arXiv papers from January 2026

Xinyu Yuan, Yan Qiao, Zonghui Wang, Meng Li

The rapid expansion of modern wide-area networks (WANs) has made traffic engineering (TE) increasingly challenging, as traditional solvers struggle to keep pace. Although existing offline ML-driven approaches accelerate TE optimization with deep neural networks (DNNs), they often lack sufficient expressiveness and generalization on unseen traffic patterns or

Fanqi Yan, Dung Le, Trang Pham, Huy Nguyen

Contaminated mixture of experts (MoE) is motivated by transfer learning methods where a pre-trained model, acting as a frozen expert, is integrated with an adapter model, functioning as a trainable expert, in order to learn a new task. Despite recent efforts to analyze the convergence behavior of parameter estimation in this model, there are still two unreso

Shahaz S. Hameed, Di Jin, Aihao Zhao, Jiayang Wu

On-chip integration of 2D materials provides a promising route towards next-generation integrated optical devices with performance beyond existing limits. Here, significantly enhanced spectral broadening induced by self-phase modulation (SPM) is experimentally demonstrated in silicon nitride (Si3N4) waveguides integrated with 2D monolayer molybdenum disulfid

I-Chun Arthur Liu, Krzysztof Choromanski, Sandy Huang, Connor Schenck

Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for robotic manipulation. However, such representations fail to capture the 3D spatial information about objects and scenes that is essential for precise manipulation. In this work, we introduce Contrastive Learning for 3

Ziqing Xiang

In 2003, van Dam and Haemers posed a fundamental question in spectral graph theory: does there exist a ``sensible'' matrix whose spectrum determines a random graph up to isomorphism? This paper introduces the class of {\em natural graph matrices}, which are matrices defined by applying a fixed sequence of elementary operations to the adjacency matrix. This c

Mohamed Sorour, Barbara Webb

Ants are highly capable of grasping objects in clutter, and we have recently observed that this involves substantial use of their forelegs. The forelegs, more specifically the tarsi, have high friction microstructures (setal pads), are covered in hairs, and have a flexible under-actuated tip. Here we abstract these features to test their functional advantage

Víctor Becerril

The existence of the Gorenstein projective precovers over $R$ an arbitrary ring, as well as the completeness of the Gorenstein projective cotorsion pair $(\mathcal{GP},\mathcal{GP}^{\perp})$, are open questions. In this paper, we provide some answers to these questions and use the tool developed to confirm the Gorenstein Symmetry Conjecture, under two differ

Muhammad Ahmed Mohsin, Muhammad Umer, Ahsan Bilal, Zihao He

Large language model reasoning is often treated as a monolithic capability, relying on binary preference supervision that fails to capture partial progress or fine-grained reasoning quality. We introduce Continuous Utility Direct Preference Optimization (CU-DPO), a framework that aligns models to a portfolio of prompt-based cognitive strategies by replacing

David Gao, David Jekel, Srivatsav Kunnawalkam Elayavalli, Gregory Patchell

We are able to explicitly compute the bimodule structure of von Neumann algebra inclusions in handle constructions, which arise as inductive limits of iterated amalgamated free products not elementarily equivalent to $L(\mathbb{F}_2)$. Our computation is achieved via identifying delicate normal form decompositions in amalgamated free products built in an ite

Zergham Ahmed, Kazuki Irie, Joshua B. Tenenbaum, Christopher J. Bates

Humans learn abstractions and use them to plan efficiently to quickly generalize across tasks -- an ability that remains challenging for state-of-the-art large language model (LLM) agents and deep reinforcement learning (RL) systems. Inspired by the cognitive science of how people form abstractions and intuitive theories of their world knowledge, Theory-Base

Thomas Werner, Erfan Riyazi, Samarth Hawaldar, Rishabh Sahu

Superconducting qubits are a leading candidate for utility-scale quantum computing due to their fast gate speeds and steadily decreasing error rates. The requirement for millikelvin operating temperatures, however, creates a significant scaling bottleneck. Modular architectures using optical fiber links could bridge separate cryogenic nodes, but superconduct

Yihao Xue, Allan Zhang, Jianhao Huang, Amit Sahai

Training LLMs to think and reason for longer has become a key ingredient in building state-of-the-art models that can solve complex problems previously out of reach. Recent efforts pursue this in different ways, such as RL fine-tuning to elicit long CoT or scaling latent reasoning through architectural recurrence. This makes reasoning length an important sca

