May 2025 arXiv papers — page 2

Richard E. Neddo, Emmanuel Atindama, Zander W. Blasingame, Chen Liu

Adversarial attacks have emerged as a critical threat to autonomous driving systems. These attacks exploit the underlying neural network, allowing small, almost invisible, perturbations to alter the behavior of such systems in potentially malicious ways, e.g., causing a traffic sign classification network to misclassify a stop sign as a speed limit sign. Pri

Marziyeh Mohammadi, Mohsen Vejdanihemmat, Mahshad Lotfinia, Mirabela Rusu

Differential privacy (DP) is a key technique for protecting sensitive patient data in medical deep learning (DL). As clinical models grow more data-dependent, balancing privacy with utility and fairness has become a critical challenge. This scoping review synthesizes recent developments in applying DP to medical DL, with a particular focus on DP-SGD and alte

Marco Di Gennaro, Mario D'Onghia, Mario Polino, Stefano Zanero

Anti-analysis techniques, particularly packing, challenge malware analysts, making packer identification fundamental. Existing packer identifiers have significant limitations: signature-based methods lack flexibility and struggle against dynamic evasion, while Machine Learning approaches require extensive training data, limiting scalability and adaptability.

Pinjun Zheng, Ruiqi Wang, Yuchen Zhang, Md. Jahangir Hossain

The transition to sixth-generation (6G) networks calls for wireless transceivers with enhanced adaptability and efficiency. Reconfigurable antennas (RAs) have emerged as a promising solution, enabling dynamic control over the electromagnetic properties of individual antenna elements. This article provides an overview of RA technologies for 6G systems, encomp

Aris J. Aristorenas

We propose a permutation-invariant neural architecture for indoor localization using RSSI scans from Wi-Fi access points. Each scan is modeled as an unordered set of (BSSID, RSSI) pairs, where BSSIDs are mapped to learned embeddings and concatenated with signal strength. These are processed by a Set Transformer, enabling the model to handle variable-length,

Zakir Hussain Shaik, Sai Subramanyam Thoota, Emil Björnson, Erik G. Larsson

We propose a novel resource-efficient over-the-air(OTA) computation framework to address the huge fronthaul computational and control overhead requirements in cell-free massive multiple-input multiple-output (MIMO) networks. We show that the global sufficient statistics to decode the data symbols can be computed OTA using the locally available information at

Marco Di Gennaro, Francesco Panebianco, Marco Pianta, Stefano Zanero

Money laundering is a financial crime that poses a serious threat to financial integrity and social security. The growing number of transactions makes it necessary to use automatic tools that help law enforcement agencies detect such criminal activity. In this work, we present Amatriciana, a novel approach based on Graph Neural Networks to detect money laund

Femi Bello, Anubrata Das, Fanzhi Zeng, Fangcong Yin

It has been hypothesized that neural networks with similar architectures trained on similar data learn shared representations relevant to the learning task. We build on this idea by extending the conceptual framework where representations learned across models trained on the same data can be expressed as linear combinations of a \emph{universal} set of basis

Yu Huang, Junhao Chen, Shuliang Liu, Hanqian Li

The rapid development of Artificial Intelligence Generated Content (AIGC) has led to significant progress in video generation, but also raises serious concerns about intellectual property protection and reliable content tracing. Watermarking is a widely adopted solution to this issue, yet existing methods for video generation mainly follow a post-generation

Nikolaos Sampanis

This paper presents an innovative pedagogical framework employing tangible interactive games to enhance artificial intelligence (AI) knowledge and literacy among elementary education students. Recognizing the growing importance of AI competencies in the 21st century, this study addresses the critical need for age-appropriate, experiential learning tools that

Neil De La Fuente, Oscar Sainz, Iker García-Ferrero, Eneko Agirre

Information Extraction (IE) systems are traditionally domain-specific, requiring costly adaptation that involves expert schema design, data annotation, and model training. While Large Language Models have shown promise in zero-shot IE, performance degrades significantly in unseen domains where label definitions differ. This paper introduces GUIDEX, a novel m

Kym Derriman

The Quantum Skip Gate (QSG) is a unitary circuit primitive that coherently superposes the execution and omission of an expensive quantum subroutine based on the outcome of a cheaper preceding subroutine, without mid-circuit measurement or loss of coherence. By using a control qubit and an internal flag, QSG enables conditional quantum logic entirely within a

