March 2025 arXiv papers — page 14

David Giofrè, David C. Geary, Lewis G. Halsey

On average men are taller and more muscular than women, which confers on them advantages related to female choice and during physical competition with other men. Sexual size dimorphisms such as these come with vulnerabilities due to higher maintenance and developmental costs for the sex with the larger trait. These costs are in keeping with evolutionary theo

Hugo de Souza Oliveira, Xin Li, Johannes Frey, Edoardo Milana

The nonlinear mechanical response of soft materials and slender structures is purposefully harnessed to program functions by design in soft robotic actuators, such as sequencing, amplified response, fast energy release, etc. However, typical designs of nonlinear actuators - e.g. balloons, inverted membranes, springs - have limited design parameters space and

Zongwei Wang, Min Gao, Junliang Yu, Yupeng Hou

The implicit feedback (e.g., clicks) in real-world recommender systems is often prone to severe noise caused by unintentional interactions, such as misclicks or curiosity-driven behavior. A common approach to denoising this feedback is manually crafting rules based on observations of training loss patterns. However, this approach is labor-intensive and the r

Shun Yamaguchi

We calculate the fundamental group of the regular part of certain compact Kahler symplectic orbifolds constructed by Fujiki, called Fujiki's examples. We determine which one is an irreducible symplectic orbifold among Fujiki's examples. This answers a question posed by A.Perego.

Shuo Huang, Hideki Umehata, Ian Smail, Kouichiro Nakanishi

Protoclusters represent the densest regions of cosmic large-scale structure in the early universe and are the environment where present-day massive elliptical galaxies are assembled. Millimeter continuum emission offers a powerful probe of obscured star formation at high redshifts across various environments. In this paper, we present a deep ALMA 1.17 mm mos

Jeonghyun Ko, Gyeongyun Park, Donghoon Lee, Kyunam Lee

One of the key tasks in machine learning for tabular data is feature engineering. Although it is vital for improving the performance of models, it demands considerable human expertise and deep domain knowledge, making it labor-intensive endeavor. To address this issue, we propose a novel framework, \textbf{FeRG-LLM} (\textbf{Fe}ature engineering by \textbf{R

Chenxing Sun, Jing Bai

In intelligent cartographic generation tasks empowered by generative models, the authenticity of synthesized maps constitutes a critical determinant. Concurrently, the selection of appropriate evaluation metrics to quantify map authenticity emerges as a pivotal research challenge. Current methodologies predominantly adopt computer vision-based image assessme

Khanh Chau Le, Hoang-Giang Bui

Accurate finite element analysis of refined shell theories is crucial but often hindered by membrane and shear locking effects. While various element-based locking-free techniques exist, this work addresses the problem at the theoretical level by utilizing results from asymptotic analysis. A formulation of a 2D refined shell theory incorporating transverse s

Xindi Yang, Baolu Li, Yiming Zhang, Zhenfei Yin

Video diffusion models (VDMs) have advanced significantly in recent years, enabling the generation of highly realistic videos and drawing the attention of the community in their potential as world simulators. However, despite their capabilities, VDMs often fail to produce physically plausible videos due to an inherent lack of understanding of physics, result

Hang Guo, Yawei Li, Taolin Zhang, Jiangshan Wang

Visual Autoregressive (VAR) modeling has gained popularity for its shift towards next-scale prediction. However, existing VAR paradigms process the entire token map at each scale step, leading to the complexity and runtime scaling dramatically with image resolution. To address this challenge, we propose FastVAR, a post-training acceleration method for effici

Aniket Mukherjee, Joy Kuri, Chandramani Singh

The Deficit Round Robin (DRR) scheduler is widely used in network systems for its simplicity and fairness. However, configuring its integer-valued parameters, known as quanta, to meet stringent delay constraints remains a significant challenge. This paper addresses this issue by demonstrating the convexity of the feasible parameter set for a two-flow DRR sys

Zhangcun Yan, Jianqiang Li, Peng Hang, Jian Sun

With the acceleration of urbanization and the growth of transportation demands, the safety of vulnerable road users (VRUs, such as pedestrians and cyclists) in mixed traffic flows has become increasingly prominent, necessitating high-precision and diverse trajectory data to support the development and optimization of autonomous driving systems. However, exis

Ángel González-Prieto, Javier Martínez, Vicente Muñoz

This paper reinterprets Alexander-type invariants of knots via representation varieties of knot groups into the group $\textrm{AGL}_1(\mathbb{C})$ of affine transformations of the complex line. In particular, we prove that the coordinate ring of the $\textrm{AGL}_{1}(\mathbb{C})$-representation variety is isomorphic to the symmetric algebra of the Alexander