Diego Jaure, Christopher Maulen

We study differential equations with piecewise constant argument (DEPCA) and establish the existence and uniqueness of remotely almost periodic (RAP) solutions for \[ x'(t)=A(t)x(t)+B(t)x([t])+f(t). \] Under an exponential dichotomy for the associated linear hybrid system \(x'(t)=A(t)x(t)+B(t)x([t])\) and suitable RAP/Lipschitz assumptions on the data, we de

Jincheng Wang, Lingfan Bao, Tong Yang, Diego Martinez Plasencia

The challenge of generating reliable local plans has long hindered practical applications in highly cluttered and dynamic environments. Key fundamental bottlenecks include acquiring large-scale expert demonstrations across diverse scenes and improving learning efficiency with limited data. This paper proposes SanD-Planner, a sample-efficient diffusion-based

Michael Kim, Wei Cai

Atomistic simulations provide valuable insights into the physical processes governing material behavior. However, their applicability is fundamentally constrained by the limited time scales accessible to brute-force simulations. This bottleneck often stems from complex energy landscapes where the systems stay trapped in metastable states for long periods of

Ayed Sayem, Shiekh Zia Uddin, Ting-Chen Hu, Alaric Tate

In this paper, we demonstrate the ultra-high-power handling capability and DC bias stability of optical microring and electro-optic (EO) coupling resonators on the thin-film lithium tantalate (TFLT) platform. We show that, with annealing, oxide-cladded TFLT resonators can handle several watts (4W) of circulating power with minimal frequency shift and no obse

Eric Gelphman, Deepanshu Verma, Nicole Tianjiao Yang, Stanley Osher

Optimal feedback control with implicit Hamiltonians poses a fundamental challenge for learning-based value function methods due to the absence of closed-form optimal control laws. Recent work~\cite{gelphman2025end} introduced an implicit deep learning approach using Jacobian-Free Backpropagation (JFB) to address this setting, but only established sample-wise

Stefano Bellucci, Stefania De Matteo

In quantum field theory, the algebraic existence of a field does not guarantee the existence of a corresponding localized asymptotic particle state. This distinction is well established in the presence of infrared effects, long-range correlations, and environmental interactions, and becomes particularly relevant in supersymmetric theories, where fermionic an

I. Apanasevich, M. Artemyev, R. Babakyan, P. Fedotova

We introduce Green-VLA, a staged Vision-Language-Action (VLA) framework for real-world deployment on the Green humanoid robot while maintaining generalization across diverse embodiments. Green-VLA follows a five stage curriculum: (L0) foundational VLMs, (L1) multimodal grounding, (R0) multi-embodiment pretraining, (R1) embodiment-specific adaptation, and (R2

Aurélien Renault, Alexis Bondu, Antoine Cornuéjols, Vincent Lemaire

Early Classification of Time Series (ECTS) addresses decision-making problems in which predictions must be made as early as possible while maintaining high accuracy. Most existing ECTS methods assume that the time-dependent decision costs governing the learning objective are known, fixed, and correctly specified. In practice, however, these costs are often u

Ali Kourani, Naveed A. Abbasi, Syeda Narjis Fatima, Katsuyuki Haneda

Precision in radiation therapy relies on immobilization systems that limit patient motion. Thermoplastic masks are commonly used for this purpose, but subtle voluntary and involuntary movements such as jaw shifts, deep breathing, or eye squinting may still compromise treatment accuracy. Existing motion tracking methods are limited: optical systems require a

Syed M Arslan, Muhammad T Rahim, Asad Ali, Hashir Kuniyil

One-sided device-independent quantum key distribution (1SDI-QKD) offers a practical middle ground between fully device-independent protocols and standard QKD, achieving security with detection efficiencies as low as 50.1\% on the untrusted side. However, prior analyses assumed idealized channels, neglecting realistic noise sources. We extend the 1SDI-QKD fra

Zhiyuan Wu, Xiangyu Zhang, Zhuo Chen, Jiankang Deng

Cross-embodiment dexterous grasping aims to generate stable and diverse grasps for robotic hands with heterogeneous kinematic structures. Existing methods are often tailored to specific hand designs and fail to generalize to unseen hand morphologies outside the training distribution. To address these limitations, we propose \textbf{UniMorphGrasp}, a diffusio

Víctor Yeste, Rodrigo Rivas-Arévalo

We present a lightweight multimodal baseline for emotion recognition in conversations using the SemEval-2024 Task 3 dataset built from the sitcom Friends. The goal of this report is not to propose a novel state-of-the-art method, but to document an accessible reference implementation that combines (i) a transformer-based text classifier and (ii) a self-super

