arXiv preprints from January 1, 2026 through September 25, 2026 — 22:13:56 EST
Text-to-Image In-Context Learning (T2I-ICL) enables customized image synthesis via interleaved text-image examples but faces two mutually reinforcing bottlenecks, compliance failure and prior-dominated hallucination, that form a vicious cycle degrading generation quality. Existing methods rely on tailored training, which limits...
Many real-world software tasks require exact transcription of provided data into code, such as cryptographic constants, protocol test vectors, allowlists, and calibration tables. These tasks are operationally sensitive because small omissions or alterations can remain silent while producing syntactically valid programs. This paper...
Integrated sensing and communication (ISAC) through Zak-transform-based orthogonal time frequency space (Zak-OTFS) modulation is a promising solution for high-mobility scenarios. Realizing accurate bistatic sensing and robust communication necessitates precise channel estimation; however, this remains a formidable challenge in doubly...
Topic modeling is a crucial technique for extracting latent themes from unstructured text data, particularly valuable in analyzing survey responses. However, traditional methods often only consider free-text responses and do not natively incorporate structured or categorical survey responses for topic modeling. And they produce...
This paper presents a sub-switching period current-limiting control for a grid-tied inverter to prevent transient overcurrents during grid faults and enable seamless fault ride-through (FRT). Sudden grid-voltage disturbances, such as voltage sags or phase jumps, can induce large transient currents within a switching period,...
Defect segmentation is central to computer vision based inspection of infrastructure assets during both construction and operation. However, deployment remains limited due to scarce pixel-level labels and domain shift across environments. We introduce CrackSegFlow, a controllable Flow Matching synthesis method that renders synthetic...
Non-Hermitian skin effects are conventionally manifested as boundary localization of eigenstates in linear systems. In nonlinear settings, however, where eigenstates are no longer well defined, it becomes unclear how skin effects should be faithfully characterized. Here, we propose a Koopman-based characterization of nonlinear skin...
In this work, we study geodesic curvature of the boundary of a two dimensional Alexandrov space of curvature bounded below (CBB). We prove several comparison and globalization theorems for the geodesic curvature, generalizing the known results for curves in space of curvature bounded above (CBA) by Alexander and Bishop (Differ. Geom....
Artificial neural network operators (ANNOs) have been widely used for approximating deterministic input-output functions; however, their extension to random dynamics remains comparatively unexplored. In this paper, we construct a new class of \textbf{Kantorovich-type Stochastic Neural Network Operators (K-SNNOs)} in which randomness...
Accurate and high-resolution precipitation nowcasting from radar echo sequences is crucial for disaster mitigation and economic planning, yet it remains a significant challenge. Key difficulties include modeling complex multi-scale evolution, correcting inter-frame feature misalignment caused by displacement, and efficiently capturing...
Zero-shot text-to-speech models can clone a speaker's timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires carefully selecting reference audio, which is impractical when only limited or mismatched references...
We study how the spin content of the thermal plasmas affects the propagation of gravitational waves in a radiation-dominated universe. As a simple but representative setup, we consider conformal scalar, Weyl fermion, and Maxwell fields that provide the background radiation, and we ask whether the resulting damping and phase shift of...
In evolutionary robotics, robot morphologies are designed automatically using evolutionary algorithms. This creates a body-brain optimization problem, where both morphology and control must be optimized together. A common approach is to include controller optimization for each morphology, but starting from scratch for every new body...
The rapid development of large language models has led to an increase in AI-generated text, with students increasingly using LLM-generated content as their own work, which violates academic integrity. This paper presents an evaluation of AI text detection methods, including both traditional machine learning models and...
Developing foundation models in medical imaging requires continuous monitoring of downstream performance. Researchers are burdened with tracking numerous experiments, design choices, and their effects on performance, often relying on ad-hoc, manual workflows that are inherently slow and error-prone. We introduce EvalBlocks, a modular,...
Massive short-period binaries involving hot subdwarf stars (sdO/Bs) are rare but important to constraining pathways for binary star evolution. Moreover, some of the most promising candidate progenitor systems leading to Type Ia supernovae (SNe Ia) involve sdO/Bs. LAMOST J065816.72+094343.1 has been identified as such a candidate. To...
The celebrated Mason's conjecture states that the sequence of independent set numbers of any matroid is log-concave, and even ultra log-concave. The strong form of Mason's conjecture was independently solved by Anari, Liu, Oveis Gharan and Vinzant, and by Brändén and Huh. The weak form of Mason's conjecture was also generalized to a...
Large language models (LLMs) have achieved notable performance in code synthesis; however, data-aware augmentation remains a limiting factor, handled via heuristic design or brute-force approaches. We introduce a performance-aware, closed-loop solution in the NNGPT ecosystem of projects that enables LLMs to autonomously engineer...
Evolutionary Robotics offers the possibility to design robots to solve a specific task automatically by optimizing their morphology and control together. However, this co-optimization of body and control is challenging, because controllers need some time to adapt to the evolving morphology - which may make it difficult for new and...
Fluctuating lattice Boltzmann solvers are widely employed to model mesoscopic fluid behavior in soft-matter systems, including colloidal suspensions and dilute polymer solutions. Despite their utility, these methods can lose accuracy and stability when non-hydrodynamic modes interfere with the dynamics, especially in...
Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are significantly harder to detect than backdoors that are based on trigger patterns due to the lack of...
New developments have been brought to our energy-, spin- and parity-dependent nuclear level densities based on the microscopic combinatorial method. Our new calculation is based on the BSkG3 mean-field model which relies on a three-dimensional coordinate-space representation of the nucleus, allowing for the spontaneous breaking of...
Single-photon emitters in hexagonal boron nitride (hBN) combine bright optical emission with optically addressable spin states, offering a promising platform for integrated quantum photonics. However, their stochastic creation and spectral variability have prevented deterministic integration with photonic cavities. Here we demonstrate...
In this paper, we present a reproducible benchmarking framework that systematically compares QML models with architecture-matched classical counterparts across three financial tasks: (i) directional return prediction on U.S. and Turkish equities, (ii) live-trading simulation with Quantum LSTMs versus classical LSTMs on the S\&P 500,...
Predicting the melting temperature (Tm) of multi-component and high-entropy alloys (HEAs) is critical for high-temperature applications but computationally expensive using traditional CALPHAD or DFT methods. In this work, we develop a gradient-boosted decision tree (XGBoost) model to predict Tm for complex alloys based on elemental...