Jiwon Jeong, Hyeju Jang, Hogun Park

The advancement of Large Language Models (LLMs) has greatly improved our ability to process complex language. However, accurately detecting logical fallacies remains a significant challenge. This study presents a novel and effective prompt formulation approach for logical fallacy detection, applicable in both supervised (fine-tuned) and unsupervised (zero-sh

Jia-Chen Zhang, Yu-Jie Xiong, Xi-He Qiu, Chun-Ming Xia

Supervised fine-tuning (SFT) is a milestone in aligning large language models with human instructions and adapting them to downstream tasks. In particular, Low-Rank Adaptation (LoRA) has gained widespread attention due to its parameter efficiency. However, its impact on improving the performance of large models remains limited. Recent studies suggest that co

Linxin Song, Xuwei Ding, Jieyu Zhang, Taiwei Shi

Large language models (LLMs) possess impressive linguistic capabilities but often fail to faithfully retain factual knowledge, leading to hallucinations and unreliable outputs. Understanding LLMs' knowledge deficiencies by exhaustively evaluating against full-scale knowledge bases is computationally prohibitive, especially for closed-weight models. We propos

Guanhua Chen, Yutong Yao, Ci-Jun Gao, Lidia S. Chao

Current research on LoRA primarily focuses on minimizing the number of fine-tuned parameters or optimizing its architecture. However, the necessity of all fine-tuned LoRA layers during inference remains underexplored. In this paper, we investigate the contribution of each LoRA layer to the model's ability to predict the ground truth and hypothesize that lowe

Linfeng Tang, Yeda Wang, Meiqi Gong, Zizhuo Li

Compared to images, videos better reflect real-world acquisition and possess valuable temporal cues. However, existing multi-sensor fusion research predominantly integrates complementary context from multiple images rather than videos due to the scarcity of large-scale multi-sensor video datasets, limiting research in video fusion and the inherent difficulty

Miaomiao Cai, Lei Chen, Yifan Wang, Zhiyong Cheng

Popularity bias is a common challenge in recommender systems. It often causes unbalanced item recommendation performance and intensifies the Matthew effect. Due to limited user-item interactions, unpopular items are frequently constrained to the embedding neighborhoods of only a few users, leading to representation collapse and weakening the model's generali

Lyuye Zhang, Jiahui Wu, Chengwei Liu, Kaixuan Li

In the rapidly evolving landscape of software development, addressing security vulnerabilities in open-source software (OSS) has become critically important. However, existing research and tools from both academia and industry mainly relied on limited solutions, such as vulnerable version adjustment and adopting patches, to handle identified vulnerabilities.

Ziwei Zhang, Juan Wen, Wanli Peng, Zhengxian Wu

Large language models (LLMs) enable powerful knowledge injection through approaches such as in-context learning and fine-tuning, but they also introduce new risks of unauthorized imitation of high-value creative works. Existing copyright protection techniques mainly focus on visual media, leaving the protection of creative writing largely unexplored. In this

Linfeng Tang, Yeda Wang, Zhanchuan Cai, Junjun Jiang

Current image fusion methods struggle to address the composite degradations encountered in real-world imaging scenarios and lack the flexibility to accommodate user-specific requirements. In response to these challenges, we propose a controllable image fusion framework with language-vision prompts, termed ControlFusion, which adaptively neutralizes composite

Linfeng Tang, Chunyu Li, Guoqing Wang, Yixuan Yuan

Existing fusion methods are tailored for high-quality images but struggle with degraded images captured under harsh circumstances, thus limiting the practical potential of image fusion. This work presents a \textbf{D}egradation and \textbf{S}emantic \textbf{P}rior dual-guided framework for degraded image \textbf{Fusion} (\textbf{DSPFusion}), utilizing degrad

Guoqing Wei, Diguang Wu, Runqi Kang, Qingning Jiang

Dark matter remains one of the most profound and unresolved mysteries in modern physics. To unravel its nature, numerous haloscope experiments have been implemented across various mass ranges. However, very few haloscope experiments conducted within millimeter-wave frequency range, which is in the favored mass region for well-motivated dark matter candidates

Xiangyang Luo, Junhao Cheng, Yifan Xie, Xin Zhang

Open-ended story visualization is a challenging task that involves generating coherent image sequences from a given storyline. One of the main difficulties is maintaining character consistency while creating natural and contextually fitting scenes--an area where many existing methods struggle. In this paper, we propose an enhanced Transformer module that use