Víctor Yeste, Paolo Rosso

Human value detection from single sentences is a sparse, imbalanced multi-label task. We study whether Schwartz higher-order (HO) categories help this setting on ValueEval'24 / ValuesML (74K English sentences) under a compute-frugal budget. Rather than proposing a new architecture, we compare direct supervised transformers, hard HO$\rightarrow$values pipelin

Erica Andreose, Ivan Heibi, Silvio Peroni, Leonardo Zilli

Recent initiatives advocating responsible, transparent research assessment have intensified the call to use open research information rather than proprietary databases. This study evaluates the coverage and citation representation of publications recorded in the Current Research Information Systems (CRIS), all instances of the IRIS software platform, of six

Gregg Hartvigsen

I present the results from a spatial model of the prisoner's dilemma, played on a toroidal lattice. Each individual has a default strategy of either cooperating ($C$) or defecting ($D$). Two strategies were tested, including ``tit-for-tat'' (TFT), in which individuals play their opponent's last play, or simply playing their default play. Each individual also

Cuong Manh Nguyen, Truong-Son Hy

Deep learning has revolutionized medical image analysis, playing a vital role in modern clinical applications. However, the deployment of large-scale models in real-world clinical settings remains challenging due to high computational costs, latency constraints, and patient data privacy concerns associated with cloud-based processing. To address these bottle

M. Reza J. Harandi, Mehrzad Namvar

Total energy shaping through interconnection and damping assignment passivity-based control (IDA-PBC) provides a powerful and systematic framework for stabilizing underactuated mechanical systems. Despite its theoretical appeal, incorporating actuator limitations into total energy shaping remains a largely open problem, with only limited results reported in

Pingping Wang, Yihong Yuan, Lingcheng Li, Yongmei Lu

PyGALAX is a Python package for geospatial analysis that integrates automated machine learning (AutoML) and explainable artificial intelligence (XAI) techniques to analyze spatial heterogeneity in both regression and classification tasks. It automatically selects and optimizes machine learning models for different geographic locations and contexts while main

M. Reza J. Harandi, Mehrzad Namvar

Although the stabilization of underactuated systems remains a challenging problem, the total energy shaping approach provides a general framework for addressing this objective. However, the practical implementation of this method is hindered by the need to analytically solve a set of partial differential equations (PDEs), which constitutes a major obstacle.

Kunal Mahatha, Ali Bahri, Pierre Marza, Sahar Dastani

State space models (SSMs) have recently emerged as an alternative to transformers due to their unique ability of modeling global relationships in text with linear complexity. However, their success in vision tasks has been limited due to their causal formulation, which is suitable for sequential text but detrimental in the spatial domain where causality brea

Thomas Muehlenstädt, Marius Bause

Coverage analysis is essential for validating the safety of autonomous driving systems, yet existing approaches typically assess coverage factors individually or in limited combinations, struggling to capture the complex interactions inherent in traffic scenes. This paper proposes a graph-based framework for coverage analysis that represents traffic scenes a

S. Mohammad Ahmadi, Nahid Ahmadi

The standard $\delta N$ formalism is a cornerstone technique for calculating nonlinear curvature perturbations on super-Hubble scales. However, its validity relies heavily on the separate universe assumption, in which spatial gradients are neglected. This approximation is known to break down in scenarios that are critical for primordial black hole formation,

Adel Magra, Aad van der Vaart

We consider the efficient inference of finite dimensional parameters arising in the context of inverse problems. Our setup is the observation of a transformation of an unknown infinite dimensional signal $f$ corrupted by statistical noise, with the transformation $K_\theta$ being linear but unknown up to a scalar $\theta$. We adopt a Bayesian approach and pu

Mritunjay Pandey

E-commerce recommendation and search commonly rely on sparse keyword matching (e.g., BM25), which breaks down under vocabulary mismatch when user intent has limited lexical overlap with product metadata. We cast content-based recommendation as recommendation-as-retrieval: given a natural-language intent signal (a query or review), retrieve the top-K most rel

Abdellatif Mouhssine

Vector extrapolation methods are widely used in large-scale simulation studies, and numerous extrapolation-based acceleration techniques have been developed to enhance the convergence of linear and nonlinear fixed-point iterative methods. While classical extrapolation strategies often reduce the number of iterations or the computational cost, they do not nec

Faizuddin Ahmed, Ahmad Al-Badawi, İzzet Sakallı

We construct a charged Bardeen black hole (BH) surrounded by perfect fluid dark matter (PFDM) and coupled to a cloud of strings (CS). The metric function combines the magnetic monopole charge from nonlinear electrodynamics, the PFDM logarithmic correction, and the CS parameter that renders the spacetime asymptotically non-flat. We analyze the horizon structu