Alessandro De Stefani, Thomas Polstra, Austyn Simpson

We construct examples of noetherian three-dimensional local geometrically normal domains of prime characteristic which are $F$-injective but not $F$-full. Along the way, we find examples of two-dimensional local geometrically normal domains which are $F$-injective but not $F$-anti-nilpotent. A crucial theme of our constructions is the behavior of $F$-injecti

Satoshi Tanaka, Samrat Thapa, Kok Seang Tan, Amadeusz Szymko

In recent years, machine learning technologies have played an important role in robotics, particularly in the development of autonomous robots and self-driving vehicles. As the industry matures, robotics frameworks like ROS 2 have been developed and provides a broad range of applications from research to production. In this work, we introduce AWML, a framewo

Ana Rita Valente, Rufael Marew, Hawau Olamide Toyin, Hamdan Al-Ali

Stuttering is a complex disorder that requires specialized expertise for effective assessment and treatment. This paper presents an effort to enhance the FluencyBank dataset with a new stuttering annotation scheme based on established clinical standards. To achieve high-quality annotations, we hired expert clinicians to label the data, ensuring that the resu

Aditya Ravuri, Neil D. Lawrence

Protein Language Models (PLMs) such as ESM2 have been shown to be capable of zero-shot prediction of critical scalar properties of proteins (fitness). In this work, we show that injecting a dropout layer at inference time between a PLM's featurizer/embedding layer and its transformer, and averaging its output akin to Monte-Carlo dropout increases zero-shot p

Weijie Xu, Shixian Cui, Xi Fang, Chi Xue

Large language models (LLMs) are increasingly evaluated on single-answer multiple-choice tasks, yet many real-world problems require identifying all correct answers from a set of options. This capability remains underexplored. We introduce SATA-BENCH, the first dedicated benchmark for evaluating LLMs on Select All That Apply (SATA) questions across diverse d

Yuliang Ji, Jian Wu, Yuanzhe Xi

Deep neural networks have achieved substantial success across various scientific computing tasks. A pivotal challenge within this domain is the rapid and parallel approximation of matrix inverses, critical for numerous applications. Despite significant progress, there currently exists no universal neural-based method for approximating matrix inversion. This

Hanjun Luo, Shenyu Dai, Chiming Ni, Xinfeng Li

Despite the rapid advancement of LLM-based agents, the reliable evaluation of their safety and security remains a significant challenge. Existing rule-based or LLM-based evaluators often miss dangers in agents' step-by-step actions, overlook subtle meanings, fail to see how small issues compound, and get confused by unclear safety or security rules. To overc

Alan G. Cesar, Mario Novello, Eduardo Bittencourt, Fernando A. Franco

We investigate the cosmological dynamics induced by nonlinear electrodynamics in a homogeneous and isotropic universe, focusing on the role of primordial electromagnetic fields with random spatial orientations. Building upon a generalization of the Tolman-Ehrenfest averaging procedure, we derive a modified energy-momentum tensor consistent with the spacetime

Yao Ji, Zhuoyi Pang, Fei Yao, Jian-Hui Zhang

It is well-known that in the study of mixing between nonlocal gluon and quark bilinear operators there exists an ambiguity when relating coordinate space and momentum space results, which can be conveniently resolved through Mellin moments matching in both spaces. In this work, we show that this ambiguity is due to the lack of a proper regularization prescri

M. El Maghri, H. Sellak

We characterize approximate global optimal solutions (${\varepsilon}$-optima) to reverse optimization problems, namely, problems whose non-convex constraint is of the form $h(x) \geq 0$. This issue has not been addressed previously in the literature. Our idea consists of converting the reverse program into an unconstrained bicriteria DC program. The main con

Lorenzo Jaime Yu Flores, Ori Ernst, Jackie Chi Kit Cheung

Well-calibrated model confidence scores can improve the usefulness of text generation models. For example, users can be prompted to review predictions with low confidence scores, to prevent models from returning bad or potentially dangerous predictions. However, confidence metrics are not always well calibrated in text generation. One reason is that in gener

Huy Ba Do, Vy Le-Phuong Huynh, Luan Thanh Nguyen

Toxic speech on online platforms is a growing concern, impacting user experience and online safety. While text-based toxicity detection is well-studied, audio-based approaches remain underexplored, especially for low-resource languages like Vietnamese. This paper introduces ViToSA (Vietnamese Toxic Spans Audio), the first dataset for toxic spans detection in

Ekram Alam, Abu Sufian, Paramartha Dutta, Marco Leo

Unintentional or accidental falls are one of the significant health issues in senior persons. The population of senior persons is increasing steadily. So, there is a need for an automated fall detection monitoring system. This paper introduces a vision-based fall detection system using a pre-trained 3D CNN. Unlike 2D CNN, 3D CNN extracts not only spatial but