Song Lulu, Zhang Di, Jia Shaobo, Zhu Pengcheng

Short packet-based advanced Internet of things (A-IoT) calls for not only the next generation of ultra-reliable low-latency communications (xURLLC) but also highly secured communications. In this paper, we aim to address this objective by developing a non-orthogonal multiple access (NOMA) system with untrusted user. There exist two key problems: The confiden

Mario Lázaro, Marc Martí-Sabaté, Richard V. Craster, Vicent Romero-García

A theoretical study on the weak scattering formulation for flexural waves in thin elastic plates loaded by point-like resonators is reported. Our approach employs the Born approximation and far-field asymptotics of the Green function to characterize multiple scattering effects in this system. The response of the system to an incident wave can be expressed as

Liangbo Ning, Ziran Liang, Zhuohang Jiang, Haohao Qu

With the advancement of web techniques, they have significantly revolutionized various aspects of people's lives. Despite the importance of the web, many tasks performed on it are repetitive and time-consuming, negatively impacting overall quality of life. To efficiently handle these tedious daily tasks, one of the most promising approaches is to advance aut

Jiude Wei, Yuxuan Li, Cewu Lu, Jianhua Sun

We humans rely on a wide range of commonsense knowledge to interact with an extensive number and categories of objects in the physical world. Likewise, such commonsense knowledge is also crucial for robots to successfully develop generalized object manipulation skills. While recent advancements in Multi-modal Large Language Models (MLLMs) have showcased thei

Nikita Kalinin

This paper establishes an extension of Wolstenholme's theorem to the ring of Gaussian integers $\mathbb{Z}[i]$. For a prime $p > 7$, we prove that the sum $S_p$ of inverses of Gaussian integers in the set $\{n+mi \mid 1 \leq n, m \leq p-1, \gcd(p, mi+n)=1\}$ satisfies the congruence $S_p \equiv 0 \pmod{p^4}$. We further generalize this result to higher-power

Yongsheng Liang, Jingyan Zhan, Shiqi Xia, Daohong Song

Flat bands are of significant interest due to their potential for energy confinement and their ability to enable strongly correlated physics. Incorporating topology into flatband systems further enhances flatband mode robustness against perturbations. Here, we present the first realization of doubly degenerate topological flatbands of edge states in chiral-s

Dimitrios Karamitros, Thomas McKelvey, Apostolos Pilaftsis

We investigate the impact of the temperature dependence of the relativistic degrees of freedom (dofs) of the plasma on lepton and baryon asymmetry. Motivated by the significant effect of the varying dofs on the tri-resonant leptogenesis particle model in low-scale leptogenesis, we show how this effect impacts the evolution of the lepton asymmetry in a simpli

Jianhua Shan, Jie Zhao, Jiangduo Liu, Xiangbo Wang

Force estimation is the core indicator for evaluating the performance of tactile sensors, and it is also the key technical path to achieve precise force feedback mechanisms. This study proposes a design method for a visual tactile sensor (VBTS) that integrates a magnetic perception mechanism, and develops a new tactile sensor called MagicGel. The sensor uses

Ragav Sachdeva, Andrew Zisserman

Comics have long been a popular form of storytelling, offering visually engaging narratives that captivate audiences worldwide. However, the visual nature of comics presents a significant barrier for visually impaired readers, limiting their access to these engaging stories. In this work, we provide a pragmatic solution to this accessibility challenge by dev

Qingyang Hu, Hantian You, Kenan Li, Luhua Lai

Ferroptosis is a form of cell death discovered in recent years, induced by excessive peroxidation of phospholipids. Glutathione peroxidase 4 (GPx4) is an intracellular enzyme that can repair the peroxidized phospholipids on membranes, thus regulating ferroptosis. By combining multiscale molecular dynamics (MD) simulations and experimental assays, we investig

Zheyuan Lai, Michael C. H. Choi

We study the problem of optimally projecting the transition matrix of a finite ergodic multivariate Markov chain onto a lower-dimensional state space, as well as the problem of finding an optimal partition of coordinates such that the factorized Markov chain gives minimal information loss compared to the original multivariate chain. Specifically, we seek to

Neil Mallinar, A. Ali Heydari, Xin Liu, Anthony Z. Faranesh

Large language models (LLMs) have emerged as powerful tools for analyzing complex datasets. Recent studies demonstrate their potential to generate useful, personalized responses when provided with patient-specific health information that encompasses lifestyle, biomarkers, and context. As LLM-driven health applications are increasingly adopted, rigorous and e