Esmée Theewis, Mark Veraar

Assuming $A$ has maximal $L^p$-regularity, this paper investigates perturbations of $A$ by time-dependent operators $B$ that are unbounded and satisfy a critical $L^q$-integrability condition in time. We establish two main results. The first proves maximal $L^p$-regularity for the critical endpoint case, generalizing previous work by Pr\"uss and Schnaubelt (

Shailesh Dhasmana

This thesis investigates the interactions of partially massless (PM) fields in 4-dimensional (anti)de Sitter spaces, along with conformal higher spin fields and their coupling to matter in arbitrary dimensions. The first part of the thesis deals with PM fields and PM algebras. A reformulation of PM fields is proposed and studied using a novel chiral formulat

Behzad Ghanbarian, Andres Patrignani

In soil physics, saturated hydraulic conductivity, K_sat, is among the most important hydraulic properties with broad applications to modeling flow and transport under saturated conditions. Its accurate estimation, however, is challenging and requires precise characterization of pore space. In this study, we applied concepts of critical path analysis (CPA) t

Jebacyril Arockiaraj, Sasindu Wijeratne, Sugeet Sunder, Md Abdullah-Al Kaiser

Photonic in-memory computing is a high-speed, low-energy alternative to traditional transistor-based digital computing that utilizes high photonic operating frequencies and bandwidths. In this work, we develop a comprehensive system-level performance model for photonic in-memory computing, capturing the effects of key latency sources such as external memory

Ivy Xiaoya, Anton M. Graf, Eric J. Heller, Joonas Keski-Rahkonen

Quantum dynamics retains a permanent and universal memory of its initial conditions, even in systems whose spectra display fully chaotic, random-matrix behavior. This effect, known as the quantum birthmark, appears as an enhancement of the long-time return probability of any non-stationary state compared to the overlap with a typical ergodic state. In this w

Behzad Ghanbarian, Victor Oladoja, Kehinde Bosikun, Tayeb Jamali

To address spatial boundary effects in climate networks, two surrogate-based correction methods, (1) subtraction and (2) division, have been widely applied in the literature. In the subtraction method, an original network measure is adjusted by subtracting the expected value obtained from a surrogate ensemble, whereas in the division method, it is normalized

Adel Magra, Frank van der Meulen, Aad van der Vaart

We consider the heat equation with absorption in a bounded domain of $\mathbb{R}^d$, where both the scalar diffusivity and the absorption function are unknown. We investigate a Bayesian approach for recovering the diffusivity from a noisy observation of the solution to the PDE over the domain. Given a Gaussian process prior on the absorption function, we der

Yingjie Niu, Lanxin Lu, Changhong Jin, Ruihai Dong

The advent of the web has led to a paradigm shift in the financial relations, with the real-time dissemination of news, social discourse, and financial filings contributing significantly to the reshaping of financial forecasting. The existing methods rely on establishing relations a priori, i.e. predefining graphs to capture inter-stock relationships. Howeve

Ruth Cohen, Lu Feng, Ayala Bloch, Sarit Kraus

While natural-language explanations from large language models (LLMs) are widely adopted to improve transparency and trust, their impact on objective human-AI team performance remains poorly understood. We identify a Persuasion Paradox: fluent explanations systematically increase user confidence and reliance on AI without reliably improving, and in some case

Aprameya Bharadwaj, Kyle Tu

Modern enterprise systems exhibit complex interdependencies that make observability and incident response increasingly challenging. Manual alert triage, which typically involves log inspection, API verification, and cross-referencing operational knowledge bases, remains a major bottleneck in reducing mean recovery time (MTTR). This paper presents an agentic

Amitesh Vatsa, Zhixian Xie, Wanxin Jin

Diffusion policies are a powerful paradigm for robotic control, but fine-tuning them with human preferences is fundamentally challenged by the multi-step structure of the denoising process. To overcome this, we introduce a Unified Markov Decision Process (MDP) formulation that coherently integrates the diffusion denoising chain with environmental dynamics, e

Ahmad Sarlak, Abolfazl Razi

Informative data selection is a key requirement for large language models (LLMs) to minimize the amount of data required for fine-tuning, network distillation, and token pruning, enabling fast and efficient deployment, especially under computational and communication constraints. Traditional subset selection methods, including those based on Determinantal Po

