arXiv preprints from January 1, 2026 through September 12, 2026 — 12:05:44 EST
Fault injection is a key technique for assessing software reliability, enabling proactive detection of system defects before they manifest in production. However, the increasing complexity of microservice architectures leads to exponential growth in the fault-injection space, rendering traditional random injection inefficient. Recent...
Multi-modal object tracking has attracted considerable attention by integrating multiple complementary inputs (e.g., thermal, depth, and event data) to achieve outstanding performance. Although current general-purpose multi-modal trackers primarily unify various modal tracking tasks (i.e., RGB-Thermal infrared, RGB-Depth or RGB-Event...
Designing good reflection questions is pedagogically important but time-consuming and unevenly supported across teachers. This paper introduces a reflection-in-reflection framework for automated generation of reflection questions with large language models (LLMs). Our approach coordinates two role-specialized agents, a Student-Teacher...
Current remote sensing change detection (CD) methods mainly rely on specialized models, which limits the scalability toward modality-adaptive Earth observation. For homogeneous CD, precise boundary delineation relies on fine-grained spatial cues and local pixel interactions, whereas heterogeneous CD instead requires broader contextual...
This guide based on recent papers should help researchers avoid some of the most common pitfalls of missing value imputation imputation.
Digital traces of daily activities, such as e-commerce (EC) purchase histories, provide scalable signals for public health surveillance, yet their epidemiological validity remains unclear. This study validates a behavioral proxy for disease onset, defined as transitions from regular to therapeutic diets, by comparing large-scale EC...
We introduce RANDSMAPs (Random-feature/multi-scale neural decoders with Mass Preservation), numerical analysis-informed, explainable neural decoders designed to explicitly respect conservation laws when solving the challenging ill-posed pre-image problem in manifold learning. We start by proving the equivalence of vanilla random...
This paper proposes LiNUS, a lightweight deep learning framework for the automatic segmentation of the Subthalamic Nucleus (STN) in Deep Brain Stimulation (DBS) surgery. Addressing the challenges of small target volume and class imbalance in MRI data, LiNUS improves upon the U-Net architecture by introducing spectral normalization...
Despite their practical success, it remains unclear why Mixture of Experts (MoE) models can outperform dense networks beyond sheer parameter scaling. We study an iso-parameter regime where inputs exhibit latent modular structure but are corrupted by feature noise, a proxy for noisy internal activations. We show that sparse expert...
The scarcity of training data presents a fundamental challenge in applying deep learning to archaeological artifact classification, particularly for the rare types of Chinese porcelain. This study investigates whether synthetic images generated through Stable Diffusion with Low-Rank Adaptation (LoRA) can effectively augment limited...
While Large Language Models demonstrate remarkable proficiency in high-level semantic planning, they remain limited in handling fine-grained, low-level web component manipulations. To address this limitation, extensive research has focused on enhancing model grounding capabilities through techniques such as Reinforcement Learning....
Understanding the thermal behavior of quantum many-body pure states is one of the most fundamental issues in quantum thermodynamics. It is widely known that typical pure states yield vanishing work, just as thermal states do, when one restricts to local operations that cannot access correlations among subsystems. However, it remains...
Diffusion models have seen widespread adoption for text-driven human motion generation and related tasks due to their impressive generative capabilities and flexibility. However, current motion diffusion models face two major limitations: a representational gap caused by pre-trained text encoders that lack motion-specific information,...
Adverse social interactions, such as bullying, harassment, and other illicit activities, pose significant threats to individual well-being and public safety, leaving profound impacts on physical and mental health. However, these critical events frequently occur in privacy-sensitive environments like restrooms, and changing rooms,...
NGC 4395 is a nearby dwarf spiral galaxy hosting an active galactic nucleus (AGN) powered by an intermediate-mass black hole (IMBH, $M_{\rm BH} \sim 10^{4}$--$10^{5}\,M_\odot$). Recent optical continuum reverberation mapping studies have suggested potential lag variations between different epochs, offering important clues to the...
Recent advances in text-to-music generation (TTM) have yielded high-quality results, but often at the cost of extensive compute and the use of large proprietary internal data. To improve the affordability and openness of TTM training, an open-source generative model backbone that is more training- and data-efficient is needed. In this...
In this analysis, we investigate the polarization radiation imaging of Kerr-Newman black holes, with a particular focus on the impact of black hole charge on photon propagation and polarization characteristics. By extending the traditional Walker-Penrose method, which is limited by its reliance on specific symmetric structures and...
Achieving bound consistency for the no-overlap constraint is known to be NP-complete. Therefore, several polynomial-time tightening techniques, such as edge finding, not-first-not-last reasoning, and energetic reasoning, have been introduced for this constraint. In this work, we derive the first bound-consistent algorithm for the...
Uncrewed aerial vehicle (UAV) swarms are pivotal in the applications such as disaster relief, aerial base station (BS) and logistics transportation. These scenarios require the capabilities in accurate sensing, efficient communication and flexible control for real-time and reliable task execution. However, sensing, communication and...
This paper presents Timepix2 Lite, a compact readout interface for the Timepix2 hybrid pixel detector, designed to provide high spatial and temporal resolution in a wide range of radiation detection applications. The Timepix2 Lite enables simultaneous energy and precise timing measurements on the nanosecond scale and supports advanced...
Changing-look active galactic nuclei (CLAGNs) represent a rare class of AGNs that undergo transitions from type 1 (characterized by the presence of broad emission lines in their spectra) to type 2 (absence of broad emission lines) or vice versa, over timescales ranging from months to years. Since normal type 1 and type 2 AGNs are...
Recognizing and navigating client resistance is critical for effective mental health counseling, yet detecting such behaviors is particularly challenging in text-based interactions. Existing NLP approaches oversimplify resistance categories, ignore the sequential dynamics of therapeutic interventions, and offer limited...
The integrated theory of the probe and singular sources methods (IPS) is developed for an inverse obstacle problem governed by the stationary Schrödinger equation in a bounded domain. The unknown obstacles are penetrable, and their surface is modeled by a part of the support of the potential in the governing equation. The main results...
Recent provably secure linguistic steganography (PSLS) methods rely on mainstream autoregressive language models (ARMs) to address historically challenging tasks, that is, to disguise covert communication as ``innocuous'' natural language communication. However, due to the characteristic of sequential generation of ARMs, the stegotext...
Movie dubbing is the task of synthesizing speech from scripts conditioned on video scenes, requiring accurate lip sync, faithful timbre transfer, and proper modeling of character identity and emotion. However, existing methods face two major limitations: (1) high-quality multimodal dubbing datasets are limited in scale, suffer from...