Nima L. Wickramasinghe, Dinuka Sandun Udayantha, Akila Abeyratne, Kavindu Weerasinghe

Objective: Young children and infants, especially newborns, are highly susceptible to seizures, which, if undetected and untreated, can lead to severe long-term neurological consequences. Early detection typically requires continuous electroencephalography (cEEG) monitoring in hospital settings, involving costly equipment and highly trained specialists. This

Fereniki Panagopoulou

Do robots vote? Do machines make decisions instead of us? No, (at least not yet), but this is something that could happen. The impact of Artificial Intelligence (AI) on democracy is a complex issue that requires thorough research and careful regulation. At the most important level, that of the electoral process, it is noted that it is not determined by the A

Jingui Ma, Yang Hu, Luyang Tang, Jiayu Yang

Recently, 3D Gaussian Spatting (3DGS) has gained widespread attention in Novel View Synthesis (NVS) due to the remarkable real-time rendering performance. However, the substantial cost of storage and transmission of vanilla 3DGS hinders its further application (hundreds of megabytes or even gigabytes for a single scene). Motivated by the achievements of pred

Sicheng Liu, Tao Luo

This manuscript concerns the stability conditions for the well-posedness of the two-dimensional plasma-vacuum interface problems for ideal incompressible magnetohydrodynamics (MHD) equations, which describe the dynamics of conducting perfect fluids in a vacuum region under the influence of magnetic fields. Due to the counterexamples constructed by C. Hao and

Loc Hoang Tran

Principal Component Analysis (PCA) is a widely utilized technique for dimensionality reduction; however, its inherent lack of interpretability-stemming from dense linear combinations of all feature-limits its applicability in many domains. In this paper, we propose a novel sparse PCA algorithm that imposes sparsity through a smooth L1 penalty and leverages a

Chi-Sheng Chen, Wei An Hou, Hsiang-Wei Hu, Zhen-Sheng Cai

Quantum generative models offer a promising new direction in machine learning by leveraging quantum circuits to enhance data generation capabilities. In this study, we propose a hybrid quantum-classical image generation framework that integrates variational quantum circuits into a diffusion-based model. To improve training dynamics and generation quality, we

J. Bharathi Kannan, Sreeram PG, Sanku Paul, S. Harshini Tekur

Krylov complexity (K-complexity) is a measure of quantum state complexity that minimizes wavefunction spreading across all the possible bases. It serves as a key indicator of operator growth and quantum chaos. In this work, K-complexity and Arnoldi coefficients are applied to probe a variety of localization phenomena in the quantum kicked rotor system. We an

Jing Zhu, Mingxuan Ju, Yozen Liu, Danai Koutra

Generative recommendation (GR) has become a powerful paradigm in recommendation systems that implicitly links modality and semantics to item representation, in contrast to previous methods that relied on non-semantic item identifiers in autoregressive models. However, previous research has predominantly treated modalities in isolation, typically assuming ite

Hongwei Zheng, Han Li, Wenrui Dai, Ziyang Zheng

Existing 2D-to-3D human pose estimation (HPE) methods struggle with the occlusion issue by enriching information like temporal and visual cues in the lifting stage. In this paper, we argue that these methods ignore the limitation of the sparse skeleton 2D input representation, which fundamentally restricts the 2D-to-3D lifting and worsens the occlusion issue

Hongxiang Jiang, Jihao Yin, Qixiong Wang, Jiaqi Feng

Recent advances in multimodal large language models (MLLMs) have demonstrated impressive results in various visual tasks. However, in remote sensing (RS), high resolution and small proportion of objects pose challenges to existing MLLMs, which struggle with object-centric tasks, particularly in precise localization and fine-grained attribute description for

Hui Li, Ante Wang, kunquan li, Zhihao Wang

Misinformation spans various domains, but detection methods trained on specific domains often perform poorly when applied to others. With the rapid development of Large Language Models (LLMs), researchers have begun to utilize LLMs for cross-domain misinformation detection. However, existing LLM-based methods often fail to adequately analyze news in the targ

Haricharan Balasundaram, Girija Limaye, Meghana Nasre, Abhinav Raja

The Hospital Residents setting models important problems like school choice, assignment of undergraduate students to degree programs, among many others. In this setting, fixed quotas are associated with the programs that limit the number of agents that can be assigned to them. Motivated by scenarios where all agents must be matched, we propose and study a ge

Man Zhang, Ying Li, Yang Peng, Yijia Sun

A key objective in artificial intelligence (AI) development is to create systems that match or surpass human creativity. Although current AI models perform well across diverse creative tasks, it remains unclear whether these achievements reflect genuine creative thinking. This study examined whether AI models (GPT-3.5-turbo, GPT-4, and GPT-4o) engage in crea

