May 2025 arXiv papers — page 4

Benjamin von Berg, Bernhard K. Aichernig

AALpy is a well-established open-source automata learning library written in Python with a focus on active learning of systems with IO behavior. It provides a wide range of state-of-the-art algorithms for different automaton types ranging from fully deterministic to probabilistic automata. In this work, we present the recent addition of a generalized impleme

Ioan-Paul Ciobanu, Andrei-Iulian Hiji, Nicolae-Catalin Ristea, Paul Irofti

Recent advances in audio generation led to an increasing number of deepfakes, making the general public more vulnerable to financial scams, identity theft, and misinformation. Audio deepfake detectors promise to alleviate this issue, with many recent studies reporting accuracy rates close to 99%. However, these methods are typically tested in an in-domain se

Ruiyang Ma, Tianhao Wei, Jiaxi Zhang, Chun Yang

As hardware design complexity increases, hardware fuzzing emerges as a promising tool for automating the verification process. However, a significant gap still exists before it can be applied in industry. This paper aims to summarize the current progress of hardware fuzzing from an industry-use perspective and propose solutions to bridge the gap between hard

A. Cornejo-Cárdenas, E. Sillero, P. B. Tissera, M. Boquien

Hydrodynamic simulations are powerful tools for studying galaxy formation. However, it is crucial to test and improve the sub-grid physics underlying these simulations by comparing their predictions with observations. To this aim, observable quantities can be derived for simulated galaxies, enabling the analysis of simulated properties through an observation

Elinor Ginzburg, Itay Segev, Yoash Levron, Sarah Keren

We aim to better understand the tradeoffs between traditional and reinforcement learning (RL) approaches for energy storage management. More specifically, we wish to better understand the performance loss incurred when using a generative RL policy instead of using a traditional approach to find optimal control policies for specific instances. Our comparison

Nina Cohen, Kordel K. France

Hanabi has become a popular game for research when it comes to reinforcement learning (RL) as it is one of the few cooperative card games where you have incomplete knowledge of the entire environment, thus presenting a challenge for a RL agent. We explored different tabular and deep reinforcement learning algorithms to see which had the best performance both

Junwoo Park, Hyuck Lee, Dohyun Lee, Daehoon Gwak

Large Language Models (LLMs) have shown remarkable performance across diverse tasks without domain-specific training, fueling interest in their potential for time-series forecasting. While LLMs have shown potential in zero-shot forecasting through prompting alone, recent studies suggest that LLMs lack inherent effectiveness in forecasting. Given these confli

Wayne Peng

Consider a number field $K$ and a rational function $f$ of degree greater than 1 over $K$. By taking preimages of $\alpha\in K$ under successive iterates of $f$, an infinite $d$-ary tree $T_\infty$ rooted at $\alpha$ can be constructed. An edge is assigned between two preimages $x$ and $y$ if $f(x)=y$. The absolute Galois group of $K$, acting on $T_\infty$ t

Kordel K. France, Ovidiu Daescu

Navigation by scent is a capability in robotic systems that is rising in demand. However, current methods often suffer from ambiguities, particularly when robots misattribute odours to incorrect objects due to limitations in olfactory datasets and sensor resolutions. To address challenges in olfactory navigation, we introduce a multimodal olfaction dataset a

Jiajun He, Tomoki Toda

End-to-end automatic speech recognition (ASR) models often struggle to accurately recognize rare words. Previously, we introduced an ASR postprocessing method called error detection and context-aware error correction (ED-CEC), which leverages contextual information such as named entities and technical terms to improve the accuracy of ASR transcripts. Althoug

Seohyun Park, Chitralekha Gupta, Michelle Kah Yian Kwan, Xinhui Fung

Dysarthria, a motor speech disorder, affects intelligibility and requires targeted interventions for effective communication. In this work, we investigate automated mispronunciation feedback by collecting a dysarthric speech dataset from six speakers reading two passages, annotated by a speech therapist with temporal markers and mispronunciation descriptions

Hao Li, Hao Wan, Yuzhou Chen, Dongsheng Ye

Dynamic graphs evolve continuously, presenting challenges for traditional graph learning due to their changing structures and temporal dependencies. Recent advancements have shown potential in addressing these challenges by developing suitable meta-learning-based dynamic graph neural network models. However, most meta-learning approaches for dynamic graphs r

Xuhui Zhang, Jian Zhou

We present a formula for the connected \(n\)-point functions of a tau-funtion of the BKP hierarchy by embedding BKP hierarchy into KP hierarchy. This formula is different from the one given by Wang and Yang. We prove that these two formulae are equivalent.