Louis Serrano, Jiequn Han, Edouard Oyallon, Shirley Ho

Neural operators have shown promise in learning solution maps of partial differential equations (PDEs), but they often struggle to generalize when test inputs lie outside the training distribution, such as novel initial conditions, unseen PDE coefficients or unseen physics. Prior works address this limitation with large-scale multiple physics pretraining fol

Alicja Polowczyk, Agnieszka Polowczyk, Piotr Borycki, Joanna Waczyńska

Despite impressive results from recent text-to-image models like FLUX, visual and anatomical artifacts remain a significant hurdle for practical and professional use. Existing methods for artifact reduction, typically work in a post-hoc manner, consequently failing to intervene effectively during the core image formation process. Notably, current techniques

Anindya Biswas

We study the relation between Pick bodies on Carath\'eodory hyperbolic domains and contractions on finite dimensional Hilbert spaces. We give a condition sufficient to realize Pick bodies on Carath\'eodory hyperbolic domains as a Pick body on the open unit disc.

Shounak Paul, Raghav Dogra, Pawan Goyal, Saptarshi Ghosh

Legal Statute Identification (LSI) for a given situation is one of the most fundamental tasks in Legal NLP. This task has traditionally been modeled using facts from court judgments as input queries, due to their abundance. However, in practical settings, the input queries are likely to be informal and asked by laypersons, or non-professionals. While a few l

Ailin Liu, Yesmine Karoui, Fiona Draxler, Frauke Kreuter

Difficulty spillover and suboptimal help-seeking challenge the sequential, knowledge-intensive nature of digital tasks. In online surveys, tough questions can drain mental energy and hurt performance on later questions, while users often fail to recognize when they need assistance or may satisfy, lacking motivation to seek help. We developed a proactive, ada

Hao Mark Chen, Zhiwen Mo, Royson Lee, Qianzhou Wang

Among parallel decoding paradigms, diffusion large language models (dLLMs) have emerged as a promising candidate that balances generation quality and throughput. However, their integration with Mixture-of-Experts (MoE) architectures is constrained by an expert explosion: as the number of tokens generated in parallel increases, the number of distinct experts

Mohsen Mostafa

Unsupervised 3D scene reconstruction from unstructured image collections remains a fundamental challenge in computer vision, particularly when images originate from multiple unrelated scenes and contain significant visual ambiguity. The Image Matching Challenge 2025 (IMC2025) highlights these difficulties by requiring both scene discovery and camera pose est

Zhipeng Zhao, Taimeng Fu, Shaoshu Su, Qiwei Du

Low speed does not always guarantee safety in off-road driving. For instance, crossing a ditch may be risky at a low speed due to the risk of getting stuck, yet safe at a higher speed with a controlled, accelerated jump. Achieving such behavior requires path planning that explicitly models complex motion dynamics, whereas existing methods often neglect this

Samuel Moor-Smith, Dino Carpentras

While opinion dynamics models have been extensively studied as stylized models, there has been growing attention to the possibility of combining these models with empirical data. This attention seems to be driven by the many social issues that strongly depend on people's opinions (such as climate change and vaccination) and the need for empirically valid mod

Md. Ismiel Hossen Abir

Quantum computing is a significant risk to classical cryptographic, especially RSA, which depends on the difficulty of factoring large numbers. Classical factorization methods, such as Trial Division and Pollard's Rho, are inefficient for large keys, while Shor's quantum algorithm can break RSA efficiently in polynomial time. This research studies RSA's vuln

Shiyu Liu, Wei Liu, Lihu Xu

We consider the following second-order stochastic differential equation on $\mathbb{R}^{2d}$: \begin{equation*} dX_t^m=Y_t^mdt, \quad mdY_t^m=b(X_t^m)dt+\sigma(X_t^m)dB_t-Y^m_tdt, \end{equation*} where $X^m_t$ and $Y^m_t$ represent the position and velocity of a particle at time $t$, $m>0$ denotes its mass, $b:\mathbb{R}^d \rightarrow \mathbb{R}^d$ is the dr

Zhao Song, Jianfei Xue, Jiahao Zhang, Lichen Zhang

Given the query, key and value matrices $Q, K, V\in \mathbb{R}^{n\times d}$, the attention module is defined as $\mathrm{Att}(Q, K, V)=D^{-1}AV$ where $A=\exp(QK^\top/\sqrt{d})$ with $\exp(\cdot)$ applied entrywise, $D=\mathrm{diag}(A{\bf 1}_n)$. The attention module is the backbone of modern transformers and large language models, but explicitly forming the