Wei Chen, Yuxuan Liang

Spatio-temporal forecasting is crucial in many domains, such as transportation, meteorology, and energy. However, real-world scenarios frequently present challenges such as signal anomalies, noise, and distributional shifts. Existing solutions primarily enhance robustness by modifying network architectures or training procedures. Nevertheless, these approach

Adam Visokay, Ruth Bagley, Ian Kennedy, Chris Hess

Rental listings offer a window into how urban space is socially constructed through language. We analyze Chicago Craigslist rental advertisements from 2018 to 2024 to examine how listing agents characterize neighborhoods, identifying mismatches between institutional boundaries and neighborhood claims. Through manual and large language model annotation, we cl

Daniele Molino, Camillo Maria Caruso, Filippo Ruffini, Paolo Soda

Generating semantically controllable 3D CT volumes from radiology reports requires more than a rich text encoder, it requires vision-language alignment grounded in volumetric space. Existing Text-to-CT approaches condition generation on encoders pretrained with language only or 2D vision-language objectives, providing conditioning signals that are linguistic

Sebastián Higuera, Armando Reyes

We investigate the diameter and girth of the nilpotent graph for skew PBW extensions over $2$-primal rings, generalizing similar results on skew polynomial rings. Under certain compatibility conditions, we establish bounds for the diameter of the nilpotent graph and prove invariance of the girth under polynomial extensions.

Viktor D. Zozulia, Natalia Ya. Sotnikova, Anton A. Smirnov

For the first time, we investigate the resonant structure of $N$-body galactic bar at the stage of buckling using action-angle variables. We studied the evolution of vertical actions ($J_z$) and angles associated with vertical resonance ($\theta_\mathrm{res}=\theta_z - \theta_R$) for all orbits in the bar. For this purpose, we divide the orbits into types ac

Young Jin Park, Francois Germain, Jing Liu, Ye Wang

Decision-making in building energy systems critically depends on the predictive accuracy of relevant time-series models. In scenarios lacking extensive data from a target building, foundation models (FMs) represent a promising technology that can leverage prior knowledge from vast and diverse pre-training datasets to construct accurate probabilistic predicto

Guy Ohad, María Camarasa-Gómez, Jeffrey B. Neaton, Ashwin Ramasubramaniam

Optimal tuning of functional parameters in density functional theory approximations, based on enforcing the ionization potential theorem, has emerged as the method of choice for the non-empirical prediction of the electronic structure of finite systems. This method has recently been extended to the bulk limit, based on an ansatz that generalizes the ionizati

Niyati Bafna, Matthew Wiesner

Prior research indicates that LID model performance significantly declines on accented speech; however, the specific causes, extent, and characterization of these errors remain under-explored. (i) We identify a common failure mode on accented speech whereby LID systems often misclassify L2 accented speech as the speaker's native language or a related languag

Srikanth Avasarala, Serena Wang, Juba Ziani

We study how partial information about scoring rules affects fairness in strategic learning settings. In strategic learning, a learner deploys a scoring rule, and agents respond strategically by modifying their features -- at some cost -- to improve their outcomes. However, in our work, agents do not observe the scoring rule directly; instead, they receive a

Yang Zhang, Karteekeya Sastry, Iyla Rossi, Joshua Olick-Gibson

Noninvasive imaging deep into the adult brain at submillimeter and millisecond scales remains a challenge in medical imaging. Here, we report a helmet based ultrasound brain imager built from a customized helmet, a scanned ultrasound array, and three dimensional printing for real time imaging of human brain anatomical and functional information. Through its

Gage K. R. Hooper

While many neural networks focus on layers to process information, the GAIN model uses a grid-based structure to improve biological plausibility and the dynamics of the model. The grid structure helps neurons to interact with their closest neighbors and improve their connections with one another, which is seen in biological neurons. While also being implemen

Julia Beuster, Carsten Andrich, Sebastian Giehl, Marc Miranda

As integrated sensing and communication (ISAC) capabilities become more prevalent in the mobile 6G radio landscape, there is a substantial opportunity to enhance situational awareness across diverse applications through multi-static radar sensing within meshed ISAC networks. To facilitate the development and testing of detection and localization algorithms a

Andrzej A. Zdziarski, Gregoire Marcel, Alexandra Veledina, Aleksandra Olejak

We review current challenges in understanding the values and origin of the spins of black holes in binaries. Thanks to recent advances in astrophysical instrumentation, the spins can now be measured using both gravitational waves emitted by merging black holes and electromagnetic radiation from accreting X-ray binaries containing black holes. A key finding o