Yiyu Qian, Tim Miller, Zheng Qian, Liyuan Zhao

Monte-Carlo Tree Search (MCTS) is a family of sampling-based search algorithms widely used for online planning in sequential decision-making domains and at the heart of many recent advances in artificial intelligence. Understanding the behavior of MCTS agents is difficult for developers and users due to the frequently large and complex search trees that resu

Jiaxu Liu, Song Chen, Shengze Cai, Chao Xu

This paper delves into the investigation of a distributed aggregative optimization problem within a network. In this scenario, each agent possesses its own local cost function, which relies not only on the local state variable but also on an aggregated function of state variables from all agents. To expedite the optimization process, we amalgamate the heavy

Shuting Wu, Yifei Wang, Jingzhe Wang, Apostolos I. Rikos

Moving Horizon Estimation~(MHE) is essentially an optimization-based approach designed to estimate the states of dynamic systems within a moving time horizon. Traditional MHE solutions become computationally prohibitive due to the \textit{curse of dimensionality} arising from increasing problem complexity and growing length of time horizon. To address this i

Vincent Gbouna Zakka, Minhyun Lee

Understanding the energy consumption pattern in the built environment is invaluable for the evaluation of the sources of energy wastage and the development of strategies for efficient energy management. An integrated monitoring system that can provide high granularity energy consumption and indoor environmental quality (IEQ) data is essential to enable intel

Xi Zhang, Huihui Liu, Junrui Xi, Menglu Chen

Facing the physical limitations and energy consumption bottlenecks of traditional electronic devices, we propose an innovative design framework integrating evolutionary algorithms and metasurface technology, aiming to achieve intelligent inverse design of photonic devices. Based on a constructed high-dimensional evolutionary algorithm framework, a four-layer

Kensuke Ogawa, Moeta Tsukamoto, Yusuke Mori, Daigo Takafuji

Spin waves propagating in magnetic materials exhibit nonlinear behavior at large amplitudes due to the competition between excitation and relaxation, providing an attractive platform for exploring nonlinear wave dynamics. In particular, spin waves with a non-zero wavenumber that carry momentum undergo nonlinear relaxation and experience wavenumber modulation

Rusiru Gambheera

For an abelian, CM extension $H/F$ of a totally real number field $F$, we improve upon the reformulation of the Equivariant Tamagawa Number Conjecture for the Artin motive $h_{H/F}$ by Atsuta-Kataoka in \cite{Atsuta-Kataoka-ETNC} and extend the results proved in \cite{Bullach-Burns-Daoud-Seo}, \cite{Dasgupta-Kakde-Silliman-ETNC}, \cite{gambheera-popescu} and

Naman S. Bajaj, Ilaria Pascucci, Tracy L. Beck, Suzan Edwards

We present JWST NIRSpec spectro-imaging observations of jets from four edge-on protoplanetary disks that exhibit clear signatures of MHD disk winds. Bipolar jets are detected and spatially resolved in over 30 shock-excited forbidden lines, multiple Paschen and Brackett series lines of atomic hydrogen, and the high-energy excitation line of atomic helium (1.0

Lingxiao Cheng, Lubo Wang

For stationary two-valued harmonic functions with H\"older regularity, we establish their Lipschitz regularity and prove that the nodal set consists of analytic hypersurfaces away from a singular set. The main tools are the Almgren monotonicity formula and the blow-up method. These results are applicable to some limiting problems in segregation models.

Majed Khalaf, Chia-Hsien Shen, Ofri Telem

We present a systematic method for analytically computing time-dependent observables for a relativistic probe particle in Coulomb and Schwarzschild backgrounds. The method generates expressions valid both in the bound and unbound regimes, namely bound-unbound universal expressions. To demonstrate our method we compute the time-dependent radius and azimuthal

Sang-Gyun Youn

We introduce an analytic family of twisted Fourier transforms $\left\{\mathcal{F}^{(x)}_p\right\}_{x\in \mathbb{R},p\in [1,2)}$ for non-Kac compact quantum groups and establish a sharpened form of the Hausdorff-Young inequality in the range $0\leq x \leq 1$. Furthermore, we prove that the range $0\leq x \leq 1$ is both necessary and sufficient for the bounde

Mohamed Elrefaie, Janet Qian, Raina Wu, Qian Chen

We introduce the concept of "Design Agents" for engineering applications, particularly focusing on the automotive design process, while emphasizing that our approach can be readily extended to other engineering and design domains. Our framework integrates AI-driven design agents into the traditional engineering workflow, demonstrating how these specialized c

