-aware

Wonjun Yi, Wonho Jung, Hyeonuk Nam, Kangmin Jang

The increasing complexity of rotating machinery and the diversity of operating conditions, such as rotating speed and varying torques, have amplified the challenges in fault diagnosis in scenarios requiring domain adaptation, particularly involving compound faults. This study addresses these challenges by introducing a novel multi-output classification (MOC)

Jad Bendarkawi, Ashley Ponce, Sean Mata, Aminah Aliu

Group conversations are valuable for second language (L2) learners as they provide opportunities to practice listening and speaking, exercise complex turn-taking skills, and experience group social dynamics in a target language. However, most existing Augmented Reality (AR)-based conversational learning tools focus on dyadic interactions rather than group di

Shital Lawande, Kuldeep Saha

We give an example of a smooth characteristic embedding of a torus in $\s^2 \times \s^2 \# \s^1 \times \s^3$ such that there exists no diffeomorphism of the ambient $4$-manifold that induces the Dehn twist along a meridian of the torus, but there exists a homeomorphism of the ambient $4$-manifold, isotopic to identity, that induces the Dehn twist. As an appl

Ali Enayat

In 1950, Novak and Mostowski showed that GB (Gödel-Bernays theory of classes) is conservative over ZF, and therefore by Gödel's second incompleteness theorem the consistency of ZF is unprovable in GB. In the same year Mostowski unveiled a contrasting result: GB provides a truth-definition for ZF-formulae. Here we first give an expository account of Mosto

Pranav Rao, Maryam Taj, Alex Mariakakis, Joseph Jay Williams

Existing stress-management tools fail to account for the timing and contextual specificity of students' daily lives, often providing static or misaligned support. Digital calendars contain rich, personal indicators of upcoming responsibilities, yet this data is rarely leveraged for adaptive wellbeing interventions. In this short paper, we explore how large l

Yinong Oliver Wang, Nivedha Sivakumar, Falaah Arif Khan, Rin Metcalf Susa

The recent rapid adoption of large language models (LLMs) highlights the critical need for benchmarking their fairness. Conventional fairness metrics, which focus on discrete accuracy-based evaluations (i.e., prediction correctness), fail to capture the implicit impact of model uncertainty (e.g., higher model confidence about one group over another despite s

Cassie Grace, Klaus Metsch, Geertrui Van de Voorde

A partial affine plane of order $n$ is a point-line incidence structure with $n^2$ points and $n$ points on each line, such that every two lines meet in at most one point. In this paper, we show that a partial affine plane of order $n$, $n$ sufficiently large, in which parallelism is an equivalence relation, containing more than $n^2-\sqrt{n}$ lines, can be

Digvijay Singh, Rahul Shukla, Karunesh Kumar Singh

This article starts with the fundamental theory of stochastic type convergence and the significance of uniform integrability in the context of expectation value. A novel probabilistic sampling kantorovich (PSK-operators) is established with the help of classical sampling operators (SK-operators). We establish the proof of the fundamental theorem of approxima

Maggie Wang, Ella Colby, Jennifer Okwara, Varun Nagaraj Rao

Public opinion shapes policy, yet capturing it effectively to surface diverse perspectives remains challenging. This paper introduces PolicyPulse, an LLM-powered interactive system that synthesizes public experiences from online community discussions to help policy researchers author memos and briefs, leveraging curated real-world anecdotes. Given a specific

Farzad Farhadzadeh, Debasmit Das, Shubhankar Borse, Fatih Porikli

We introduce ProLoRA, enabling zero-shot adaptation of parameter-efficient fine-tuning in text-to-image diffusion models. ProLoRA transfers pre-trained low-rank adjustments (e.g., LoRA) from a source to a target model without additional training data. This overcomes the limitations of traditional methods that require retraining when switching base models, of

Chuan-Shen Hu

Defining cellular sheaves beyond graph structures, such as on simplicial complexes containing higher-dimensional simplices, is an essential and intriguing topic in topological data analysis (TDA) and the development of sheaf neural networks. In this paper, we explore methods for constructing non-trivial cellular sheaves on spaces that include structures of d

Weijian Zhang, Hashan K. Weerasooriya, Stanley Chan

Efficient simulation of photon registrations in single-photon LiDAR (SPL) is essential for applications such as depth estimation under high-flux conditions, where hardware dead time significantly distorts photon measurements. However, the conventional wisdom is computationally intensive due to their inherently sequential, photon-by-photon processing. In this

L. M. Lerman, R. Mazrooei-Sebdani, N. E. Kulagin

The double Hamiltonian Hopf bifurcation is studied, i.e. a generic two-parametric unfolding of a smooth Hamiltonian system with four degrees of freedom which has at the critical value of parameters the equilibrium with two pairs of double non semi-simple pure imaginary eigenvalues $\pm i\omega_1,$ $\pm i\omega_2,$ $\omega_1\ne \omega_2$ under an assumption o