I. A. Aleksandrov, V. A. Bokhan, A. I. Baksheev, A. Kudlis

The evolution of the vacuum state in a time-dependent external electric field of arbitrary polarization is investigated within a nonperturbative framework of quantum kinetic equations (QKEs). In our previous work [Phys. Rev. Res. 6, 043009 (2024)], a revised version of the QKEs was derived by using an adiabatic basis constructed from one-particle Hamiltonian

Shihao Wang, Qipeng Qian, Jingquan Wang

We study solution learning for heat-based equations in self-similar variables (SSV). We develop an SSV training framework compatible with standard neural-operator training. We instantiate this framework on the two-dimensional incompressible Navier-Stokes equations and the one-dimensional viscous Burgers equation, and perform controlled comparisons between mo

Hossein A. Rahmani, Mengting Wan, Pei Zhou, Longqi Yang

Large language models (LLMs) have shown promising self-correction abilities, where iterative refinement improves the quality of generated responses. However, most existing approaches operate at the level of output critique, patching surface errors while often failing to correct deeper reasoning flaws. We propose SELF-THOUGHT, a framework that introduces an i

Shiyuan Li, Hossein Salahshoor

Neural operators aim to learn mappings between infinite-dimensional function spaces, but their performance often degrades on complex or irregular geometries due to the lack of geometry-aware representations. We propose the Finite Element Eigenfunction Network (FEENet), a hybrid spectral learning framework grounded in the eigenfunction theory of differential

Srinivas Rao Marri

The proliferation of AI-assisted "vibe coding" enables rapid software development but introduces significant security risks, as Large Language Models (LLMs) prioritize functional correctness over security. We present Constitutional Spec-Driven Development, a methodology that embeds non-negotiable security principles into the specification layer, ensuring AI-

Yuhao Huang, Taos Transue, Shih-Hsin Wang, William Feldman

Conditional flow matching (CFM) stands out as an efficient, simulation-free approach for training flow-based generative models, achieving remarkable performance for data generation. However, CFM is insufficient to ensure accuracy in learning probability paths. In this paper, we introduce a new partial differential equation characterization for the error betw

Nikhil Uday Shinde, Dylan Hirsch, Michael C. Yip, Sylvia Herbert

Autonomous robots operating in unstructured, safety-critical environments, from planetary exploration to warehouses and homes, must learn to safely navigate and interact with their surroundings despite limited prior knowledge. Current methods for safe control, such as Hamilton-Jacobi Reachability and Control Barrier Functions, assume known system dynamics. M

David Lucchesi, Massimo Visco, Roberto Peron, José C. Rodriguez

Strong theoretical arguments suggest that a breakdown of Lorentz Invariance could arise under some very particular conditions. From an experimental point of view, it is important to test the Local Lorentz Invariance with ever greater precision and in all contexts, regardless of the theoretical motivation for the possible violation. In this paper we discuss s

Akiharu Esashi, Pawissanutt Lertpongrujikorn, Justin Makino, Yuibi Fujimoto

The Controller Area Network (CAN) bus provides a rich source of vehicular signals increasingly leveraged for applications in automotive and auto insurance domains, including collision detection, predictive maintenance, and driver risk modeling. Despite this potential, existing pipelines largely train isolated task-specific models on raw CAN data, with only l

Brandon Leblanc, Charalambos Poullis

While multi-view 3D reconstruction has shifted toward large-scale foundation models capable of inferring globally consistent geometry, their reliance on massive computational clusters for training has created a significant barrier to entry for most academic laboratories. To bridge this compute divide, we introduce Distill3R, a framework designed to distill t

Krzysztof Kutak

I present derivation the BK equation for the dipole gluon density in momentum space, starting from its standard formulation in coordinate space. I review the equation for both proton and nuclear targets, and I also discuss the resummed BK evolution.The purpose of this paper is to consolidate derivations and formulas scattered across the literature, to show i

André F. R. Guarda, Nuno M. M. Rodrigues, Fernando Pereira

While point cloud-based applications are gaining traction due to their ability to provide rich and immersive experiences, they critically need efficient coding solutions due to the large volume of data involved, often many millions of points per object. The JPEG Pleno Learning-based Point Cloud Coding standard, as the first learning-based coding standard for

Dmitry A. Cheshkov, Dmitry O. Sinitsyn

This work provides a comprehensive theoretical framework for understanding the symmetry properties of High-Resolution NMR spectra. We analyze the conditions under which a spectrum exhibits mirror symmetry (palindromicity). We demonstrate that such symmetry can arise from two distinct mechanisms: (1) the direct geometric bisymmetry of the Hamiltonian matrix i