Wonduk Seo, Juhyeon Lee, Yanjun Shao, Qingshan Zhou

Large Language Models (LLMs) have enabled dynamic reasoning in automated data analytics, yet recent multi-agent systems remain limited by rigid, single-path workflows that restrict strategic exploration and often lead to suboptimal outcomes. To overcome these limitations, we propose SPIO (Sequential Plan Integration and Optimization), a framework that replac

Harshvardhan Takawale, Nirupam Roy

In this paper, we introduce SpINR, a novel framework for volumetric reconstruction using Frequency-Modulated Continuous-Wave (FMCW) radar data. Traditional radar imaging techniques, such as backprojection, often assume ideal signal models and require dense aperture sampling, leading to limitations in resolution and generalization. To address these challenges

Hyunsik Jeon, Satoshi Koide, Yu Wang, Zhankui He

Conversational recommender systems engage users in dialogues to refine their needs and provide more personalized suggestions. Although textual information suffices for many domains, visually driven categories such as fashion or home decor potentially require detailed visual information related to color, style, or design. To address this challenge, we propose

Daniele Corradetti, Alessio Marrani

In this work we introduce the concepts of linguistic transformation, linguistic loop and semantic deficit. By exploiting Lie group theoretical and geometric techniques, we define invariants that capture the structural properties of a whole linguistic loop. This result introduces new line of research, employing tools from Lie theory and higher-dimensional geo

Alexander Koldobsky

We introduce the class of functions positively associated with a linear operator. We describe these classes for several integral operators including the $q$-cosine transform and the spherical Radon transform. We show that positively associated functions control the comparison problem for linear operators generalizing the Busemann-Petty problem for convex bod

Ioan Trifoi

The main purpose of this paper is to extend some fixed point results for single valued $b$-enriched nonexpansive mappings to the case of multivalued mappings. To this end, we introduce *-$b$-enriched nonexpansive mappings, as a generalization of *-nonexpansive mappings \cite{Abdul Rahim Khan} for which we establish an existence theorem in Hilbert space. We p

Wenjie Cai, Gongyi Wang, Yu Zhang, Xiang Qu

Active matter refers to systems composed of self-propelled entities that consume energy to produce motion, exhibiting complex non-equilibrium dynamics that challenge traditional models. With the rapid advancements in machine learning, reinforcement learning (RL) has emerged as a promising framework for addressing the complexities of active matter. This revie

Cong Wei, Bo Sun, Haoyu Ma, Ji Hou

Recent advancements in video generation have achieved impressive motion realism, yet they often overlook character-driven storytelling, a crucial task for automated film, animation generation. We introduce Talking Characters, a more realistic task to generate talking character animations directly from speech and text. Unlike talking head, Talking Characters

Youxiang Zhu, Ruochen Li, Danqing Wang, Daniel Haehn

Long-context large language models (LLMs) are prone to be distracted by irrelevant contexts. The reason for distraction remains poorly understood. In this paper, we first identify the contextual heads, a special group of attention heads that control the overall attention of the LLM. Then, we demonstrate that distraction arises when contextual heads fail to a

Kenneth J. Sible, David Chiang

We present an interactive machine translation (MT) system designed for users who are not proficient in the target language. It aims to improve trustworthiness and explainability by identifying potentially mistranslated words and allowing the user to intervene to correct mistranslations. However, confidence estimation in machine translation has traditionally

Simone Mezzasoma, Carl-Johan Haster, Caroline B. Owen, Neil J. Cornish

Semi-analytical waveform models for black hole binaries require calibration against numerical relativity waveforms to accurately represent the late inspiral and merger, where analytical approximations fail. After the fitting coefficients contained in the model are optimized, they are typically held fixed when the model is used to infer astrophysical paramete

Nandakishor M

Current approaches to sales conversation analysis and conversion prediction typically rely on Large Language Models (LLMs) combined with basic retrieval augmented generation (RAG). These systems, while capable of answering questions, fail to accurately predict conversion probability or provide strategic guidance in real time. In this paper, we present SalesR

Guang-Wei Mi, Xiaofen Huang, Shao-Ming Fei, Tinggui Zhang

The quantum Bell nonlocality plays a crucial role in quantum information processing. In this paper, we first obtain the quantitative analytical expression of the genuine four-partite Bell nonlocality of any 4-qubit quantum state. Then, we investigate and derive the genuine four-partite nonlocalities in the background of the Schwarzschild black hole and the S