Haesung Pyun, Yoonah Park, Yohan Jo

In dialogue state tracking (DST), in-context learning comprises a retriever that selects labeled dialogues as in-context examples and a DST model that uses these examples to infer the dialogue state of the query dialogue. Existing methods for constructing training data for retrievers suffer from three key limitations: (1) the synergistic effect of examples i

Laurette S. Tuckerman

Turbulent Taylor-Couette flow displays traces of axisymmetric Taylor vortices even at high Reynolds numbers. With this motivation, Feldmann & Avila (2025) carry out long-time numerical simulations of axisymmetric high-Reynolds-number Taylor-Couette flow. They find that the Taylor vortices, using the only degree of freedom that remains available to them, carr

Ming-Yu Chung, Jiashuo Fan, Hancheng Ye, Qinsi Wang

Model Reprogramming (MR) is a resource-efficient framework that adapts large pre-trained models to new tasks with minimal additional parameters and data, offering a promising solution to the challenges of training large models for diverse tasks. Despite its empirical success across various domains such as computer vision and time-series forecasting, the theo

Davide Dardari

To meet the stringent requirements of next-generation wireless networks, multiple-input multiple-output (MIMO) technology is expected to become massive and pervasive. Unfortunately, this could pose scalability issues in terms of complexity, power consumption, cost, and processing latency. Therefore, novel technologies and design approaches, such as the recen

Jingyi Yang, Shuai Shao, Dongrui Liu, Jing Shao

With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk principles designed and aligned for general MLLMs in dialogue scenarios be effectively transferred to real-world compute

Rui Zhou, Igor Vinograd, Hadrien Mayffre, Juan Porras

Charge-density wave (CDW) order is a key property of high-Tc cuprates, but its boundaries in the phase diagram and potential connections to other phases remain controversial. We report nuclear magnetic resonance (NMR) measurements in the prototypical cuprate YBa2Cu3Oy demonstrating that short-range static CDW order remains robust at optimal doping (p=0.165),

Shan Shan, Chongjun Ouyang, Yong Li, Yuanwei Liu

The pinching-antenna system (PASS) reconfigures wireless links through pinching beamforming, in which the activated locations of pinching antennas (PAs) along dielectric waveguides are optimized. This article investigates the application of PASS in multicast communication systems, where pinching beamforming is designed to maximize the multicast rate. i) In t

Andreu Ballus Santacana

We present a tractable, incremental framework for topological dialogue semantics based on finite, discrete semantic spaces. Building on the intuition that utterances correspond to open sets and their combinatorial relations form a simplicial complex (the dialogue nerve), we give a rigorous foundation, a provably correct incremental algorithm for nerve update

Ziqi Liu, Pei Zeng, Yi Ding

Real-world multichannel time series prediction faces growing demands for efficiency across edge and cloud environments, making channel compression a timely and essential problem. Motivated by the success of Multiple-Input Multiple-Output (MIMO) methods in signal processing, we propose a predictability-aware compression-decompression framework to reduce runti

Julian Quevedo, Ansh Kumar Sharma, Yixiang Sun, Varad Suryavanshi

Evaluating robot control policies is difficult: real-world testing is costly, and handcrafted simulators require manual effort to improve in realism and generality. We propose a world-model-based policy evaluation environment (WorldGym), an autoregressive, action-conditioned video generation model which serves as a proxy to real world environments. Policies

Running Yang, Wenlong Deng, Minghui Chen, Yuyin Zhou

Clinical tasks such as diagnosis and treatment require strong decision-making abilities, highlighting the importance of rigorous evaluation benchmarks to assess the reliability of large language models (LLMs). In this work, we introduce a knowledge-guided data augmentation framework that enhances the difficulty of clinical multiple-choice question (MCQ) data

Adam R. Vernon, Mitch Peaks

A scheme for excitation and individual addressing using Rydberg states of trapped Barium ions is presented for the purpose of fast gates and entanglement. Dipole matrix elements, dynamic polarizabilities, and one- and two-photon transition strengths are computed with a Supersymmetric Wentzel-Kramers-Brillouin (SWKB) method. A favorable two-photon excitation

Mikhail V. Kochetov, Serhii D. Koval

We study generic graded contractions of Lie algebras from the perspectives of group cohomology, affine algebraic geometry and monoidal categories. We show that generic graded contractions with a fixed support are classified by a certain abelian group, which we explicitly describe. Analyzing the variety of generic graded contractions as an affine algebraic va