Michael T. M. B. Morris-Thomas, Marius Martens

The real-time prediction of floating offshore asset behavior under stochastic metocean conditions remains a significant challenge in offshore engineering. While traditional empirical and frequency-domain methods work well in benign conditions, they struggle with both extreme sea states and nonlinear responses. This study presents a supervised machine learnin

Wenhan Lyu, Devashish Tyagi, Yihang Yang, Ziwei Li

Long user history is highly valuable signal for recommendation systems, but effectively incorporating it often comes with high cost in terms of data center power consumption and GPU. In this work, we chose offline embedding over end-to-end sequence length optimization methods to enable extremely long user sequence modeling as a cost-effective solution, and p

S. Mo, K. Kovalenka, S. Buchberger, B. K. Saika

Moir{\'e} heterostructures, created by stacking two-dimensional (2D) materials together with a finite lattice mismatch or rotational twist, represent a new frontier of designer quantum materials. Typically, however, this requires the painstaking manual assembly of heterostructures formed from exfoliated materials. Here, we observe clear spectroscopic signatu

Suhas BN, Han-Chin Shing, Lei Xu, Mitch Strong

Hallucinations in large language models (LLMs) during summarization of patient-clinician dialogues pose significant risks to patient care and clinical decision-making. However, the phenomenon remains understudied in the clinical domain, with uncertainty surrounding the applicability of general-domain hallucination detectors. The rarity and randomness of hall

Mehedi Ahamed, Radib Bin Kabir, Tawsif Tashwar Dipto, Mueeze Al Mushabbir

This study investigates the performance of few-shot learning (FSL) approaches in recognizing Bangla handwritten characters and numerals using limited labeled data. It demonstrates the applicability of these methods to scripts with intricate and complex structures, where dataset scarcity is a common challenge. Given the complexity of Bangla script, we hypothe

Hao Song, Yiming Shen, Wenxuan Luo, Leixin Guo

The Model Context Protocol (MCP) is an emerging standard designed to enable seamless interaction between Large Language Model (LLM) applications and external tools or resources. Within a short period, thousands of MCP services have been developed and deployed. However, the client-server integration architecture inherent in MCP may expand the attack surface a

Tatsuki Takahashi, Chihiro Maru, Hiroko Shoji

Off-policy evaluation (OPE) in ranking settings with large ranking action spaces, which stems from an increase in both the number of unique actions and length of the ranking, is essential for assessing new recommender policies using only logged bandit data from previous versions. To address the high variance issues associated with existing estimators, we int

Long Bai, Zixuan Li, Xiaolong Jin, Jiafeng Guo

Forecasting over Temporal Knowledge Graphs (TKGs) which predicts future facts based on historical ones has received much attention. Recent studies have introduced Large Language Models (LLMs) for this task to enhance the models' generalization abilities. However, these models perform forecasting via simultaneously learning two kinds of entangled knowledge in

Tiefeng Jiang, Tuan Pham

We propose a new probabilistic characterization of the uniform distribution on the hypersphere in terms of the distribution of pairwise inner products, extending the ideas of \citep{cuesta2009projection,cuesta2007sharp} in a data-driven manner. This characterization naturally leads to an Ingster-type distance for quantifying deviations from uniformity, whose

Haoshuai Zhou, Changgeng Mo, Boxuan Cao, Linkai Li

Personalized speech intelligibility prediction is challenging. Previous approaches have mainly relied on audiograms, which are inherently limited in accuracy as they only capture a listener's hearing threshold for pure tones. Rather than incorporating additional listener features, we propose a novel approach that leverages an individual's existing intelligib

Lothar Sebastian Krapp, Salma Kuhlmann, Lasse Vogel

We introduce the notion of the definable rank of an ordered field, ordered abelian group and ordered set, respectively. We study the relation between the definable rank of an ordered field and the definable rank of the value group of its natural valuation. Similarly, we compare the definable rank of an ordered abelian group to that of its value set with resp

Yongming Luo

We study the small data scattering problem in critical spaces for the nonlinear Schr\"odinger equation (NLS) on waveguide manifolds. Our work is primarily inspired by the recent paper of Kwak and Kwon \cite{KwakKwon} that established the local well-posedness of the periodic NLS with possibly non-algebraic nonlinearity. While we adopt a framework similar to \

