April 2026 arXiv papers — page 155

Zachary T. Rewolinski, Austin V. Zane, Hao Huang, Chandan Singh

Agentic data science (ADS) pipelines have grown rapidly in both capability and adoption, with systems such as OpenAI Codex now able to directly analyze datasets and produce answers to statistical questions. However, these systems can reach falsely optimistic conclusions that are difficult for users to detect. To address this, we propose a pair of lightweight

Haesung Oh, Jaeheung Park

End-to-End (E2E) autonomous driving models are usually trained and evaluated with a fixed ego-vehicle, even though their driving policy is implicitly tied to vehicle dynamics. When such a model is deployed on a vehicle with different size, mass, or drivetrain characteristics, its performance can degrade substantially; we refer to this problem as the vehicle-

Avinanda Chaudhuri

We investigate resonant leptogenesis in a two-triplet Type-II seesaw framework and demonstrate a coherent and predictive connection between neutrino mass generation, baryogenesis, and charge lepton flavor violation (LFV). In the presence of quasi-degenerate scalar triplets, self-energy effects induce a resonant enhancement of the CP asymmetry, enabling succe

Zhuolun Dong, Junyu Cao

Large language models (LLMs) have been widely adopted due to their great performance across a wide range of applications. ChatGPT and Gemini now serve hundreds of millions of active users and handle billions of user requests per day, which puts optimizing LLM inference into the spotlight. A key challenge in LLM inference is that decode lengths are unknown. T

Lingyi Kong, Chen Huang, Zhemin Zhang, Yidong Zhou

We present a directional-transport (DT)-based remote CZ gate and compiler for zoned neutral-atom arrays that overcomes movement-bound entanglement limitations. Current AOD-based shuttling faces row/column non-crossing constraints, device-speed limits, and hardware-restricted range - bottlenecks for long-distance connectivity. Our approach reserves AODs for c

Biswarup Mukherjee

This paper proposes a two-stage optimization framework to evaluate whether cost-optimal electric vehicle (EV) charging infrastructure translates into effective operation under distribution grid constraints. The proposed approach explicitly links infrastructure planning with grid-constrained charging operation through a consistent optimal power flow (OPF) for

Zhengzhe Yang

Can large language models (LLMs) generate continuous numerical features that improve reinforcement learning (RL) trading agents? We build a modular pipeline where a frozen LLM serves as a stateless feature extractor, transforming unstructured daily news and filings into a fixed-dimensional vector consumed by a downstream PPO agent. We introduce an automated

Michael J. Plank, Matt Ryan, Lloyd Chapman, Roslyn I. Hickson

Infectious disease transmission in human populations has a complex two-way interaction with changes in host behaviour. It is increasingly recognised that incorporating adaptive behavioural change into epidemic models is important for improving understanding of infectious disease dynamics and developing policy-relevant modelling tools. An important aspect of

Joanna Kaleta, Piotr Wójcik, Kacper Marzol, Tomasz Trzciński

In 3D reconstruction, the problem of inverse rendering, namely recovering the illumination of the scene and the material properties, is fundamental. Existing Gaussian Splatting-based methods primarily target static scenes and often assume simplified or moderate lighting to avoid entangling shadows with surface appearance. This limits their ability to accurat

Zihan Li, Ziming Wang, Xin Wang

Vehicular formation control is an important component of intelligent transportation systems (ITSs). In practical implementations, the controller design needs to satisfy multiple state constraints, including inter-vehicle spacing and vehicle speed. When system states approach the constraint boundaries, control singularity and excessive control effort may aris

Yuan Shui, Yandong Guan, Zhanwei Zhang, Juncheng Hu

Parametric Computer-Aided Design (CAD) of articulated assemblies is essential for product development, yet generating these multi-part, movable models from high-level descriptions remains unexplored. To address this, we propose ArtiCAD, the first training-free multi-agent system capable of generating editable, articulated CAD assemblies directly from text or

Yiran Du, Huimin He

The growing use of generative artificial intelligence (AI) in academic writing has raised increasing concerns regarding transparency and academic integrity in higher education. This study examines the psychological factors influencing English for Academic Purposes (EAP) students' intention to disclose their use of AI tools. Drawing on the cognition-affect-co

Muxin Liu, Delip Rao, Grace Kim, Chris Callison-Burch

Scientific claim verification, the task of determining whether claims are entailed by scientific evidence, is fundamental to establishing discoveries in evidence while preventing misinformation. This process involves evaluating each asserted constraint against validated evidence. Under the Closed-World Assumption (CWA), a claim is accepted if and only if all