José A. S. Laranjeira, Nicolas F. Martins, Kleuton A. L. Lima, Luis A. Cabral

The shift from fossil fuels to renewable energy sources is essential for reducing global carbon emissions and addressing climate change. Developing advanced materials for efficient hydrogen storage enables sustainable energy solutions in this context. Herein, we propose sodium-decorated TPHE-graphene as a high-performance two-dimensional material for hydroge

Petros Raptopoulos, Giorgos Filandrianos, Maria Lymperaiou, Giorgos Stamou

Contract review is a complex and time-intensive task that typically demands specialized legal expertise, rendering it largely inaccessible to non-experts. Moreover, legal interpretation is rarely straightforward-ambiguity is pervasive, and judgments often hinge on subjective assessments. Compounding these challenges, contracts are usually confidential, restr

JungWoo Chae, Jiyoon Kim, Sangheum Hwang

Personalizing diffusion models to specific users or concepts remains challenging, particularly when only a few reference images are available. Existing methods such as DreamBooth and Textual Inversion often overfit to limited data, causing misalignment between generated images and text prompts when attempting to balance identity fidelity with prompt adherenc

Tim Möbus, Andreas Bluhm, Tuvia Gefen, Yu Tong

Discrete and continuous variables oftentimes require different treatments in many learning tasks. Identifying the Hamiltonian governing the evolution of a quantum system is a fundamental task in quantum learning theory. While previous works mostly focused on quantum spin systems, where quantum states can be seen as superpositions of discrete bit-strings, rel

Ruiming Min, Minghao Liu

With the advancement of modern medicine and the development of technologies such as MRI, CT, and cellular analysis, it has become increasingly critical for clinicians to accurately interpret various diagnostic images. However, modern medical education often faces challenges due to limited access to high-quality teaching materials, stemming from privacy conce

Jose A. S. Laranjeira, Nicolas F. Martins, Kleuton A. L. Lima, Bill. D. Aparicio-Huacarpuma

Potassium-decorated graphenyldiene (K@GPD) is investigated as a promising two-dimensional material for reversible hydrogen storage using first-principles density functional theory calculations. Potassium atoms bind strongly to the GPD monolayer, and ab initio molecular dynamics (AIMD) simulations confirm the thermal stability of the functionalized system at

Samuel D. Tomlinson, Aliki M. Tsopelakou, Tzia M. Onn, Steven R. H. Barrett

Atmospheric pollution from particulate matter, volatile organic compounds and greenhouse gases is a critical environmental and public health issue, leading to respiratory diseases and climate change. A potential mitigation strategy involves utilising ventilation systems, which process large volumes of indoor and outdoor air and remove particulate pollutants

Karina Arias-Calluari, Theotime Colin, Tanya Latty, Mary Myerscough

Honey bees face an increasing number of stressors that disrupt the natural behaviour of colonies and, in extreme cases, can lead to their collapse. Quantifying the status and resilience of colonies is essential to measure the impact of stressors and to identify colonies at risk. In this manuscript, we present and apply new methodologies to efficiently diagno

Jingke Sun, Liang Yang, Alexandros-Apostolos A. Boulogeorgos, Theodoros A. Tsiftsis

To enhance both the sensing and covert communication performance, a dual-unmanned aerial vehicle (UAV)-aided scheme is proposed for integrated sensing and communication networks, in which one UAV maneuvers as the aerial dual-functional base-station (BS), while another UAV flies as the cooperative jammer. Artificial noise (AN) transmitted by the jamming UAV i

Xianghui Ze, Beiyi Zhu, Zhenbo Song, Jianfeng Lu

Generating multiview-consistent $360^\circ$ ground-level scenes from satellite imagery is a challenging task with broad applications in simulation, autonomous navigation, and digital twin cities. Existing approaches primarily focus on synthesizing individual ground-view panoramas, often relying on auxiliary inputs like height maps or handcrafted projections,

Tanvir Khan, F. Parvin, S. H. Naqib

In this investigation, we have used the density functional theory (DFT) to investigate several aspects of the half-Heusler compound HoPdBi. The following properties have been studied: spin polarized electronic properties, magnetic moment, phonon dispersion with phonon density of states, structural, elastic properties, optical characteristics, and thermo-phys