Shihao Cai, Chongming Gao, Yang Zhang, Wentao Shi

To adapt large language models (LLMs) to ranking tasks, existing list-wise methods, represented by list-wise Direct Preference Optimization (DPO), focus on optimizing partial-order or full-order list ranking consistency for LLMs to enhance their ranking abilities. However, we argue that optimizing top-K ranking consistency could be more appropriate for real-

Daniel-M. Jimenez-Gutierrez, David Solans, Mohammed Elbamby, Nicolas Kourtellis

Federated Learning (FL) enables decentralized machine learning (ML) model training while preserving data privacy by keeping data localized across clients. However, non-independent and identically distributed (non-IID) data across clients poses a significant challenge, leading to skewed model updates and performance degradation. Addressing this, we propose PS

Yuqian Fu, Yuanheng Zhu, Jiajun Chai, Guojun Yin

Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting strategies that fail to adapt to the dynamic, context-dependent characteristics of LLM capabilities. In this work, we prop

Keisuke Sugiura, Mizuki Yasuda, Hiroki Matsutani

Embedded edge devices are often used as a computing platform to run real-world point cloud applications, but recent deep learning-based methods may not fit on such devices due to limited resources. In this paper, we aim to fill this gap by introducing PointODE, a parameter-efficient ResNet-like architecture for point cloud feature extraction based on a stack

Jiaxing Zhang, Xiaoou Liu, Dongsheng Luo, Hua Wei

Explaining Graph Neural Networks (GNNs) has garnered significant attention due to the need for interpretability, enabling users to understand the behavior of these black-box models better and extract valuable insights from their predictions. While numerous post-hoc instance-level explanation methods have been proposed to interpret GNN predictions, the reliab

Masahiro Kato, Yuki Ikeda, Kentaro Baba, Takashi Imai

In this study, we propose a method for identifying potential customers in targeted marketing by applying learning from positive and unlabeled data (PU learning). We consider a scenario in which a company sells a product and can observe only the customers who purchased it. Decision-makers seek to market products effectively based on whether people have loyalt

Yi-Han Iris Yin, Yuan Fang, Bin-Bin Zhang, Chen Deng

The prompt emission and afterglow phases of gamma-ray bursts (GRBs) have been extensively studied, yet the transition between these two phases remains inadequately characterized due to limited multiwavelength observational coverage. Among the recent growing samples of fast X-ray transients observed by Einstein Probe (EP), a subgroup of GRBs are captured with

Jiaming Yi, Ruirui Pan, Jishen Yang, Xiulong Yang

Improving the generalization ability of Vision-Language Pre-trained Models (VLMs) under test-time data distribution shifts remains a critical challenge. The existing Test-Time Adaptation (TTA) methods fall short in fully leveraging the model's internal knowledge, particularly in dynamically adapting to complex and hierarchical visual semantic information. In

Tuan-Luc Huynh, Thanh-Danh Le, Tam V. Nguyen, Trung-Nghia Le

In this paper, we address the crucial task of brain tumor segmentation in medical imaging and propose innovative approaches to enhance its performance. The current state-of-the-art nnU-Net has shown promising results but suffers from extensive training requirements and underutilization of pre-trained weights. To overcome these limitations, we integrate Axial

Luigi Sigillo, Shengfeng He, Danilo Comminiello

High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present Latent Wavelet Diffusion (LWD), a lightweight training framework that significantly improves detail and texture fidelity in ultra-high-resolution (2K-4K) image synt

Jiajun He, Naoki Sawada, Koichi Miyazaki, Tomoki Toda

In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditional methods address multi-talker ASR and contextual biasing separately, limiting performance in complex scenarios. We propose a unified framework that combines multi-talker overlap

Seunghan Lee, Taeyoung Park, Kibok Lee

Channel identifiability (CID) refers to the ability to distinguish between individual channels in time series (TS) modeling. The absence of CID often results in producing identical outputs for identical inputs, disregarding channel-specific characteristics. In this paper, we highlight the importance of CID and propose Channel Normalization (CN), a simple yet

Nicole Hsing

Multiple cognitive theories -- Global Workspace Theory, reconstructive episodic memory, inner speech, and complementary learning systems -- converge on a shared set of architectural principles: parallel specialized processing, integrative synthesis into a bounded unified representation, and reconstructive rather than accumulative maintenance. We test whether

Hengfeng Liu, Chunming Tang, Cuiling Fan, Rong Luo

In this paper, we establish the conditions for some finite abelian groups and the family all the $k$-sets in each of them summing up to an element $x$ to form $t$-designs. We fully characterize the sufficient and necessary conditions for the incidence structures to form $1$-designs in finite abelian $p$-groups, generalizing existing results on vector spaces