Shixing Zhao, Zheng Si, Pengpeng Ouyang, Zhengqing Hu

Emergency situations in scheduling systems often trigger local functional failures that undermine system stability and even cause system collapse. Existing methods primarily rely on robust scheduling or reactive scheduling, handling emergencies through predefined rules or rescheduling strategies. However, the diversity and unpredictability of real-world emer

Peng Yuan, Yuyang Yin, Yuxuan Cai, Zheng Wei

Existing browser agent benchmarks face a fundamental trilemma: real-website benchmarks lack reproducibility due to content drift, controlled environments sacrifice realism by omitting real-web noise, and both require costly manual curation that limits scalability. We present WebForge, the first fully automated framework that resolves this trilemma through a

Sameera Horawalavithana, Lauren Phillips, Ian Stewart, Sai Munikoti

Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge with improved reasoning, instruction-following, and generalization, there is a pressing need to efficiently update existing VLMs to incorporate these advancements. However, the in

Mohith H., Sudarshan Vijay

Interatomic potentials which accurately describe long-range electrostatics require atom-centred charges. One such method to determine these atom-centred charges from density functional theory (DFT) calculations is the density-derived atomic point (DDAP) charge method. DDAP fits atom-centred Gaussians to the ground-state DFT charge density and preserves the m

Jinhui Hou, Zhiyu Zhu, Junhui Hou

Diffusion bridge models have shown great promise in image restoration by explicitly connecting clean and degraded image distributions. However, they often rely on complex and high-cost trajectories, which limit both sampling efficiency and final restoration quality. To address this, we propose an Energy-oriented diffusion Bridge (E-Bridge) framework to appro

Xuan Yu, Yuxuan Xie, Changjian Jiang, Shichao Zhai

Open-vocabulary panoptic reconstruction is essential for advanced robotics perception and simulation. However, existing methods based on 3D Gaussian Splatting (3DGS) often struggle to simultaneously achieve geometric accuracy, coherent panoptic understanding, and real-time inference frequency in large-scale scenes. In this paper, we propose a comprehensive f

Samuel Sameer Tanguturi

ATANT v1.0 (arXiv:2604.06710) defined continuity as a system property with 7 required properties and introduced a 10-checkpoint, LLM-free evaluation methodology validated on a 250-story corpus. Since publication, a recurring reviewer and practitioner question has concerned not the framework itself but its relationship to a wider set of memory evaluations: LO

Zhao Song

Diffusion models have become the de facto standard for modern visual generation, including well-established frameworks such as latent diffusion and flow matching. Recently, modeling high-order dynamics has emerged as a promising frontier in generative modeling. Rather than only learning the first-order velocity field that transports random noise to a target

Shuning Dai

Traditional Active Noise Control (ANC) systems are mostly based on FxLMS algorithms, but such algorithms rely on linear assumptions and are often limited in handling broadband non-stationary noise or nonlinear acoustic paths. Not only that, the traditional method is used to eliminating all signals together, and noise reduction often accidentally damages the

Yiran Du, Huimin He

This study investigates students' AI use concealment intention in higher education by integrating the cognition-affect-conation (CAC) framework with a dual-method approach combining structural equation modelling (SEM) and fuzzy-set qualitative comparative analysis (fsQCA). Drawing on data from 1346 university students, the findings reveal two opposing mechan

Marc Estafanous

One of the limitations of transformer networks is the sequence length due to the quadratic nature of the attention matrix. Classical self attention uses the entire sequence length, however, the actual attention being used is sparse. Humans use a form of sparse attention when analyzing an image or scene called saccades. Focusing on key features greatly reduce

Ye Zhou

The finite-cutoff disk amplitude of Jackiw-Teitelboim (JT) gravity is known from closed-channel spectral methods and finite-cutoff trumpet/cap gluing, while its complete open-channel operator formulation has remained incomplete. In this paper, we provide an operator-level open-channel closure of this known result. More precisely, we separate the data importe

Yuli Slavutsky, Sebastian Salazar, David M. Blei

Generalized linear mixed-effects models (GLMMs) are widely used to analyze grouped and hierarchical data. In a GLMM, each response is assumed to follow an exponential-family distribution where the natural parameter is given by a linear function of observed covariates and a latent group-specific random effect. Since exact marginalization over the random effec