William Andrew Simon, Leonid Yavits, Konstantina Koliogeorgi, Yann Falevoz

Low-cost, high-throughput DNA and RNA sequencing (HTS) data is the backbone of the life sciences. Genome sequencing is now becoming a part of Predictive, Preventive, Personalized, and Participatory (termed 'P4') medicine. All genomic data are currently processed in energy-hungry computer clusters and centers, necessitating data transfer, consuming substantia

Danfeng Li, Hui Zhang, Sheng Wang, Jiacheng Li

Despite recent advances in diffusion models, top-tier text-to-image (T2I) models still struggle to achieve precise spatial layout control, i.e. accurately generating entities with specified attributes and locations. Segmentation-mask-to-image (S2I) generation has emerged as a promising solution by incorporating pixel-level spatial guidance and regional text

Stepan Bosak, Miloslav Capek, Jiri Matas

This paper presents a novel bi-level topology optimization strategy within the method-of-moments paradigm. The proposed approach utilizes an auxiliary variables called edge resistivities related to the Rao-Wilton-Glisson method-of-moments basis functions, for a definition of a fast local optimization algorithm. The local algorithm combines automatic differen

Chunyu Wei, Wenji Hu, Xingjia Hao, Yunhai Wang

Graph anomaly detection faces significant challenges due to the scarcity of reliable anomaly-labeled datasets, driving the development of unsupervised methods. Graph autoencoders (GAEs) have emerged as a dominant approach by reconstructing graph structures and node features while deriving anomaly scores from reconstruction errors. However, relying solely on

Michael Brocidiacono, James Wellnitz, Konstantin I. Popov, Alexander Tropsha

Despite recent advances in protein-ligand structure prediction, deep learning methods remain limited in their ability to accurately predict binding affinities, particularly for novel protein targets dissimilar from the training set. In contrast, physics-based binding free energy calculations offer high accuracy across chemical space but are computationally p

Hongyao Tang, Johan Obando-Ceron, Pablo Samuel Castro, Aaron Courville

Plasticity, or the ability of an agent to adapt to new tasks, environments, or distributions, is crucial for continual learning. In this paper, we study the loss of plasticity in deep continual RL from the lens of churn: network output variability for out-of-batch data induced by mini-batch training. We demonstrate that (1) the loss of plasticity is accompan

Xudong Ma, Nantheera Anantrasirichai, Stefanos Bolomytis, Alin Achim

The diagnosis of prostate cancer increasingly depends on multimodal imaging, particularly magnetic resonance imaging (MRI) and transrectal ultrasound (TRUS). However, accurate registration between these modalities remains a fundamental challenge due to the differences in dimensionality and anatomical representations. In this work, we present a novel framewor

Lukas Silvester Barth, Parvaneh Joharinad, Jürgen Jost, Walter Wenzel

A metric relation by definition is symmetric. Since many data sets are non-symmetric, in this paper we develop a systematic theory of non-symmetric cost functions. Betweenness relations play an important role. We also introduce the notion of a Dress group in the non-symmetric setting and indicate a notion of curvature.

Griffin Tabor, Tucker Hermans

Many core problems in robotics can be framed as constrained optimization problems. Often on these problems, the robotic system has uncertainty, or it would be advantageous to identify multiple high quality feasible solutions. To enable this, we present two novel frameworks for applying principles of constrained optimization to the new variational inference a

Jayanta Dey, Nicholas Soures, Miranda Gonzales, Itamar Lerner

In this pilot study, we propose a neuro-inspired approach that compresses temporal sequences into context-tagged chunks, where each tag represents a recurring structural unit or``community'' in the sequence. These tags are generated during an offline sleep phase and serve as compact references to past experience, allowing the learner to incorporate informati

Sonia Koszut, Sam Nallaperuma-Herzberg, Pietro Lio

Stress significantly contributes to both mental and physical disorders, yet traditional self-reported questionnaires are inherently subjective. In this study, we introduce a novel framework that employs geometric machine learning to detect stress from raw EEG recordings. Our approach constructs graphs by integrating structural connectivity (derived from elec

Carlos A. Gomez-Uribe

We derive the Planck law from a classical variational principle over probability densities, without invoking quantum states, quantized oscillator energies, or ensemble averages. We construct a generalized free energy functional involving entropy and Fisher information, with weights determined by the dimensionless ratio of quantum to thermal energy. When extr

Yucheng Cai, Ke Li, Yi Huang, Junlan Feng

A retriever, which retrieves relevant knowledge pieces from a knowledge base given a context, is an important component in many natural language processing (NLP) tasks. Retrievers have been introduced in knowledge-grounded dialog systems to improve knowledge acquisition. In knowledge-grounded dialog systems, when conditioning on a given context, there may be