Yufan Huang, Peter Jin, Kent Quanrud

The textbook algorithm for real-weighted single-source shortest paths takes $O(m n)$ time on a graph with $m$ edges and $n$ vertices. The breakthrough algorithm by Fineman [Fin24] takes $\tilde{O}(m n^{8/9})$ randomized time. The running time was subsequently improved to $\tilde{O}(mn^{4/5})$ [HJQ25]. We build on [Fin24; HJQ25] to obtain an $\tilde{O}(m n^{3

Poonam Rani, Yuto Watanabe, Takuma Shiga, Yuya Sakuraba

Magneto-thermal transport is a promising physical property for thermal management applications. Magneto-thermal switching enables active control of heat flows, and a high switching ratio is desirable for improving performance. Here, we report on the observation of a huge magneto-thermal switching (MTS) effect in high-purity (5N) Pb polycrystalline wires, whe

Anjani kumar Polinati

The pervasive use of hybrid cloud computing models has changed enterprise as well as Information Technology services infrastructure by giving businesses simple and cost-effective options of combining on-premise IT equipment with public cloud services. hybrid cloud solutions deploy multifaceted models of security, performance optimization, and cost efficiency

Bingsen Chen, Shengjie Wang, Xi Ye, Chen Zhao

Multi-answer question answering (QA), where questions can have many valid answers, presents a significant challenge for existing retrieval-augmented generation-based QA systems, as these systems struggle to retrieve and then synthesize a large number of evidence passages. To tackle these challenges, we propose a new multi-answer QA framework -- Retrieval-aug

Chamika Sudusinghe, Gerasimos Gerogiannis, Damitha Lenadora, Charles Block

Sparse tensor programs are essential in deep learning and graph analytics, driving the need for optimized processing. To meet this demand, specialized hardware accelerators are being developed. Optimizing these programs for accelerators is challenging for two reasons: program performance is highly sensitive to variations in sparse inputs, and early-stage acc

Anum Nawaz, Hafiz Humza Mahmood Ramzan, Xianjia Yu, Zhuo Zou

Edge Intelligence (EI) serves as a critical enabler for privacy-preserving systems by providing AI-empowered computation and distributed caching services at the edge, thereby minimizing latency and enhancing data privacy. The integration of blockchain technology further augments EI frameworks by ensuring transactional transparency, auditability, and system-w

Ryuji Tanimoto

Let $k$ be an algebraically closed field of positive characteistic $p$ and let ${\rm SL}(n, k)$ denote the special linear algebraic group of degree $n$ over $k$. In this paper, we describe homomorphisms from ${\rm SL}(2, k)$ to ${\rm SL}(4, k)$. As by-products of this description, we give a classification of homomorphisms from ${\rm SL}(2, k)$ to ${\rm SL}(4

Yui Sudo, Yosuke Fukumoto, Muhammad Shakeel, Yifan Peng

Contextual biasing (CB) improves automatic speech recognition for rare and unseen phrases. Recent studies have introduced dynamic vocabulary, which represents context phrases as expandable tokens in autoregressive (AR) models. This method improves CB accuracy but with slow inference speed. While dynamic vocabulary can be applied to non-autoregressive (NAR) m

Jihyoung Jang, Minwook Bae, Minji Kim, Dilek Hakkani-Tur

As chatbots continue to evolve toward human-like, real-world, interactions, multimodality remains an active area of research and exploration. So far, efforts to integrate multimodality into chatbots have primarily focused on image-centric tasks, such as visual dialogue and image-based instructions, placing emphasis on the "eyes" of human perception while neg

Miao Ye, Suxiao Wang, Jiaguang Han, Yong Wang

Detecting anomalies in the data collected by WSNs can provide crucial evidence for assessing the reliability and stability of WSNs. Existing methods for WSN anomaly detection often face challenges such as the limited extraction of spatiotemporal correlation features, the absence of sample labels, few anomaly samples, and an imbalanced sample distribution. To

Mohammad Saqib Hasan, Saikat Chakraborty, Santu Karmaker, Niranjan Balasubramanian

LLM generated code often contains security issues. We address two key challenges in improving secure code generation. First, obtaining high quality training data covering a broad set of security issues is critical. To address this, we introduce a method for distilling a preference dataset of insecure and secure code pairs from frontier LLMs, along with a sec