Mingyang Mao, Mariela M. Perez-Cabarcas, Utteja Kallakuri, Nicholas R. Waytowich

To effectively engage in human society, the ability to adapt, filter information, and make informed decisions in ever-changing situations is critical. As robots and intelligent agents become more integrated into human life, there is a growing opportunity-and need-to offload the cognitive burden on humans to these systems, particularly in dynamic, information

Christian de Ronde

The notion of quantum state plays a fundamental role within the Standard account of Quantum Mechanics (SQM) as established by Dirac and von Neumann during 1930s and up to the present. In this work we expose the deep inconsistencies that exist within the multiple definitions of the notion of quantum state that are provided within this axiomatic formulation. A

Preet Mishra, Shyam Kumar, Sapna Ratan Shah, R. K. Brojen Singh

Cell proliferation and diffusion can be modeled through reaction-diffusion systems describing the space-time evolution of a density variable. In this work, we present non-linear transformations of heat equation solutions to model cellular growth and diffusion using a Richards growth function. The solutions are obtained by using two-variable Hermite Polynomia

Vishal Dey, Xiao Hu, Xia Ning

In real-world drug design, molecule optimization requires selectively improving multiple molecular properties up to pharmaceutically relevant levels, while maintaining others that already meet such criteria. However, existing computational approaches and instruction-tuned LLMs fail to capture such nuanced property-specific objectives, limiting their practica

J. M. Borrero, A. Pastor Yabar, M. Schmassmann, M. Rempel

Sunspots survive on the solar surface for time-scales ranging from days to months. This requires them to be in an equilibrium involving magnetic fields and hydrodynamic forces. Unfortunately, theoretical models of sunspot equilibrium are very simplified as they assume that spots are static and possess a self-similar and axially symmetric magnetic field. Thes

Amalia Puente, Diego Radillo-Ochoa, C. A. Terrero-Escalante

Complex systems often exhibit highly structured network topologies that reflect functional constraints. In this work, we investigate how, under varying combinations of system-wide selection rules and special agents, different classes of random processes give rise to global order, with a focus restricted to finite-size networks. Using the large-$N$ Erdos-Reny

Vahid Danesh, Paul Arauz, Maede Boroji, Andrew Zhu

Pelvic bone tumor resections remain significantly challenging due to complex three-dimensional anatomy and limited surgical visualization. Current navigation systems and patient-specific instruments, while accurate, present limitations including high costs, radiation exposure, workflow disruption, long production time, and lack of reusability. This study eva

Oliver Kost, Jindrich Dunik, Ivo Puncochar, Ondrej Straka

This paper deals with the noise identification of a linear time-varying stochastic dynamic system described by the state-space model. In particular, the stress is laid on the design of the correlation measurement difference method for estimation of the state and measurement noise covariance matrices for both observable and \textit{unobservable} systems with

Jerry Junyang Cheung, Shiyao Shen, Yuchen Zhuang, Yinghao Li

Despite recent advances in large language models (LLMs) for materials science, there is a lack of benchmarks for evaluating their domain-specific knowledge and complex reasoning abilities. To bridge this gap, we introduce MSQA, a comprehensive evaluation benchmark of 1,757 graduate-level materials science questions in two formats: detailed explanatory respon

Omar Ulises Reyes-Amador, Omaira González-Martín, Jacopo Fritz, Maarten Baes

Several models of nuclear dust in active galactic nuclei (AGN) have been presented in the literature to determine its physical and geometrical properties, usually assuming the dust density distribution as the main aspect producing differences in the mid-infrared (MIR) emission of AGNs. We present a study of the MIR emission of nearby AGNs by exploring the ef

Bayu Adhi Tama, Mansa Krishna, Homayra Alam, Mostafa Cham

Understanding Greenland's subglacial topography is critical for projecting the future mass loss of the ice sheet and its contribution to global sea-level rise. However, the complex and sparse nature of observational data, particularly information about the bed topography under the ice sheet, significantly increases the uncertainty in model projections. Bed t

Tomáš Novák, Martin Guldan, Josef Vojtěch, Josef Blažej

Commercial sources of polarization entanglement at telecommunication wavelengths are already available on the market, but they lack proper certification or third-party testing. We aim to provide a comprehensive testing framework for photon counting and correlation measurements to characterize the parameters of these sources in a scalable and repeatable manne

Daniele Barolo, Chiara Valentin, Fariba Karimi, Luis Galárraga

This paper evaluates the performance of six open-weight LLMs (llama3-8b, llama3.1-8b, gemma2-9b, mixtral-8x7b, llama3-70b, llama3.1-70b) in recommending experts in physics across five tasks: top-k experts by field, influential scientists by discipline, epoch, seniority, and scholar counterparts. The evaluation examines consistency, factuality, and biases rel