Kamiokande Collaboration, K. Abe, S. Abe, Y. Asaoka

We searched for proton decay via $p \to e^{+}\pi^{0}\pi^{0}$ and $p \to \mu^{+}\pi^{0}\pi^{0}$ in 0.401 megaton-years of data collected in all pure water detector phases of Super-Kamiokande (SK) I-V. A theoretical study predicts proton decay rates without assuming a particular grand unified theory and suggests that three-body proton decays involving two pion

Mintae Kim, Koushil Sreenath

Reinforcement learning (RL) policies often fail under dynamics that differ from training, a gap not fully addressed by domain randomization or existing adversarial RL methods. Distributionally robust RL provides a formal remedy but still relies on surrogate adversaries to approximate intractable primal problems, leaving blind spots that potentially cause ins

Qixian Huang, Hongqiang Lin, Tong Fu, Yingsen Wang

Reasoning over tabular data is a crucial capability for tasks like question answering and fact verification, as it requires models to comprehend both free-form questions and semi-structured tables. However, while methods like Chain-of-Thought (CoT) introduce reasoning chains, purely symbolic methodes are inherently limited by their blindness to holistic visu

Kouser Qureshie, S. P. Rouoof, J. A. Sheikh, N. Rather

The present work is a continuation of our earlier investigation with the primary objective to systematically calculate the $E2$ matrix elements using the microscopic approach of the triaxial projected shell model (TPSM). In the earlier work, we studied nine nuclides of $^{72}$Ge, $^{76}$Ge, $^{104}$Ru, $^{168}$Er, $^{186}$Os, $^{188}$Os, $^{190}$Os, $^{192}$

Xincheng Yao, Zefeng Qian, Chao Shi, Jiayang Song

In the progress of industrial anomaly detection, general anomaly detection (GAD) is an emerging trend and also the ultimate goal. Unlike the conventional single- and multi-class AD, general AD aims to train a general AD model that can directly detect anomalies in diverse novel classes without any retraining or fine-tuning on the target data. Recently, Multim

Kevin Setterstrom, Jeremy Straub

This study evaluates the feasibility of integrating lightweight block cipher payload encryption into a real-time embedded controller area network (CAN) node using a QT PY ESP32-S2 microcontroller. This work seeks to determine whether the use of a block cipher can prevent semantic taxonomy-based reverse engineering, which infers signal meaning from unencrypte

Ben Isselmann, Dilara Göksu, Heinz Neumann, Andreas Weinmann

Background: Task-specific microscopy datasets are often small, making it difficult to train deep learning models that learn robust features. While self-supervised learning (SSL) has shown promise through pretraining on large, domain-specific datasets, generalizability across datasets with differing staining protocols and channel configurations remains undere

Muhammad Junaid Asif, Muhammad Saad Rafaqat, Usman Nazakat, Uzair Khan

To ensure energy efficiency and reliable operations, it is essential to monitor solar panels in generation plants to detect defects. It is quite labor-intensive, time consuming and costly to manually monitor large-scale solar plants and those installed in remote areas. Manual inspection may also be susceptible to human errors. Consequently, it is necessary t

Victor De Lima, Grace Hui Yang

Most conversational agents (CAs) are designed to satisfy user needs through user-driven interactions. However, many real-world settings, such as academic interviewing, judicial proceedings, and journalistic investigations, involve broader institutional decision-making processes and require agents that can elicit information from users. In this paper, we intr

Minxing Zheng, Zewei Deng, Liyan Xie, Shixiang Zhu

Many safety-critical scientific and engineering systems evolve according to differential-algebraic equations (DAEs), where dynamical behavior is constrained by physical laws and admissibility conditions. In practice, these systems operate under stochastically varying environmental inputs, so stability is not a static property but must be reassessed as the co

Yinuo Yang, Zixian Ma, Manasi Ganti, Jieyu Zhang

We present a discriminative multimodal reward model that scores all candidate responses in a single forward pass. Conventional discriminative reward models evaluate each response independently, requiring multiple forward passes, one for each potential response. Our approach concatenates multiple responses with separator tokens and applies cross-entropy over

Selçuk Korkmaz

Data leakage remains a recurrent source of optimistic bias in biomedical machine learning studies. Standard row-wise cross-validation and globally estimated preprocessing steps are often inappropriate for data with repeated measurements, study-level heterogeneity, batch effects, or temporal dependencies. This paper describes bioLeak, an R package for constru

Linquan Ma

We construct examples of local cohomology modules of ramified regular local rings with infinitely many associated primes and infinite Bass numbers.