L. Golinskii, S. Kupin

We study the growth of the resolvent of a Hardy--Toeplitz operator $T_b$ with a Laurent polynomial symbol (\emph{i.e., } the matrix $T_b$ is banded), at the neighborhood of a point $w_0\in\partial(\sigma(T_b))$ on the boundary of its spectrum. We show that such growth is inverse linear in some non-tangential domains at the vertex $w_0$, provided that $w_0$ d

Yuhang Zhou, Yimin Xiao, Wei Ai, Ge Gao

Social media platforms have become central to modern communication, yet they also harbor offensive content that challenges platform safety and inclusivity. While prior research has primarily focused on textual indicators of offense, the role of emojis, ubiquitous visual elements in online discourse, remains underexplored. Emojis, despite being rarely offensi

Chenjun Xu, Bingbing Wen, Bin Han, Robert Wolfe

Psychology research has shown that humans are poor at estimating their performance on tasks, tending towards underconfidence on easy tasks and overconfidence on difficult tasks. We examine three LLMs, Llama-3-70B-instruct, Claude-3-Sonnet, and GPT-4o, on a range of QA tasks of varying difficulty, and show that models exhibit subtle differences from human pat

Chang Cai, Wenjun Jiang, Xiaojun Yuan, Ying-Jun Angela Zhang

Massive connectivity supports the sporadic access of a vast number of devices without requiring prior permission from the base station (BS). In such scenarios, the BS must perform joint activity detection and channel estimation (JADCE) prior to data reception. Message-passing algorithms have emerged as a prominent solution for JADCE under a Bayesian inferenc

Merlin Schüler, Laurenz Wiskott

This work presents a novel probabilistic interpretation of Slow Feature Analysis (SFA) through the lens of variational inference. Unlike prior formulations that recover linear SFA from Gaussian state-space models with linear emissions, this approach relaxes the key constraint of linearity. While it does not lead to full equivalence to non-linear SFA, it reca

Grace M. Sommers, Michael Foss-Feig, David Hayes, David A. Huse

We introduce a fault-tolerant protocol for code concatenation of a generalized Shor code using a butterfly network architecture with high noise thresholds and low ancilla overhead to allow implementation on current devices. We develop a probability passing decoder using tensor networks that applies Bayesian updates to the marginal error probabilities after e

Taihang Lei, Banglei Guan, Minzu Liang, Xiangyu Li

The characterization of mechanical properties for high-dynamic, high-velocity target motion is essential in industries. It provides crucial data for validating weapon systems and precision manufacturing processes etc. However, existing measurement methods face challenges such as limited dynamic range, discontinuous observations, and high costs. This paper pr

Yufa Zhou, Shaobo Wang, Xingyu Dong, Xiangqi Jin

Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether post-training techniques, specifically Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR), can

Fatemeh Lotfi, Hossein Rajoli, Fatemeh Afghah

Advanced wireless networks must support highly dynamic and heterogeneous service demands. Open Radio Access Network (O-RAN) architecture enables this flexibility by adopting modular, disaggregated components, such as the RAN Intelligent Controller (RIC), Centralized Unit (CU), and Distributed Unit (DU), that can support intelligent control via machine learni

Amirhossein Momtaheni, Mohammadsadegh Khazali

Atomic processing units require robust entanglement between individual qubits, typically achieved via excitation to highly interacting Rydberg states. However, short Rydberg lifetimes and ionization risks limit the quantum volume score of the atomic processing units. Inspired by Landau resonances in alkaline atoms, we introduce Rydberg-Landau (rLandau) state

Fatemeh Lotfi, Hossein Rajoli, Fatemeh Afghah

Modern wireless networks must adapt to dynamic conditions while efficiently managing diverse service demands. Traditional deep reinforcement learning (DRL) struggles in these environments, as scattered and evolving feedback makes optimal decision-making challenging. Large Language Models (LLMs) offer a solution by structuring unorganized network feedback int

Dor Tsur, Ziv Goldfeld, Kristjan Greenewald, Haim Permuter

Multimarginal optimal transport (MOT) is a powerful framework for modeling interactions between multiple distributions, yet its applicability is bottlenecked by a high computational overhead. Entropic regularization provides computational speedups via the multimarginal Sinkhorn algorithm, whose time complexity, for a dataset size $n$ and $k$ marginals, gener