Siqi Liang, Sumyeong Ahn, Paramveer S. Dhillon, Jiayu Zhou

In context learning (ICL) relies heavily on high quality demonstrations drawn from large annotated corpora. Existing approaches detect noisy annotations by ranking local perplexities, presuming that noisy samples yield higher perplexities than their clean counterparts. However, this assumption breaks down when the noise ratio is high and many demonstrations

Changyuan Zhao, Ruichen Zhang, Jiacheng Wang, Gaosheng Zhao

World models are emerging as a transformative paradigm in artificial intelligence, enabling agents to construct internal representations of their environments for predictive reasoning, planning, and decision-making. By learning latent dynamics, world models provide a sample-efficient framework that is especially valuable in data-constrained or safety-critica

Anum Nawaz, Muhammad Irfan, Xianjia Yu, Hamad Aldawsari

Federated learning (FL) is increasingly recognised for addressing security and privacy concerns in traditional cloud-centric machine learning (ML), particularly within personalised health monitoring such as wearable devices. By enabling global model training through localised policies, FL allows resource-constrained wearables to operate independently. Howeve

Matthew Brophy

As large language models (LLMs) become more powerful and pervasive across society, ensuring these systems are beneficial, safe, and aligned with human values is crucial. Current alignment techniques, like Constitutional AI (CAI), involve complex iterative processes. This paper argues that the Method of Wide Reflective Equilibrium (MWRE) -- a well-established

Ali Ghalavand, Sandi Klavžar, Xueliang Li

Let $G$ be a graph of order $ n(G) $, local metric dimension $ \dim_l(G) $, and clique number $ \omega(G) $. It has been conjectured that if $ n(G) \geq \omega(G) + 1 \geq 4 $, then $ \dim_l(G) \leq \left( \frac{\omega(G) - 2}{\omega(G) - 1} \right) n(G) $. In this paper the conjecture is confirmed for the case $ \omega(G) = 3 $. Consequently, a problem rega

Yaowei Bai, Ruiheng Zhang, Yu Lei, Jingfeng Yao

A global shortage of radiologists has been exacerbated by the significant volume of chest X-ray workloads, particularly in primary care. Although multimodal large language models show promise, existing evaluations predominantly rely on automated metrics or retrospective analyses, lacking rigorous prospective clinical validation. Janus-Pro-CXR (1B), a chest X

Daniel Israel, Guy Van den Broeck, Aditya Grover

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in practice struggle to achieve the speed of autoregressive models without significantly sacrificing quality. We therefore i

Yueqiang Song, Xueqi Sun, Dušan D. Repovš

This article deals with the following fractional $(p,q)$-Choquard equation with exponential growth of the form: $$\varepsilon^{ps}(-\Delta)_{p}^{s}u+\varepsilon^{qs}(-\Delta)_q^su+ Z(x)(|u|^{p-2}u+|u|^{q-2}u)=\varepsilon^{\mu-N}[|x|^{-\mu}*F(u)]f(u) \ \ \mbox{in} \ \ \mathbb{R}^N,$$ where $s\in (0,1),$ $\varepsilon>0$ is a parameter, $2\leq p=\frac{N}{s}<q,$

Songqi Zhou, Ruixue Liu, Yixing Wang, Jia Lu

Accurate fault detection in lithium-ion batteries is essential for the safe and reliable operation of electric vehicles and energy storage systems. However, existing methods often struggle to capture complex temporal dependencies and cannot fully leverage abundant unlabeled data. Although large language models (LLMs) exhibit strong representation capabilitie

Yi Yang, Jiaxuan Sun, Siqi Kou, Yihan Wang

Real-world embodied agents face long-horizon tasks, characterized by high-level goals demanding multi-step solutions beyond single actions. Successfully navigating these requires both high-level task planning (i.e., decomposing goals into sub-tasks) and low-level motion control (i.e., generating precise robot actions). While existing vision language action (

Ziwen Wang

Single-cell RNA sequencing (scRNA-seq) has revolutionized our understanding of cellular processes by enabling gene expression analysis at the individual cell level. Clustering allows for the identification of cell types and the further discovery of intrinsic patterns in single-cell data. However, the high dimensionality and sparsity of scRNA-seq data continu

Ása Skúladóttir, Heitor Ernandes, Diane K. Feuillet, Alice Mori

One of the major recent breakthroughs has been the discovery of the last Major Merger to happen in the history of the Milky Way. Around 10 Gyr ago the galaxy Gaia Enceladus, with estimated ~10% of the Milky Way mass, fell into its potential, bringing a large amount of stars which can be identified through their unique chemical and kinematic signatures. Simul