Ruiyang Li, Fang Liu, Licheng Jiao, Xinglin Xie

Medical image segmentation supports clinical workflows by precisely delineating anatomical structures and lesions. However, medical image datasets medical image datasets suffer from acquisition noise and annotation ambiguity, causing pervasive data uncertainty that substantially undermines model robustness. Existing research focuses primarily on model archit

Xiaotian Qiu, Lukai Chen, Jinhao Li, Qi Sun

Flow Matching (FM) policies have emerged as an efficient backbone for robotic control, offering fast and expressive action generation that underpins recent large-scale embodied AI systems. However, FM policies trained via imitation learning inherit the limitations of demonstration data; surpassing suboptimal behaviors requires reinforcement learning (RL) fin

Tomoei Takahashi, Takashi Takahashi, Yoshiyuki Kabashima

Diffusion models generate high-dimensional data such as images by learning a process that gradually removes noise from corrupted data. Recent studies have shown that the backward dynamics of diffusion models exhibit two characteristic transitions: the speciation transition, at which generated samples begin to capture the global structure of the training data

Zhiyi Duan, Hongyu Yuan, Rui Liu

Knowledge Tracing (KT) infers a student's knowledge state from past interactions to predict future performance. Conventional Deep Learning (DL)-based KT models are typically tied to platform-specific identifiers and latent representations, making them hard to transfer and interpret. Large Language Model (LLM)-based methods can be either ungrounded under prom

Erhan Bayraktar, Bingyan Han, Ziqing Zhang

We study continuous-time online learning where data are generated by a diffusion process with unknown coefficients. The learner employs a two-layer neural network, continuously updating its parameters in a non-anticipative manner. The mean-field limit of the learning dynamics corresponds to a stochastic Wasserstein gradient flow adapted to the data filtratio

Hiroki Fukui

Writing systems are cultural replicators whose evolution has never been studied quantitatively at global scale. We compile the Global Script Database (GSD): 300 writing and notation systems, 50 binary structural characters, and 259 phylogenetic edges spanning 5,400 years. Applying four methods -- phenetics, cladistics, Bayesian inference, and neural network

Alma Partos, Igor Di Marco, Shivalika Sharma

The study of magnetism in transition metals is a cornerstone in understanding complex electronic and magnetic interactions in condensed matter systems. Among transition metal elements, body-centered cubic (bcc) chromium stands out because of its spin-density wave (SDW) ground state, posing a long-standing challenge for density functional theory (DFT). Conven

Zhiheng Zhou, Mengyao Zhou, Xixun Lin, Xingqin Qi

Hypergraph neural networks (HGNNs) have shown remarkable potential in modeling high-order relationships that naturally arise in many real-world data domains. However, existing HGNNs often suffer from shallow propagation, oversmoothing, and limited adaptability to complex hypergraph structures. In this paper, we propose Hypergraph Neural Diffusion (HND), a no

Haohang Xu, Lin Liu, Zhibo Zhang, Rong Cong

Diffusion-based image editing models have achieved significant progress in real world applications. However, conventional models typically rely on natural language prompts, which often lack the precision required to localize target objects. Consequently, these models struggle to maintain background consistency due to their global image regeneration paradigm.

Jie Han, Tong Li, Qingyang Xu, Yong Song

The online 3D bin packing problem is important in logistics, warehousing and intelligent manufacturing, with solutions shifting to deep reinforcement learning (DRL) which faces challenges like low sample efficiency. This paper proposes a diffusion reinforcement learning-based algorithm, using a Markov decision chain for packing modeling, height map-based sta

Prateek Chanda, Prayas Agrawal, Karthik S. Gurumoorthy, Ganesh Ramakrishnan

Selecting prototypical examples from a source distribution to represent a target data distribution is a fundamental problem in machine learning. Existing subset selection methods often rely on implicit importance scores, which can be skewed towards majority classes and lead to low-quality prototypes for minority classes. We present $\methodprop$, a novel sub

Farrukh A. Chishtie

We propose that the enhanced Higgs quartic coupling required by radiatively broken electroweak symmetry (RBEWS) emerges naturally from SO(10) grand unification. Our previous analysis demonstrated that a coupling enhancement factor $k = \lambda_{\rm enhanced}/\lambda_{\rm SM}$ leads to absolute vacuum stability with a UV Landau pole near the GUT scale for $k