Tobias Adrian, Hongqi Chen, Max-Sebastian Dovì, Ji Hyung Lee

We analyse growth vulnerabilities in the US using quantile partial correlation regression, a selection-based machine-learning method that achieves model selection consistency under time series. We find that downside risk is primarily driven by financial, labour-market, and housing variables, with their importance changing over time. Decomposing downside risk

Samantha Sandberg-Clark, Krystal Taylor

This article focuses on the occurrence of 3-point configurations in subsets of $\mathbb{R}^d$ of sufficient thickness. We prove that a compact set $A\subset \mathbb{R}^d$ contains a similar copy of any linear $3$-point configuration (such as a $3$-point arithmetic progression) provided $A$ satisfies a mild Yavicoli-thickness condition and an $r$-uniformity c

Liang Geng

With the rapid penetration of artificial intelligence across industries and scenarios, a key challenge in building the next-generation intelligent core lies in effectively integrating the language understanding capabilities of foundation models with domain-specific knowledge bases in complex real-world applications. This paper proposes a multimodal cognition

Xuan Xu, Fufang Wen, Beilin Chu, Zhibing Fu

In natural language processing (NLP), the focus has shifted from encoder-only tiny language models like BERT to decoder-only large language models(LLMs) such as GPT-3. However, LLMs' practical application in the financial sector has revealed three limitations: (1) LLMs often perform worse than fine-tuned BERT on discriminative tasks despite costing much high

Nicholas E. Corrado, Julian Katz-Samuels, Adithya Devraj, Hyokun Yun

When aligning large language models (LLMs), their performance on various tasks (such as being helpful, harmless, and honest) depends heavily on the composition of their training data. However, selecting a data mixture that achieves strong performance across all tasks is challenging. Existing approaches rely on large ablation studies, heuristics, or human int

Ke Niu, Zhuofan Chen, Haiyang Yu, Yuwen Chen

Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing. Orthographic projection reasoning underpins the entire CAD workflow, encompassing design, manufacturing, and simulation. However, prevailing deep-learning approaches employ standard 3D reconstruction pipelines as an alternative, which often introduce imprecise dimensions and limit

Xinyu Feng, Yukun Wang, Cong Li, Wu Xin

Multiparty private set intersection (MPSI) allows multiple participants to compute the intersection of their locally owned data sets without revealing them. MPSI protocols can be categorized based on the network topology of nodes, with the star, mesh, and ring topologies being the primary types, respectively. Given that star and mesh topologies dominate curr

Zhenan Sui

We prove the existence of a smooth complete $3$-convex hypersurface which satisfies prescribed curvature equation $\prod\limits_{i = 1}^n (H - \kappa_i) = \big( (n - 1) \sigma \big)^n$ for $n = 4$ and has prescribed asymptotic boundary $\Gamma$ at the infinity of hyperbolic space of dimension 5, where $\sigma \in (0, 1)$ is a constant and $\Gamma$ is assumed

Haosen Liu, Jiahao Liu, Shan Tan, Edmund Y. Lam

Noisy supervision refers to supervising image restoration learning with noisy targets. It can alleviate the data collection burden and enhance the practical applicability of deep learning techniques. However, existing methods suffer from two key drawbacks. Firstly, they are ineffective in handling spatially correlated noise commonly observed in practical app

Ziyan Luo, Tianwei Ni, Pierre-Luc Bacon, Doina Precup

A key approach to state abstraction is approximating behavioral metrics (notably, bisimulation metrics) in the observation space and embedding these learned distances in the representation space. While promising for robustness to task-irrelevant noise, as shown in prior work, accurately estimating these metrics remains challenging, requiring various design c

Yule Zhu, Ping Liu, Zhedong Zheng, Wei Liu

Diffusion models have recently enabled precise and photorealistic facial editing across a wide range of semantic attributes. Beyond single-step modifications, a growing class of applications now demands the ability to analyze and track sequences of progressive edits, such as stepwise changes to hair, makeup, or accessories. However, sequential editing introd

Fumika Suzuki, Nikolai A. Sinitsyn

We discuss a classical anisotropic oscillator and the Foucault pendulum as examples illustrating non-conservation of action variables in integrable classical mechanical systems with adiabatically slow evolution. We also emphasize the importance of the mass parameter of a harmonic oscillator, alongside its frequency, in explicitly time-dependent situations.

Adrian Azzarelli, Ge Gao, Ho Man Kwan, Fan Zhang

As research on neural volumetric video reconstruction and compression flourishes, there is a need for diverse and realistic datasets, which can be used to develop and validate reconstruction and compression models. However, existing volumetric video datasets lack diverse content in terms of both semantic and low-level features that are commonly present in re