Kamal K. Barley, Andreas Ruffing, Sergei K. Suslov

We review Bohr's atomic model and its extension by Sommerfeld from a mathematical perspective of wave mechanics. The derivation of quantization rules and energy levels is revisited using semiclassical methods. Sommerfeld-type integrals are evaluated by elementary techniques, and connections with the Schr\"{o}dinger and Dirac equations are established. Histor

Ruixuan Chen, Wentao Li, Jiahui Xiao, Yuchen Li

Machine learning models often degrade when deployed on data distributions different from their training data. Challenging conventional validation paradigms, we demonstrate that higher in-distribution (ID) bias can lead to better out-of-distribution (OOD) generalization. Our Adaptive Distribution Bridge (ADB) framework implements this insight by introducing c

Huahui Yi, Wei Xu, Ziyuan Qin, Xi Chen

Existing prompt-based approaches have demonstrated impressive performance in continual learning, leveraging pre-trained large-scale models for classification tasks; however, the tight coupling between foreground-background information and the coupled attention between prompts and image-text tokens present significant challenges in incremental medical object

Ziqiang Feng, Raúl Ures

We show that any conservative partially hyperbolic diffeomorphism homotopic to the identity is accessible unless the fundamental group of its ambient 3-manifold is virtually solvable. As a consequence, such diffeomorphisms are ergodic, giving an affirmative answer to the Hertz-Hertz-Ures Ergodicity Conjecture in the homotopy class of identity.

Joshua Akingbade, Jianhua Yang, Mir Seyedebrahimi

Coding is a fundamental skill required in the engineering discipline, and much work exists exploring better ways of teaching coding in the higher education context. In particular, Code Snippets (CSs) are approved to be an effective way of introducing programming language units to students. CSs are portions of source code of varying size and content. They can

Haiquan Zhao, Chengjin Li

Recently, the proposal of the least mean square (LMS) and recursive least squares (RLS) algorithm for graph signal processing (GSP) provides excellent solutions for processing signals defined on irregular structures such as sensor networks. The existing work has completed the steady state error analysis of the GSP LMS algorithm and GSP RLS algorithm in Gauss

Vishwanath Pratap Singh, Md. Sahidullah, Tomi Kinnunen

Children's automatic speech recognition (ASR) often underperforms compared to that of adults due to a confluence of interdependent factors: physiological (e.g., smaller vocal tracts), cognitive (e.g., underdeveloped pronunciation), and extrinsic (e.g., vocabulary limitations, background noise). Existing analysis methods examine the impact of these factors in

Seonghyun Jeong

The testing-based approach is a fundamental tool for establishing posterior contraction rates. Although the Hellinger metric is attractive owing to the existence of a desirable test function, it is not directly applicable in Gaussian models, because translating the Hellinger metric into more intuitive metrics typically requires strong boundedness conditions.

Montri Maleewong, Roger Grimshaw

In recent papers, denoted by MG24, MG25 in this text, we used the Korteweg-de Vries (KdV) equation and its two-dimensional extension, the Kadomtsev-Petviashvili (KP) equation to describe the evolution of wind-driven water wave packets in shallow water. Both equations were modified to include the effect of wind forcing, modelled using the Miles critical level

Kordel K. France, Rohith Peddi, Nik Dennler, Ovidiu Daescu

Despite extraordinary progress in artificial intelligence (AI), modern systems remain incomplete representations of human cognition. Vision, audition, and language have received disproportionate attention due to well-defined benchmarks, standardized datasets, and consensus-driven scientific foundations. In contrast, olfaction - a high-bandwidth, evolutionari

Yi Peng, Haiquan Zhao, Jinhui Hu

The continuous development of new adaptive filters (AFs) based on novel cost functions (CFs) is driven by the demands of various application scenarios and noise environments. However, these algorithms typically demonstrate optimal performance only in specific conditions. In the event of the noise change, the performance of these AFs often declines, rendering

Jiawei Gu, Shangsong Liang

Effective decision-making in Large Language Models (LLMs) is essential for handling intricate tasks. However, existing approaches prioritize performance but often overlook the balance between effectiveness and computational cost. To address this, we first introduce the 3E Criteria to systematically assess the cost-effectiveness of search strategies, revealin

Ziwei Zhao, Xizi Wang, Yuchen Wang, Feng Cheng

The increasing popularity of egocentric cameras has generated growing interest in studying multi-camera interactions in shared environments. Although large-scale datasets such as Ego4D and Ego-Exo4D have propelled egocentric vision research, interactions between multiple camera wearers remain underexplored-a key gap for applications like immersive learning a