Xuan Yu, Yuxuan Xie, Shichao Zhai, Shuhao Ye

Open-vocabulary panoptic reconstruction is crucial for advanced robotics and simulation. However, existing 3D reconstruction methods, such as NeRF or Gaussian Splatting variants, often struggle to achieve the real-time inference frequency required by robotic control loops. Existing methods incur prohibitive latency when processing the high-dimensional featur

Jihun Kim, Hoyong Kwon, Hyeokjun Kweon, Kuk-Jin Yoon

Fully supervised Video Semantic Segmentation (VSS) relies heavily on densely annotated video data, limiting practical applicability. Alternatively, applying pre-trained Image Semantic Segmentation (ISS) models frame-by-frame avoids annotation costs but ignores crucial temporal coherence. Recent foundation models such as SAM2 enable high-quality mask propagat

Songlin Yang, Xianghao Kong, Anyi Rao

Unified multimodal models (UMMs) were designed to combine the reasoning ability of large language models (LLMs) with the generation capability of vision models. In practice, however, this synergy remains elusive: UMMs fail to transfer LLM-like reasoning to image synthesis and exhibit divergent response behaviors. We term this phenomenon pseudo-unification. D

Lewis A. Williamson, Karandeep Gill, Andrew J. Groszek, Matthew J. Davis

Free-fall atom interferometers offer a powerful platform for accurate, absolute gravitational sensing. Szigeti et al. [Phys. Rev. Lett. 125, 100402 (2020)] recently proposed a quantum-enhanced scheme that uses a spin-squeezed Bose-Einstein condensate as an input state to improve the phase sensitivity of the interferometer. The spin squeezing, generated via o

Jing Qi, Yuxiang Wang, Zhiyuan Yu, Xiaoliang Xu

Continual Knowledge Graph Embedding (CKGE) aims to continually learn embeddings for new knowledge, i.e., entities and relations, while retaining previously acquired knowledge. Most existing CKGE methods mitigate catastrophic forgetting via regularization or replaying old knowledge. They conflate new and old knowledge of an entity within the same embedding sp

Zhen Qin, Jiachen Jiang, Zhihui Zhu

Transformer models have become foundational across a wide range of scientific and engineering domains due to their strong empirical performance. A key capability underlying their success is in-context learning (ICL): when presented with a short prompt from an unseen task, transformers can perform per-token and next-token predictions without any parameter upd

Omid Halimi Milani, Amanda Nikho, Marouane Tliba, Lauren Mills

Accurate assessment of spheno-occipital synchondrosis (SOS) maturation is a key indicator of craniofacial growth and a critical determinant for orthodontic and surgical timing. However, SOS staging from cone-beam CT (CBCT) relies on subtle, continuously evolving morphological cues, leading to high inter-observer variability and poor reproducibility, especial

Xin-Ru Wang, Shu-Qi Wang, Shi-Dong Liu, Qi Wu

Recently, the BESIII Collaboration reported the first observation of the decays $\chi_{cJ} \to \eta \eta \eta^\prime$ in order to search for the $1^{-+}$ exotic state $\eta_1(1855)$. A partial wave analysis of the $\eta \eta^\prime$ invariant mass spectrum shows no significant signal for the $\eta_1(1855)$. In this work, we, using an effective Lagrangian app

Jonathan A. Hillman, Riccardo Pedrotti

We address the question of existence of sections of fibrations in two settings. First, we show that a bundle with base a finite 2-complex admits a section if and only if the inclusion of the fiber is $\pi_1$-injective and the associated short exact sequence of fundamental groups splits. Second, for Lefschetz fibrations over the disk we provide a complete alg

Jian-Dong Liu, Wen-Biao Han, Hiromichi Tagawa

Extreme-mass-ratio inspirals (EMRIs) carry valuable information about their surrounding astrophysical environments. Over the course of their long-term evolution, interactions between the secondary object and the accretion disk can produce observable effects on both the orbital evolution and the emitted gravitational waveform. Based on the modifications to th

Zheng Liu

Rapid growth in artificial intelligence (AI) workloads is driving up data center power densities, increasing the need for advanced thermal management. Direct-to-chip liquid cooling can remove heat efficiently at the source, but many cold plate channel layouts remain heuristic and are not optimized for the strongly non-uniform temperature distribution of mode

Juncheng Hu, Ziteng Xue, Guotao Liang, Anran Qi

We introduce AmodalSVG, a new framework for amodal image vectorization that produces semantically organized and geometrically complete SVG representations from natural images. Existing vectorization methods operate under a modal paradigm: tracing only visible pixels and disregarding occlusion. Consequently, the resulting SVGs are semantically entangled and g