Atsuhide Nagasaka

Goda showed that the twisted Alexander polynomial can be recovered from the zeta function of a matrix-weighted graph. Motivated by this, we study transformations of weighted graphs that preserve this zeta function, introducing a notion of holonomy as an analogy for the accumulation of weights along cycles. We extend the framework from matrices to group eleme

Jerry Xu, Justin Wang, Joley Leung, Jasmine Gu

There are a growing number of AI applications, but none tailored specifically to help residents answer their questions about municipal budget, a topic most are interested in but few have a solid comprehension of. In this research paper, we propose GRASP, a custom AI chatbot framework which stands for Generation with Retrieval and Action System for Prompts. G

Jiachuan Wang, Shimin Di, Tianhao Tang, Haoyang LI

Emergence, the phenomenon of a rapid performance increase once the model scale reaches a threshold, has achieved widespread attention recently. The literature has observed that monosemantic neurons in neural networks gradually diminish as the model scale increases. Subsequently, Learning From Emergence is proposed to actively inhibit monosemantic neurons in

Zhenyang Liu, Yikai Wang, Sixiao Zheng, Tongying Pan

Open-vocabulary 3D visual grounding and reasoning aim to localize objects in a scene based on implicit language descriptions, even when they are occluded. This ability is crucial for tasks such as vision-language navigation and autonomous robotics. However, current methods struggle because they rely heavily on fine-tuning with 3D annotations and mask proposa

Binghong Li, Xiaoli Li, Xu Li, Hongxing Rui

The velocity errors of the classical marker and cell (MAC) scheme are dependent on the pressure approximation errors, which is non-pressure-robust and will cause the accuracy of the velocity approximation to deteriorate when the pressure approximation is poor. In this paper, we first propose the reconstructed MAC scheme (RMAC) based on the finite volume meth

Mikhail Krasitskii, Olga Kolesnikova, Liliana Chanona Hernandez, Grigori Sidorov

The sentiment analysis task in Tamil-English code-mixed texts has been explored using advanced transformer-based models. Challenges from grammatical inconsistencies, orthographic variations, and phonetic ambiguities have been addressed. The limitations of existing datasets and annotation gaps have been examined, emphasizing the need for larger and more diver

Wei Tao, Bin Zhang, Xiaoyang Qu, Jiguang Wan

Recently, large language models (LLMs) have been able to handle longer and longer contexts. However, a context that is too long may cause intolerant inference latency and GPU memory usage. Existing methods propose mixed-precision quantization to the key-value (KV) cache in LLMs based on token granularity, which is time-consuming in the search process and har

DUNE Collaboration, A. Abed Abud, R. Acciarri, M. A. Acero

The international collaboration designing and constructing the Deep Underground Neutrino Experiment (DUNE) at the Long-Baseline Neutrino Facility (LBNF) has developed a two-phase strategy for the implementation of this leading-edge, large-scale science project. The 2023 report of the US Particle Physics Project Prioritization Panel (P5) reaffirmed this visio

Yunan Wei, Shengnan Zhao, Chuan Zhao, Zhe Liu

Federated learning (FL) is a distributed machine learning paradigm enabling multiple clients to train a model collaboratively without exposing their local data. Among FL schemes, clustering is an effective technique addressing the heterogeneity issue (i.e., differences in data distribution and computational ability affect training performance and effectivene

DUNE Collaboration, A. Abed Abud, R. Acciarri, M. A. Acero

The international collaboration designing and constructing the Deep Underground Neutrino Experiment (DUNE) at the Long-Baseline Neutrino Facility (LBNF) has developed a two-phase strategy for the implementation of this leading-edge, large-scale science project. The 2023 report of the US Particle Physics Project Prioritization Panel (P5) reaffirmed this visio

Junlong Chen, Jiawen Kang, Minrui Xu, Fan Wu

Vehicle Twins (VTs) as digital representations of vehicles can provide users with immersive experiences in vehicular metaverse applications, e.g., Augmented Reality (AR) navigation and embodied intelligence. VT migration is an effective way that migrates the VT when the locations of physical entities keep changing to maintain seamless immersive VT services.