Tiefeng Jiang, Tuan Pham

We study the high-dimensional uniformity testing problem, which involves testing whether the underlying distribution is the uniform distribution, given $n$ data points on the $p$-dimensional unit hypersphere. While this problem has been extensively studied in scenarios with fixed $p$, only three testing procedures are known in high-dimensional settings: the

Xingyu Wang

This work investigates the vector-valued Allen-Cahn equation with potentials of high-dimensional double-wells under Robin boundary conditions. We establish local-in-time convergence of solutions to mean curvature flow with a fixed contact angle $0<\alpha\leq 90^\circ$, for a broad class of boundary energy densities and well-prepared initial data. The limitin

Ge Qu, Jinyang Li, Bowen Qin, Xiaolong Li

Current self-correction approaches in text-to-SQL face two critical limitations: 1) Conventional self-correction methods rely on recursive self-calls of LLMs, resulting in multiplicative computational overhead, and 2) LLMs struggle to implement effective error detection and correction for declarative SQL queries, as they fail to demonstrate the underlying re

Thanh-Nhan Nguyen, Minh-Phuong Tran

In this study, we deal with generalized regularity properties for solutions to $p$-Laplace equations with degenerate matrix weights. It has already been observed in previous interesting works [A. Kh. Balci, L. Diening, R. Giova, A. Passarelli di Napoli, SIAM J. Math. Anal. 54(2022), 2373-2412] and [A. Kh. Balci, S.-S. Byun, L. Diening, H.-S. Lee, J. Math. Pu

Tong Zhang, Tian-Tian Li, Jing-Ru Wang, Yu-Wen Zhang

The temperature distribution within cells, especially the debates on mitochondrial temperature, has recently attracted widespread attention. Some studies have claimed that the temperature of mitochondria can reach up to 50-53 degrees Celsius. Yet others have questioned that this is due to measurement errors from fluorescent thermometry caused by other factor

Mikko Stenlund

Predictive coding networks (PCNs) constitute a biologically inspired framework for understanding hierarchical computation in the brain, and offer an alternative to traditional feedforward neural networks in ML. This note serves as a quick, onboarding introduction to PCNs for machine learning practitioners. We cover the foundational network architecture, infe

Ni Mu, Hao Hu, Xiao Hu, Yiqin Yang

Preference-based reinforcement learning (PbRL) bypasses explicit reward engineering by inferring reward functions from human preference comparisons, enabling better alignment with human intentions. However, humans often struggle to label a clear preference between similar segments, reducing label efficiency and limiting PbRL's real-world applicability. To ad

Fang-Fang Du, Xin-Shan Du, Zhuo-Ya Bai, Qiu-Lin Tan

The realization of quantum networks that exploit multiqubit entanglement opens avenues for transformative applications in the realm of quantum communication. In the paper, we present a set of heralded deterministic protocols designed for the generation of two-qubit, three-qubit, and $N$-qubit Knill-Laflamme-Milburn (KLM) states by the photon scattering prope

Keyeun Lee, Seolhee Lee, Esther Hehsun Kim, Yena Ko

Effective communication training is essential to preparing nurses for high-quality patient care. While standardized patient (SP) simulations provide valuable experiential learning, they are often costly and inflexible. Virtual patient (VP) systems offer a scalable alternative, but most fail to adapt to the varying communication skills of trainees. In particu

Yakun Song, Jiawei Chen, Xiaobin Zhuang, Chenpeng Du

Neural audio codecs have made significant strides in efficiently mapping raw audio waveforms into discrete token representations, which are foundational for contemporary audio generative models. However, most existing codecs are optimized primarily for reconstruction quality, often at the expense of the downstream modelability of the encoded tokens. Motivate

Yutong Huang, Zhiyuan Guo, Yiying Zhang

Memory prefetching has long boosted CPU caches and is increasingly vital for far-memory systems, where large portions of memory are offloaded to cheaper, remote tiers. While effective prefetching requires accurate prediction of future accesses, prior ML approaches have been limited to simulation or small-scale hardware. We introduce FarSight, the first Linux

Ishan Paranjape, Islam Hussein, Jeremy Murray-Krezan, Sean Phillips

Consensus is a popular technique for distributed state estimation. This formulation allows networks of connected agents or sensors to exchange information about the distribution of a set of targets with their immediate neighbors without the need of a centralized node or layer. We present decentralized consensus-based fusion techniques for a system whose targ