Yueci Deng, Guiliang Liu, Kui Jia

Deploying generative World-Action Models for manipulation is severely bottlenecked by redundant pixel-level reconstruction, $\mathcal{O}(T)$ memory scaling, and sequential inference latency. We introduce the Causal Latent World Model (CLWM), which employs DINOv3 features as generative targets to disentangle interaction semantics from visual noise, yielding h

Hai-Yang Cheng, Chia-Wei Liu

We study the lifetimes and inclusive semileptonic decay widths of doubly heavy baryons within the framework of heavy quark expansion. Our analysis includes next-to-leading-order corrections to the dimension-3, -5, and -6 operators, together with the leading dimension-7 contributions, while the nonperturbative matrix elements are evaluated in a bag model with

Shanshan Zhong, Kate Shen, Chenyan Xiong

Agentic Web is an emerging paradigm where autonomous agents help users use online information. As the paradigm develops, content providers are also deploying agents to manage their data and serve it through controlled interfaces. This shift moves information access from centralized retrieval to decentralized coordination. To study this setting, we introduce

Angqing Jiang, Jianlyu Chen, Zhe Fang, Yongcan Wang

Effective medical text retrieval requires both high accuracy and low latency. While LLM-based embedding models possess powerful retrieval capabilities, their prohibitive latency and high computational cost limit their application in real-time scenarios. Furthermore, the lack of comprehensive and high-fidelity benchmarks hinders progress in Chinese medical te

Devika Shylaja

This paper presents a convergence analysis for the Hessian Discretisation Method (HDM) applied to fourth-order semilinear elliptic equations involving a trilinear nonlinearity and general source, based on two complementary approaches. The HDM serves as a unified framework for the convergence analysis of various numerical schemes, including conforming and non

Sunao Ouchi

A singular perturbation problem called WKB equation (Eq) $h^2u(x,h)-Q(x)u(x,h)=0$ is studied. $h>0$ is a small parameter. Investigation of (Eq) has long history. Recently it has developed by a new method named "Exact WKB Analysis" based on Borel resummation method and new analytic results. Here we study (Eq) by another elementary method. We only apply advanc

Sergey V. Samsonau

The way science is currently practiced shows conclusions but hides how they were reached. Researchers work privately, polish their results, publish a finished paper, and defend it. Errors are punished by retraction rather than corrected by amendment. Alternative directions are pursued through competing papers with no shared history. The reasoning, the dead e

Huawei Hou, Suzhi Bi, Xian Li, Haixia Zhang

Semantic communication has been increasingly integrated into edge computing systems for reconstruction tasks, owing to its advantages in source compression, robustness to channel noise, and task execution efficiency. However, the black-box nature of neural-network (NN)-based semantic codecs, together with the noisy transmission of semantic features, makes it

Ishara Hewa Pathiranage, Aneta Neumann

The multiple knapsack problem (MKP) generalizes the classical knapsack problem by assigning items to multiple knapsacks subject to capacity constraints. It is used to model many real-world resource allocation and scheduling problems. In practice, these optimization problems often involve stochastic and dynamic components. Evolutionary algorithms provide a fl

Wenhao Wang, Yanyan Li, Long Jiao, Jiawei Yuan

Recent advances in large language models (LLMs) provide robots with contextual reasoning abilities to comprehend human instructions. Yet, current LLM-enabled robots typically depend on cloud-based models or high-performance computing infrastructure, which limit their deployment on robots under unreliable internet environments or with constrained computationa

Muhammad Usama Saleem, Mayur Jagdishbhai Patel, Ekkasit Pinyoanuntapong, Zhongxing Qin

We propose LiveGesture, the first fully streamable, speech-driven full-body gesture generation framework that operates with zero look-ahead and supports arbitrary sequence length. Unlike existing co-speech gesture methods, which are designed for offline generation and either treat body regions independently or entangle all joints within a single model, LiveG

Mengyuan Cao, Xu Liu, Hongliang Zhang

Meta-backscatter system that utilizes meta-material sensors is a promising enabler for future environmental sensing, offering distinct advantages such as low cost, zero-power consumption, and robustness. Specifically, the electromagnetic response of the sensor, typically characterized by a frequency-selective absorption profile, is affected by the environmen

Shasha Luo, Jiabao Gong, Qiang Tu

In this paper, we investigate an $L_p$ dual Christoffel-Minkowski type problem for the Hessian quotient operator $\frac{\sigma_{k}(\Lambda)}{\sigma_{l}(\Lambda)}$, where the operator $\Lambda$ has been widely studied in the literature. Exploiting the recently discovered ``inverse convexity'' property of this class of operators, we establish a full rank theor

Zihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang

While large language model--powered agents can self-evolve by accumulating experience or by dynamically creating new assets (i.e., tools or expert agents), existing frameworks typically treat these two evolutionary processes in isolation. This separation overlooks their intrinsic interdependence: the former is inherently bounded by a manually predefined stat

Andrei K. Svinin

We present and investigate a new infinite family of homogeneous equations which possess the Laurent property. The first representative in this family is the well-known Somos-5 recurrence.

