arXiv preprints from January 1, 2026 through September 27, 2026 — 02:08:47 EST
In this paper we consider a testing setting where the set of possible definitions of the Implementation Under Test (IUT), as well as the behavior of each of these definitions in all possible interactions, are extensionally defined, i.e., on an element-by-element and case-by-case basis. Under this setting, the problem of finding the...
Unsupervised deep image prior (DIP) addresses shortcomings of training data requirements and limited generalization associated with supervised deep learning. The performance of DIP depends on the network architecture and the stopping point of its iterative process. Optimizing these parameters for a new image requires time, restricting...
Understanding how the brain integrates motor suppression with motivational processes remains a fundamental question in neuroscience. The rostral Pedunculopontine nucleus, a brainstem structure involved in motor control, has been shown to induce transient motor arrest upon optogenetic or electrical stimulation. However, our current...
While foundation models have achieved remarkable results across a diversity of domains, they still rely on human-generated data, such as text, as a fundamental source of knowledge. However, this data is ultimately the product of human brains, the filtered projection of a deeper neural complexity. In this paper, we explore a new...
Optical remote sensing imagery is indispensable for Earth observation, yet persistent cloud occlusion limits its downstream utility. Most cloud removal (CR) methods are optimized for low-level fidelity and can over-smooth textures and boundaries that are critical for analysis-ready data (ARD), leading to a mismatch between visually...
In federated learning, Transformer, as a popular architecture, faces critical challenges in defending against gradient attacks and improving model performance in both Computer Vision (CV) and Natural Language Processing (NLP) tasks. It has been revealed that the gradient of Position Embeddings (PEs) in Transformer contains sufficient...
We study function computation over a Gaussian multiple-access channel (MAC), where multiple transmitters aim at computing a function of their values at a common receiver. To this end, we propose a novel coded-modulation framework for over-the-air computation (OAC) based on hierarchical constellation design, which supports reliable...
Interpretability of modern visual models is crucial, particularly in high-stakes applications. However, existing interpretability methods typically suffer from either reliance on white-box model access or insufficient quantitative rigor. To address these limitations, we introduce FocaLogic, a novel model-agnostic framework designed to...
We prove a family of partition identities involving integer partitions in three colors. The conditions imposed on the types of partitions appearing in these identities involve constraints that arise in the Rogers-Ramanujan and Andrews-Gordon identities, as well as in their recent extensions. The identities established in this paper...
The spin properties of excitons and charge carriers in CsPbBr$_3$ lead halide perovskite crystals are investigated by spin-dependent light scattering in magnetic fields up to 10 T. Spin-flip Raman scattering spectra measured under resonant excitation of exciton-polaritons show a rich variety of features provided by the Zeeman...
We study dynamic games with hidden states and absorbing failure, where belief-driven actions can trigger irreversible collapse. In such environments, equilibria that sustain activity generically operate at the boundary of viability. We show that this geometry endogenously reverses the value of information: greater informational...
The type $A_n$-singularity $\mathbb{C}^2/\mathbb{Z}_{n+1}$ can be resolved by hyper-Kähler manifolds $X_ζ$ with underlying smooth manifolds diffeomorphic to the resolution of singularities $X_{\text{res}}$, whose hyper-Kähler structure depends on a parameter $ζ\in H_2(X_{\text{res}};\mathbb{R})$. The structure as a complex manifold of...
We study endpoint Koopman spectral computation from the viewpoint of the Solvability Complexity Index (SCI). Let \((\mathcal X,d)\) be a compact metric space with finite Borel measure \(ω\), and let \(\mathcal K_F\) be the Koopman operator associated with a continuous nonsingular map \(F:\mathcal X\to\mathcal X\). First, on...
The theory of nuclear excitations involving nucleon resonances is revisited and significantly extended to asymmetric nuclear matter and higher P- and S-wave $N^*$ resonances. Excited states of are described as superpositions of particle-hole configurations including $NN^{'-1}$ and $N^*N^{-1}$ configurations. Configuration mixing is...
Visual token compression is widely adopted to improve the inference efficiency of Large Vision-Language Models (LVLMs), enabling their deployment in latency-sensitive and resource-constrained scenarios. However, existing work has mainly focused on efficiency and performance, while the security implications of visual token compression...
We study ideal-based refinements of sequential compactness arising from the class FinBW(I), consisting of topological spaces in which every sequence admits a convergent subsequence indexed by a set outside a given ideal I. A central theme of this work is the existence of critical ideals whose position in the Katetov order determines...
The use of Large Language Models (LLMs) for reasoning and planning tasks has drawn increasing attention in Artificial Intelligence research. Despite their remarkable progress, these models still exhibit limitations in multi-step inference scenarios, particularly in mathematical and logical reasoning. We introduce PREGU (Partial...
The paper develops a Transformer architecture for estimating dynamic factors from multivariate time series data under flexible identification assumptions. Performance on small datasets is improved substantially by using a conventional factor model as prior information via a regularization term in the training objective. The results...
Dung's abstract argumentation frameworks model acceptability solely in terms of an attack relation, thereby conflating two conceptually distinct aspects of argumentative reasoning: direct conflict between arguments and the structural dependencies that arise from their internal composition. While this abstraction preserves...
Wildfires cause major losses worldwide, and the frequency of fire-weather conditions is likely to increase in many regions. We study the allocation of suppression resources over time on a graph-based representation of a landscape to slow down fire propagation. Our contributions are theoretical and methodological. First, we prove that...
We investigate how vibrotactile wrist feedback can enhance spatial guidance for handheld tool movement in optical see-through augmented reality (AR). While AR overlays are widely used to support surgical tasks, visual occlusion, lighting conditions, and interface ambiguity can compromise precision and confidence. To address these...
We generalize Tutte's integer flows and the $d$-dimensional Euclidean flows of Mattiolo, Mazzuoccolo, Rajník, and Tabarelli to \emph{$d$-dimensional $p$-normed nowhere-zero flows} and define the corresponding flow index $φ_{d,p}(G)$ to be the infimum over all real numbers $r$ for which $G$ admits a $d$-dimensional $p$-normed...
With the growing scale of social media, social event detection and evolution modeling have attracted increasing attention. Graph neural networks (GNNs) and transformer-based pre-trained language models (PLMs) have become mainstream approaches in this area. However, existing methods still face three major challenges. First, the sheer...
Personalization in Large Language Models (LLMs) often relies on user-specific soft prompts. However, these prompts become obsolete when the foundation model is upgraded, necessitating costly, full-scale retraining. To overcome this limitation, we propose the Prompt-level User Migration Adapter (PUMA), a lightweight framework to...
Quantization is widely adopted to reduce the computational cost of large language models (LLMs); however, its implications for fairness and safety, particularly in dynamic quantization and multilingual contexts, remain underexplored. In this work, we conduct a systematic study of how static and dynamic quantization methods impact...