arXiv preprints from January 1, 2026 through September 23, 2026 — 06:49:15 EST
As Large Language Models (LLMs) are increasingly deployed as autonomous agents, they face a critical scalability bottleneck known as the "Generalization-Specialization Dilemma." Monolithic agents equipped with extensive toolkits suffer from context pollution and attention decay, leading to hallucinations. Conversely, static...
Accurate prediction of joint kinematics and kinetics is essential for advancing gait analysis and developing intelligent assistive systems such as prosthetics and exoskeletons. This study presents a hybrid LSTM-UKF framework for estimating ankle angle and ground reaction force (GRF) across varying walking speeds. A multimodal sensor...
Learning solution operators for differential equations with neural networks has shown great potential in scientific computing, but ensuring their stability under input perturbations remains a critical challenge. This paper presents a robust self-supervised neural operator framework that enhances stability through adversarial training...
Large language model (LLM) personalization aims to adapt general-purpose models to individual users. Most existing methods, however, are developed under data-rich and resource-abundant settings, often incurring privacy risks. In contrast, realistic personalization typically occurs after deployment under (i) extremely limited user...
We introduce a {\it non-linear} generalization of the classical Dobrushin-Lanford-Ruelle (DLR) framework by developing the concept of a $q$-specification and the associated $q$-equilibrium measures. These objects arise naturally from a family of non-linear $q$-stochastic operators acting on the space of probability measures. A...
Deep generative models, particularly denoising diffusion models, have achieved remarkable success in high-fidelity generation of architected microstructures with desired properties and styles. Nevertheless, these recent methods typically rely on conditional training mechanisms and demand substantial computational effort to prepare the...
The M8.8 Kamchatka earthquake on July 29, 2025 was one of the largest in the first quarter of the 21st century. It deserves a thorough analysis including the preparation process. A smaller M7.4 earthquake occurred on July 20 with its epicenter within the confidence ellipse for the July 29 event. The aftershock sequence of the July 20...
Multimodal emotion recognition in conversation (MERC) requires representations that effectively integrate signals from multiple modalities. These signals include modality-specific cues, information shared across modalities, and interactions that emerge only when modalities are combined. In information-theoretic terms, these correspond...
For a purely $N$-periodic continued fraction $ξ=[\overline{a_0,a_1,\dots,a_{N-1}}]=[a_0,a_1,\cdots]$, with $a_k=a_{k+N}$ for all $k\ge 0$, and convergents $h_n/k_n=[a_0,a_1,\dots,a_n]$, we obtain explicit expressions for the weighted error sums $f_ξ(s)=\sum a_{n+1}\lvert h_n-ξk_n\rvert^s$ for $s>1$. A key observation is that, for each...
Weakly-interacting many-body systems possess remarkable quantum properties that are essential components of quantum technologies, and constitute a topic of fundamental interest. Here we show that in a solid-state nonlinear microcavity embedding discrete modes of exciton-dressed photons, we can isolate a single eigenmode of quantum...
WiFi sensing has suffered from the limited bandwidths designated for its original communication purpose, leading to fundamental limits in multipath resolution and thus multi-user sensing. Unfortunately, it is practically prohibitive to obtain large bandwidths on commercial WiFi, considering the conflict between the limited spectrum...
The rapid proliferation of Internet of Things (IoT) devices across domains such as smart homes, industrial control systems, and healthcare networks has significantly expanded the attack surface for cyber threats, including botnet-driven distributed denial-of-service (DDoS), malware injection, and data exfiltration. Conventional...
Millimeter-wave radar enables robust environment perception in autonomous systems under adverse conditions yet suffers from sparse, noisy point clouds with low angular resolution. Existing diffusion-based radar enhancement methods either incur high learning complexity by modeling full LiDAR distributions or fail to prioritize critical...
3D Vision-Language Models (VLMs), such as PointLLM and GPT4Point, have shown strong reasoning and generalization abilities in 3D understanding tasks. However, their adversarial robustness remains largely unexplored. Prior work in 2D VLMs has shown that the integration of visual inputs significantly increases vulnerability to...
Designing a unified neural network to efficiently and inherently process sequential data with arbitrary lengths is a central and challenging problem in sequence modeling. The design choices in Transformer, including quadratic complexity and weak length extrapolation, have limited their ability to scale to long sequences. In this work,...
Applying Physics-Informed Gaussian Process Regression to the eigenvalue problem $(\mathcal{L}-λ)u = 0$ poses a fundamental challenge, where the null source term results in a trivial predictive mean and a degenerate marginal likelihood. Drawing inspiration from system identification, we construct a transfer function-type indicator for...
Visual Reasoning CAPTCHAs (VRCs) combine visual scenes with natural-language queries that demand compositional inference over objects, attributes, and spatial relations. They are increasingly deployed as a primary defense against automated bots. Existing solvers fall into two paradigms: vision-centric, which rely on template-specific...
Vision-Language Models (VLMs) are increasingly used in safety-critical applications that require reliable visual grounding. However, these models often hallucinate details that are not present in the image to satisfy user prompts. While recent datasets and benchmarks have been introduced to evaluate systematic hallucinations in VLMs,...
Rendering reflections in curved mirrors is crucial for enhancing the realism in computer-generated hologram (CGH), yet it poses a fundamental challenge due to the unique computational principles of CGH. Conventional methods using Bézier clipping are computationally prohibitive, and a previously proposed mirror surface subdivision...
Large Language Models (LLMs) have recently shown strong potential for usage in sequential recommendation tasks through text-only models, which combine advanced prompt design, contrastive alignment, and fine-tuning on downstream domain-specific data. While effective, these approaches overlook the rich visual information present in many...
Guided by the flipping principle, we propose a novel extension of the Standard Model based on a double right-handed $U(1)$ gauge symmetry. In this framework, all left-handed fermions are neutral, while right-handed fermions of the third generation carry charges distinct from those of the first two generations. This structure naturally...
The emergence of Agentic AI systems has outpaced the architectural thinking required to operate them effectively. These agents differ fundamentally from traditional software: their behavior is not fixed at deployment but continuously shaped by experience, feedback, and context. Applying operational principles inherited from DevOps or...
We introduce pseudofinite W*-probability spaces. These are W*-probability spaces that are elementarily equivalent to Ocneanu ultraproducts of finite-dimensional von Neumann algebras equipped with arbitrary faithful normal states. We are particularly interested in the case where these finite-dimensional von Neumann algebras are full...
The author has been interested in regions surrounded by cylinders of real algebraic hypersurfaces and their shapes and polynomials associated to them. Here, we formulate and investigate natural decompositions into such cylinders of real algebraic hypersurfaces. Especially, intersections of these cylinders of real algebraic...
Large language models (LLMs) are increasingly grounded in sensor data to perceive and reason about human physiology and the physical world. However, accurately interpreting heterogeneous multimodal sensor data remains a fundamental challenge. We show that a single monolithic LLM often fails to reason coherently across modalities,...