Shih-Hsin Wang, Yuhao Huang, Taos Transue, Justin Baker

Graph neural networks (GNNs) have emerged as powerful tools for learning protein structures by capturing spatial relationships at the residue level. However, existing GNN-based methods often face challenges in learning multiscale representations and modeling long-range dependencies efficiently. In this work, we propose an efficient multiscale graph-based lea

Kushal Chakrabarti, Nirmal Balachundar

Modern transformer attention is internally multi-agent -- heads compete and coordinate -- yet we train it as if it were a monolithic optimizer. We formalize this gap: cross-entropy training induces an implicit potential game among heads, and gradient descent converges to Nash equilibria with potentially unbounded inefficiency due to unpriced externalities (r

Javier Jiménez-López, Stephen Maple, Paul R. Newman, Katarzyna Wichmann

We explore the potential for extracting proton structure functions, proton parton density functions (PDFs), and the strong coupling $\alpha_s(M_z^2)$, using early science data from the future Electron-Ion Collider (EIC), both standalone, and in combination with HERA data. Different scenarios are considered in which samples with modest luminosity are collecte

Anurag Satpathy, Arindam Khanda, Chittaranjan Swain, Sajal K. Das

Cyber-physical systems (CPS) increasingly manage shared physical resources in the presence of human decision-making, where system-assigned actions must be executed by users or agents in the physical world. A fundamental challenge in such settings is user non-compliance: individuals may deviate from assigned resources due to personal preferences or local info

Manveer Singh Tamber, Hosna Oyarhoseini, Jimmy Lin

Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In this work, we propose unifying the study of adversarial robustness in text scoring models spanning dense retrievers, rerankers, and reward models. This motivates adapting both attacks and adversarial training met

Luca Apadula, Alessandro Bisio, Giulio Chiribella, Paolo Perinotti

Bidirectional devices are devices for which the roles of the input and output ports can be exchanged. Mathematically, these devices are described by bistochastic quantum channels, namely completely positive linear maps that are both trace-preserving and identity-preserving. Recently, it has been shown that bidirectional quantum devices can, in principle, be

Gabriele Fabbro, Jan Brandejs, Trond Saue

The nuclear electric quadrupole moment (NQM) of $^{87}$Sr has recently been revisited using high-precision relativistic atomic calculations [B. Lu et al., Phys. Rev. A 100, 012504 (2019)], indicating that the currently accepted value should be revised and that their result may serve as a new reference. In the present work, we determine the NQM of $^{87}$Sr f

Fangzhou Lin, Qianwen Ge, Lingyu Xu, Peiran Li

AI systems increasingly produce fluent, correct, end-to-end outcomes. Over time, this erodes users' ability to explain, verify, or intervene. We define this divergence as the Capability-Comprehension Gap: a decoupling where assisted performance improves while users' internal models deteriorate. This paper argues that prevailing approaches to transparency, us

Ayrton Almada, Laurent Pagnier, Igal Goldshtein, Saif R. Kazi

Power system operators routinely perform N-1 contingency analysis, yet conventional tools provide limited guidance on which lines or transformers deserve heightened attention during fast post-fault transients. In particular, static screening does not reveal whether (1) the same faulted line repeatedly triggers severe downstream overloads, or (2) a specific t

Gerardo Barrera, Jonas M. Tölle

We give an overview on existing quantitative results on long-time behavior of the stochastic $p$-Laplace equation with additive Wiener noise, $p>1$. We summarize the existing results in a table. We give explicit quantitative upper and lower estimates for the $\varepsilon$-mixing times of the stochastic $p$-Laplace equations for $p>1$. We summarize the mixing

Pattarawat Chormai, Klaus-Robert Müller, Grégoire Montavon

Subtask distillation is an emerging paradigm in which compact, specialized models are extracted from large, general-purpose 'foundation models' for deployment in environments with limited resources or in standalone computer systems. Although distillation uses a teacher model, it still relies on a dataset that is often limited in size and may lack representat

Ruochen Liu, Zhiyuan Wen, Hao Yan, Jun Yin

Understanding how students with different proficiency levels respond to educational materials is a critical issue within the field of AI for Education. However, acquiring sufficient real student response data for a robust evaluation is often hindered by cost, ethics, and security constraints. Consequently, LLM-based student proficiency simulation, especially

Yuhao Huang, Shih-Hsin Wang, Andrea L. Bertozzi, Bao Wang

Mean flow (MeanFlow) enables efficient, high-fidelity image generation, yet its single-function evaluation (1-NFE) generation often cannot yield compelling results. We address this issue by introducing RMFlow, an efficient multimodal generative model that integrates a coarse 1-NFE MeanFlow transport with a subsequent tailored noise-injection refinement step.