Zuyu Xu, Bin Lv

Neural networks have emerged as powerful tools for modeling complex physical systems, yet balancing high accuracy with computational efficiency remains a critical challenge in their convergence behavior. In this work, we propose the Hybrid Parallel Kolmogorov-Arnold Network (KAN) and Multi-Layer Perceptron (MLP) Physics-Informed Neural Network (HPKM-PINN), a

Xingyu Lyu, Ning Wang, Yang Xiao, Shixiong Li

Federated Learning is a popular paradigm that enables remote clients to jointly train a global model without sharing their raw data. However, FL has been shown to be vulnerable towards model poisoning attacks due to its distributed nature. Particularly, attackers acting as participants can upload arbitrary model updates that effectively compromise the global

Nhung T. T. Nguyen, Anh T. Ngo, Trinh X. Hoang

DNA toroids are compact torus-shaped bundles formed by one or multiple DNA molecules being condensed from the solution due to various condensing agents. It has been shown that the DNA toroidal bundles are twisted. However, the global conformations of DNA inside these bundles are still not well understood. In this study, we investigate this issue by solving d

Jiangtao Li

The set of multiple zeta-star values is a countable dense subset of the half line $(1,+\infty)$. In this paper, we establish some classical Diophantine type results for the set of multiple zeta-star values. Firstly, we give a criterion to determine whether a number is a multiple zeta-star value. Secondly, we establish the zero-one law for the set of multiple

Zhuoqi Lyu, Qing Ke

Understanding the changing structure of science over time is essential to elucidating how science evolves. We develop diachronic embeddings of scholarly periodicals to quantify "semantic changes" of periodicals across decades, allowing us to track the evolution of research topics and identify rapidly developing fields. By mapping periodicals within a physica

Feng-Lin Liu, Hongbo Fu, Xintao Wang, Weicai Ye

Video generation and editing conditioned on text prompts or images have undergone significant advancements. However, challenges remain in accurately controlling global layout and geometry details solely by texts, and supporting motion control and local modification through images. In this paper, we aim to achieve sketch-based spatial and motion control for v

Lu Yu, Haoyu Han, Zhe Tao, Hantao Yao

Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability across tasks. Most existing CL methods focus primarily on preserving learned knowledge to improve model performance. Howe

Felix Wimbauer, Weirong Chen, Dominik Muhle, Christian Rupprecht

Estimating camera motion and intrinsics from casual videos is a core challenge in computer vision. Traditional bundle-adjustment based methods, such as SfM and SLAM, struggle to perform reliably on arbitrary data. Although specialized SfM approaches have been developed for handling dynamic scenes, they either require intrinsics or computationally expensive t

Hieu Nghiem, Tuan-Dung Le, Suhao Chen, Thanh Thieu

Extracting medical history entities (MHEs) related to a patient's chief complaint (CC), history of present illness (HPI), and past, family, and social history (PFSH) helps structure free-text clinical notes into standardized EHRs, streamlining downstream tasks like continuity of care, medical coding, and quality metrics. Fine-tuned clinical large language mo

Nhung T. T. Nguyen, Pham Nam Phong, Duy Manh Le, Minh-Tien Tran

The aqueous solvent profoundly influences protein folding, yet its effects are relatively poorly understood. In this study, we investigate the impact of solvation on the folding of lattice proteins by using Monte Carlo simulations. The proteins are modelled as self-avoiding 27-mer chains on a cubic lattice, with compact native states and structure-based G\=o

Moniellen Pires Monteiro, Juan Pablo Carrillo-Mora, Nahuel Gutiérrez, Sofía Montagna

Bradyrhizobium diazoefficiens is a nitrogen-fixing symbiont of soybean, worldwide used as biofertilizer. This soil bacterium possesses two flagellar systems enabling it to swim in water-saturated soils. However, the motility in soil pores, which may be crucial for competitiveness for root nodulation, is difficult to predict. To address this gap, we fabricate

Xinyi Hou, Yanjie Zhao, Shenao Wang, Haoyu Wang

The Model Context Protocol (MCP) is an emerging open standard that defines a unified, bi-directional communication and dynamic discovery protocol between AI models and external tools or resources, aiming to enhance interoperability and reduce fragmentation across diverse systems. This paper presents a systematic study of MCP from both architectural and secur

Yunfei Meng, Changbo Ke, Zhiqiu Huang

Satellite communication systems (SatCom) is a brand-new network that uses artificial Earth satellites as relay stations to provide communication services such as broadband Internet access to various users on land, sea, air and in space. It features wide coverage, relatively high transmission rates and strong anti-interference capabilities. Security authentic

Kevin Esmeral García, Egor A. Maximenko

It is well known that for every measurable function $a$, essentially bounded on the positive halfline, the corresponding radial Toeplitz operator $T_a$, acting in the Segal--Bargmann--Fock space, is diagonal with respect to the canonical orthonormal basis consisting of normalized monomials. We denote by $\gamma_a$ the corresponding eigenvalues sequence. Give