Xuyuan Liu, Lei Hsiung, Yaoqing Yang, Yujun Yan

Understanding how feature representations evolve across layers in large language models (LLMs) is key to improving their interpretability and robustness. While recent studies have identified critical layers linked to specific functions or behaviors, these efforts typically rely on data-dependent analyses of fine-tuned models, limiting their use to post-hoc s

Siavash Shams, Richard Antonello, Gavin Mischler, Stephan Bickel

Decoding continuous language from neural signals remains a significant challenge in the intersection of neuroscience and artificial intelligence. We introduce Neuro2Semantic, a novel framework that reconstructs the semantic content of perceived speech from intracranial EEG (iEEG) recordings. Our approach consists of two phases: first, an LSTM-based adapter a

Yichen Ma

We study the Hopf monoid of convex geometries, which contains partial orders as a Hopf submonoid, and investigate the combinatorial invariants arising from canonical characters. Each invariant consists of a pair: a polynomial and a more general quasisymmetric function. We give combinatorial descriptions of the polynomial invariants and prove combinatorial re

Qi Qin, Erbo Li, Xingxiang Li, Yifan Sun

Distributed and federated learning are important tools for high-dimensional classification of large datasets. To reduce computational costs and overcome the curse of dimensionality, feature screening plays a pivotal role in eliminating irrelevant features during data preprocessing. However, data heterogeneity, particularly label shifting across different cli

Qiansheng Liu, Takashi Okamoto, Taira Oogi, Masahiro Nagashima

We investigate the origin of the observed metallicity difference between star-forming and passive galaxies using the semi-analytic galaxy formation model nu2GC. Our fiducial model successfully reproduces the observed metallicity differences in local galaxies while simultaneously matching the potential-metallicity relations of both star-forming and passive ga

Mohammad Shamim Ahsan, Salekul Islam, Swakkhar Shatabda

The widespread adoption of the Internet of Things (IoT) has raised a new challenge for developers since it is prone to known and unknown cyberattacks due to its heterogeneity, flexibility, and close connectivity. To defend against such security breaches, researchers have focused on building sophisticated intrusion detection systems (IDSs) using machine learn

Jiawen Stefanie Zhu, Jian Zhao

Grandparent-grandchild bonds are crucial for both parties. Many immigrant families are geographically dispersed, and the grandparents and grandchildren need to rely on remote communication to maintain their relationships. In addition to geographical separation, grandparents and grandchildren in such families also face language and culture barriers during rem

Ruibo Fu, Xiaopeng Wang, Zhengqi Wen, Jianhua Tao

Existing methods for deepfake audio detection have demonstrated some effectiveness. However, they still face challenges in generalizing to new forgery techniques and evolving attack patterns. This limitation mainly arises because the models rely heavily on the distribution of the training data and fail to learn a decision boundary that captures the essential

Satyavrat Wagle, Akshay Malhotra, Shahab Hamidi-Rad, Aditya Sant

In recent years, machine learning (ML) methods have become increasingly popular in wireless communication systems for several applications. A critical bottleneck for designing ML systems for wireless communications is the availability of realistic wireless channel datasets, which are extremely resource-intensive to produce. To this end, the generation of rea

Pappu Jha, Hanzla Hamid, Oluseyi Olukola, Ashim Dahal

Passwords remain one of the most common methods for securing sensitive data in the digital age. However, weak password choices continue to pose significant risks to data security and privacy. This study aims to solve the problem by focusing on developing robust password strength estimation models using adversarial machine learning, a technique that trains mo

Feng Wang, Yiding Sun, Jiaxin Mao, Wei Xue

Large language models (LLMs) have demonstrated remarkable capabilities across various professional domains, with their performance typically evaluated through standardized benchmarks. In the financial field, the stringent demands for professional accuracy and real-time data processing often necessitate the use of retrieval-augmented generation (RAG) techniqu

Yuexin Liao, Kota Saito, Alec Sandroni

We study random utility (RU) rationality with aggregation when the underlying alternatives in each aggregate vary across consumers and are unobserved, as is typical for an outside option. RUM over the underlying alternatives is the natural assumption on the data generating process, while an aggregated random utility model (ARUM) is the standard empirical too

Yizhou Gao, Tim Barfoot

We present a new method to combine several rigidly connected but physically separated IMUs through a weighted average into a single virtual IMU (VIMU). This has the benefits of (i) reducing process noise through averaging, and (ii) allowing for tuning the location of the VIMU. The VIMU can be placed to be coincident with, for example, a camera frame or GNSS