Mohammad Milanian, Alex Dytso, Martina Cardone

In this paper, we study Sibson's $α$-mutual information in the context of the additive Gaussian noise channel. While the classical case $α= 1$ is well understood and admits deep connections to estimation-theoretic quantities, such as the minimum mean-square error (MMSE) and Fisher information, many of the corresponding structural properties for general $

Elmira Nabizadeh-Morsalfard, Christine Pfeuffer, Nenad Teofanov, Joachim Toft

We deduce various norm equivalences, and convolution estimates for the modulation space $M^{\sharp ,q}_{(\omega )}$ consisting of all $f\in M^{\infty ,q}_{(\omega )}$ such that $|V_\phi f \cdot \omega |$ satisfies a mild vanishing condition at infinity. We prove that $M^{\sharp ,q}_{(\omega )}$ is the completion of the Gelfand-Shilov space $\Sigma _1$ under

Tian Liu, Haohao Hao, Jiaxi Liu, Yongjie Zhou

Hydrodynamic coarsening of bicontinuous domains is a central process in liquid-liquid phase separation, yet how soluble surfactants regulate this process remains poorly understood. Using a validated two-order-parameter phase-field model coupled to the incompressible Navier-Stokes equations, we show that hydrodynamic coarsening is suppressed primarily by surf

Wei Gu

We present a semiclassical account of the Veneziano-Yankielowicz (VY) superpotential in four-dimensional $N=1$ super Yang-Mills theory. Motivated by two-dimensional gauged linear sigma models, where superpotentials arise from vortex dynamics, we reinterpret domain walls as fundamental objects associated with higher-form gauge fields. In this formulation, the

Yunfan Yang, Cuiling Lan, Jitao Sang, Yan Lu

Tables contain rich structured information, yet when stored as images their contents remain "locked" within pixels. Converting table images into LaTeX code enables faithful digitization and reuse, but current multimodal large language models (MLLMs) often fail to preserve structural, style, or content fidelity. Conventional post-training with reinfor

Chengrui Huang, Junshuo Zhang, Zhiyuan Ma, Xikun Wang

Enabling large language models to scale and reliably use hundreds of tools is critical for real-world applications, yet challenging due to the inefficiency and error accumulation inherent in flat tool-calling architectures. To address this, we propose Hybrid Toolset Agentization & Adaptation (HTAA), a hierarchical framework for scalable tool-use planning. We

Xucheng Wang, Xiaoman Zhang, Sung Eun Kim, Ankit Pal

Ultrasound acquisition requires skilled probe manipulation and real-time adjustments. Vision-language models (VLMs) could enable autonomous ultrasound systems, but existing benchmarks evaluate only static images, not dynamic procedural understanding. We introduce ReXSonoVQA, a video QA benchmark with 514 video clips and 514 questions (249 MCQ, 265 free-respo

R. B. Iyer, S. H. Park, N. R. Sahoo, T. Low

Moire lattices provide a powerful route for engineering emergent symmetries and length scales through the relative rotation of periodic structures. However, their implementation in polaritonic systems remains relatively unexplored, and a general framework describing how twist modifies the interaction of optical modes in momentum space is still lacking. Here,

Jian Zhou

The Cohn-Elkies linear programming (LP) bound for sphere packing is known to be sharp in dimensions 8 and 24 but in no other dimension above 2. We investigate why by examining three independent necessary conditions for LP sharpness, drawn from number theory, lattice theory, and conformal field theory. The first condition, dim S_{d/2}(SL_2(Z)) <= 1, bounds th

Shin Kiriki, Xiaolong Li, Yushi Nakano, Teruhiko Soma

We show that within the Newhouse domain of $C^r$ surface diffeomorphisms ($r \in [2,\infty )$), there exists a dense subset $\mathcal D$ such that for any $f \in \mathcal D$, Lyapunov exponents fail to exist for all points in some open set $U$ and all nonzero tangent vectors in some open cone $V \subset \mathbb{R}^2$. This demonstrates that the non-existence