Ziwei Gong, Yanda Chen, Julia Hirschberg, Chen Zhao

Large language models (LLMs) encode knowledge with varying degrees of confidence. When responding to queries, models face an inherent trade-off: they can generate responses that are less informative but highly factual, or more informative but potentially less accurate. Different applications demand different balances between informativeness and factuality. W

Anaëlle Pfister

We study the relative homology group of an affine hyperplane arrangement and its Poincar\'e dual, the cohomology at finite distance of the complement. We give an Orlik--Solomon-type description of the latter, and identify it with the vector space of logarithmic forms having vanishing residues at infinity. To this end, we introduce a partial version of wonder

Che-Yi Liao, Zheng Dong, Gian-Gabriel Garcia, Kamran Paynabar

Multivariate time series imputation is often compromised by mismatch between the observed and true data distributions, a bias induced by the combined effects of time-series non-stationarity and systematic missingness. Standard methods that encourage point-wise reconstruction or direct distributional alignment may overfit these biased observations. We propose

Claude Carlet, Marko Ðurasevic, Ermes Franch, Domagoj Jakobovic

Negabent Boolean functions are defined by having a flat magnitude spectrum under the nega-Hadamard transform. They exist in both even and odd dimensions, and the subclass of functions that are simultaneously bent and negabent (bent-negabent) has attracted interest due to the combined optimal periodic and negaperiodic spectral properties. In this work, we inv

Christopher M. Herald, Paul Kirk

We provide a proof that the $SU(2)$ character variety of a genus two surface, $\chi(F_2)$, is a closed compact manifold, and a proof of the Narasimhan-Ramanan theorem that $\chi(F_2)$ is homeomorphic to ${\mathbb C} P^3$. This is done entirely in the language of $SU(2)$ representations, differential topology and elementary algebraic topology. It avoids the N

Biruk Tadesse, Vikram Nitin, Mazin Salah, Baishakhi Ray

C/C++ is a prevalent programming language. Yet, it suffers from significant memory and thread-safety issues. Recent studies have explored automated translation of C/C++ to safer languages, such as Rust. However, these studies focused mostly on the correctness and safety of the translated code, which are indeed critical, but they left other important quality

Mingwei Li, Hehe Fan, Yi Yang

Monocular normal estimation for transparent objects is critical for laboratory automation, yet it remains challenging due to complex light refraction and reflection. These optical properties often lead to catastrophic failures in conventional depth and normal sensors, hindering the deployment of embodied AI in scientific environments. We propose TransNormal,

Prabhu Vellaisamy, Harideep Nair, Di Wu, Shawn Blanton

General matrix multiplication (GEMM) is a fundamental operation in deep learning (DL). With DL moving increasingly toward low precision, recent works have proposed novel unary GEMM designs as an alternative to conventional binary GEMM hardware. A rigorous evaluation of recent unary and binary GEMM designs is needed to assess the potential of unary hardware f

Claude Carlet, Marko Ðurasevic, Domagoj Jakobovic, Luca Mariot

Idempotent Boolean functions form a highly structured subclass of Boolean functions that is closely related to rotation symmetry under a normal-basis representation and to invariance under a fixed linear map in a polynomial basis. These functions are attractive as candidates for cryptographic design, yet their additional algebraic constraints make the search

Tanique Schaffe-Odeleye, Kōsaku Takanashi, Vishesh Karwa, Edoardo M. Airoldi

We generalize the potential outcome framework to time series with an intervention by defining causal effects on stochastic processes. Interventions in dynamic systems alter not only outcome levels but also evolutionary dynamics -- changing persistence and transition laws. Our framework treats potential outcomes as entire trajectories, enabling causal estiman

Ahmed Aloui, Junyi Liao, Ali Hasan, Jose Blanchet

Sampling from heavy-tailed and multimodal distributions is challenging when neither the target density nor the proposal density can be evaluated, as in $\alpha$-stable L\'evy-driven fractional Langevin algorithms. While the target distribution can be estimated from data via score-based or energy-based models, the $\alpha$-stable proposal density and its scor

Wei Chen, Jiacheng Li, Shigui Li, Zhiqi Lin

Score-based methods are powerful across machine learning, but they face a paradox: theoretically path-independent, yet practically path-dependent. We resolve this by proving that practical training objectives differ from the ideal, ground-truth objective by a crucial, overlooked term: the path variance of the score function. We propose the MVP (**M**imum **V