arXiv preprints from January 1, 2026 through September 23, 2026 — 08:50:36 EST
Existing multi-object image generation methods face difficulties in achieving precise alignment between localized image generation regions and their corresponding semantics based on language descriptions, frequently resulting in inconsistent object quantities and attribute aliasing. To mitigate this limitation, mainstream approaches...
This study addresses critical gaps in Automated Essay Scoring (AES) systems and Large Language Models (LLMs) with regard to their ability to effectively identify and score harmful essays. Despite advancements in AES technology, current models often overlook ethically and morally problematic elements within essays, erroneously...
A scoring system is a linear classifier composed of a small number of explanatory variables, each assigned a small integer coefficient. This system is highly interpretable and allows predictions to be made with simple manual calculations without the need for a calculator. Several previous studies have used mixed-integer optimization...
Although Speech Large Language Models have achieved notable progress, a substantial modality reasoning gap remains: their reasoning performance on speech inputs is markedly weaker than on text. This gap could be associated with representational drift across Transformer layers and behavior deviations in long-chain reasoning. To address...
Automated unit test generation aims to improve software quality while reducing the time and effort required for creating tests manually. However, existing techniques primarily generate regression oracles that predicate on the implemented behavior of the class under test. They do not address the oracle problem: the challenge of...
Modern fourth-generation storage ring light sources predominantly utilize digital I/Q-based proportional-integral (PI) feedback for their radio-frequency (RF) systems. This paper introduces a dedicated PI feedback model implemented in the STABLE tracking code to enable accurate and fast longitudinal beam dynamics simulations. The...
\underline{Context:} Logging is a fundamental yet complex practice in software engineering, essential for monitoring, debugging, and auditing software systems. With the increasing integration of machine learning (ML) components into software systems, effective logging has become critical to ensure reproducibility, traceability, and...
LLM-integrated software, which embeds or interacts with large language models (LLMs) as functional components, exhibits probabilistic and context-dependent behaviors that fundamentally differ from those of traditional software. This shift introduces a new category of integration defects that arise not only from code errors but also...
Multi-modal image fusion aims to integrate complementary information from multiple source images to produce high-quality fused images with enriched content. Although existing approaches based on state space model have achieved satisfied performance with high computational efficiency, they tend to either over-prioritize infrared...
Heterogeneous Graph Neural Networks(HGNNs) have advanced mainly through better encoders, yet their decoding/projection stage still relies on a single shared linear head, assuming it can map rich node embeddings to labels. We call this the Linear Projection Bottleneck: in heterogeneous graphs, contextual diversity and long-tail shifts...
Modern database systems allow users to query or process unstructured text or document columns using LLM-powered functions. Users can express an operation in natural language (e.g., "identify if this review mentions billing issues"), with the system executing the operation on each document, in a row-by-row fashion. One way to reduce...
Video-based Person Re-IDentification (VPReID) aims to retrieve the same person from videos captured by non-overlapping cameras. At extreme far distances, VPReID is highly challenging due to severe resolution degradation, drastic viewpoint variation and inevitable appearance noise. To address these issues, we propose a Scale-Adaptive...
Blockchain is a decentralized, distributed ledger technology that ensures transparency, security, and immutability through cryptographic techniques. However, advancements in quantum computing threaten the security of classical cryptographic schemes, jeopardizing blockchain integrity once cryptographic quantum supremacy is achieved....
This paper presents a novel approach to learning from demonstration that enables robots to autonomously execute complex tasks in dynamic environments. We model latent tasks as probabilistic formal languages and introduce a tailored reactive synthesis framework that balances robot costs with user task preferences. Our methodology...
We present a new kinetic equation for cell migration driven by mechanical interactions with the substrate, an effect not previously captured in kinetic models, and essential for explaining observed collective behaviors such as those in bacterial colonies. The model introduces an acceleration term that accounts for the dynamics of...
The integration of cryptocurrencies into institutional portfolios necessitates the adoption of robust risk modeling frameworks. This study is a part of a series of subsequent works to fine-tune model risk analysis for cryptocurrencies. Through this first research work, we establish a foundational benchmark by applying the traditional...
Tokenization sits at the boundary between high-throughput genomic input and GPU compute, posing challenges in both algorithm design and system throughput. Overlapping k-mer tokenization can introduce information leakage under masked language modeling (MLM) and may degrade downstream accuracy. Single-nucleotide tokenization avoids...
Bug severity prediction is important in software maintenance, because it helps the development teams to prioritize bugs that have a significant impact on the operation, stability and security of the system. In large software projects bug repositories will grow at very rapid rate making classification of severity manual work labourious...
We present theoretical predictions for the transverse-momentum distribution of $J/ψ$ produced within jets at the upcoming Electron-Ion Collider (EIC). Utilizing the semi-inclusive fragmenting jet function (FJF) framework, our calculation achieves next-to-leading order (NLO) accuracy in the strong coupling and leading-logarithmic (LL)...
High success rates on navigation-related tasks do not necessarily translate into reliable decision making by foundation models. To examine this gap, we evaluate current models on six diagnostic tasks spanning three settings: reasoning under complete spatial information, reasoning under incomplete spatial information, and reasoning...
This paper examines the relationship between Official Development Assistance (ODA) and conflict in the ten largest aid-receiving African countries between 2009 and 2023. Using Ordinary Least Squares, Principal Component Analysis, and Ridge (L2) regression, the study assesses whether conflict, proxied by political stability, governance...
Combinatorial materials libraries are an efficient route to generate large families of candidate compositions, but their impact is often limited by the speed and depth of characterization and by the difficulty of extracting actionable structure-property relations from complex characterization data. Here we develop an autonomous...
Post-acute sequelae of SARS-CoV-2 infection (Long COVID) frequently persists for months, yet drivers of clinical remission remain incompletely defined. Here we analyzed 97,564 longitudinal PASC assessments from 13,511 participants with linked vaccination histories to disentangle passive temporal progression from vaccine-associated...
Accurate and efficient multivariate time series (MTS) analysis is increasingly critical for a wide range of intelligent applications. Within this realm, Transformers have emerged as the predominant architecture due to their strong ability to capture pairwise dependencies. However, Transformer-based models suffer from quadratic...
The rapid adoption of LLMs has increased the need for reliable AI text detection, yet existing detectors often fail outside controlled benchmarks. We systematically evaluate 2 dominant paradigms (training-free and supervised) and show that both are brittle under distribution shift, unseen generators, and simple stylistic...