Qiang Gao, Yi Wang, Yong Zhang, Yong Li

Medical image segmentation remains challenging due to limited fine-grained annotations, complex anatomical structures, and image degradation from noise, low contrast, or illumination variation. We propose TAMISeg, a text-guided segmentation framework that incorporates clinical language prompts and semantic distillation as auxiliary semantic cues to enhance v

Qinghui Gong

Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limitations. Feature-correction approaches often cause uncontrolled over-correction, while token-level interventions struggle with semantic granularity and context. Moreover, both types of methods are prone to sev

Chongliu Jia, Yi Luo, Sipeng Han, Pengwei Li

Medium- to long-horizon equity allocation is challenging due to weak predictive structure, non-stationary market regimes, and the degradation of signals under realistic trading constraints. Conventional approaches often rely on single predictors or loosely coupled pipelines, which limit robustness under distributional shift. This paper proposes EvoNash-MARL,

Jierun Lin, Jiacong Chen, Qingyu Mao, Shuai Liu

2D Gaussian Splatting (2DGS) has recently become a promising paradigm for high-quality video representation. However, existing methods employ content-agnostic or spatio-temporal feature overlapping embeddings to predict canonical Gaussian primitive deformations, which entangles static and dynamic components in videos and prevents modeling their distinct prop

Francesco De Pas, Serena Dipierro, Enrico Valdinoci

This survey offers an overview of recent advances in nonlocal phase transition problems, modeled by Ginzburg--Landau type energies of the form \[ \frac{1}{4}\iint_{\R^{2n}\setminus (\R^n \setminus \Omega)^2} \frac{|u(x)-u(y)|^2}{|x-y|^{n+2s}}\,dx\,dy \;+\; \int_\Omega W(u(x))\,dx. \] Here,~$W$ is a smooth and possibly \textit{degenerate} double well potentia

Chao Li, Yuru Wang

Every existing knowledge system separates storage from computation. We show this separation is unnecessary and eliminate it. In a standard triple is_a(Apple, Company), domain context lives in the query or the programmer's mind. In a CDC four-tuple is_a(Apple, Company, @Business), domain becomes a structural field embedded in predicate arity. Any system respe

Shilian Zheng, Jie Chen, Luxin Zhang, Xiaoniu Yang

Robust radio signal recognition is fundamental to spectrum management, electromagnetic space security, and intelligent wireless applications, yet existing deep-learning methods rely heavily on large labeled datasets and struggle to capture the multi-domain characteristics inherent in real-world signals. To address these limitations, we propose an unsupervise

Ma. Madecheen S. Pangaliman, Steven S. Sison, Erwin P. Quilloy, Rowel Atienza

As vision-based robots navigate larger environments, their spatial memory grows without bound, eventually exhausting computational resources, particularly on embedded platforms (8-16GB shared memory, $<$30W) where adding hardware is not an option. This survey examines the spatial memory efficiency problem across 88 references spanning 52 systems (1989-2025),

Sreyan Ghosh, Arushi Goel, Kaousheik Jayakumar, Lasha Koroshinadze

We present Audio Flamingo Next (AF-Next), the next-generation and most capable large audio-language model in the Audio Flamingo series, designed to advance understanding and reasoning over speech, environmental sounds and music. Compared to Audio Flamingo 3, AF-Next introduces: (i) a stronger foundational audio-language model that significantly improves accu

Matteo Wohlrapp, Niklas Bubeck, Daniel Rueckert, William Lotter

AI-based image reconstruction models are increasingly deployed in clinical workflows to improve image quality from noisy data, such as low-dose X-rays or accelerated MRI scans. However, these models are typically evaluated using pixel-level metrics like PSNR, leaving their impact on downstream diagnostic performance and fairness unclear. We introduce a scala

Hanxiao Li, Kun Zhang

We study a weakened version of the Holm--Willems Local Conjecture. The problem is reduced to quasi-simple groups under the assumption that the defect group is abelian. Complete proofs are provided in the case \(p = 2\).

Vishesh Jain, Huy Tuan Pham, Thuy-Duong Vuong

Entropic independence is a structural property of measures that underlies modern proofs of functional inequalities, notably (modified) log-Sobolev inequalities, via ``annealing'' or local-to-global schemes. Existing sufficient criteria for entropic independence typically require spectral independence and/or uniform bounds on marginals under \emph{all} pinnin