Research

Papers

Research papers from arXiv and related sources

Total: 4513 AI/LLM: 2483 Testing: 2030
TESTING

AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks

Automating garment assembly from sewing patterns remains a significant challenge due to the lack of standardized annotation protocols and the frequent absence of semantic cues. Existing methods oft...

Pablo Ríos-Navarro, Elena Garces, Jorge Lopez-Moreno

2602.22052 2026-02-25
TESTING

SPGen: Stochastic scanpath generation for paintings using unsupervised domain adaptation

Understanding human visual attention is key to preserving cultural heritage We introduce SPGen a novel deep learning model to predict scanpaths the sequence of eye movementswhen viewers observe pai...

Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, Alessandro Bruno

2602.22049 2026-02-25
TESTING

IGR J12580+0134: A Candidate for Repeating Partial Tidal Disruption Events Supported by Multi-Wavelength Observations

Repeating partial tidal disruption events (pTDEs) provide a direct probe of stellar orbits and episodic mass loss around supermassive black holes, but robust identification requires multi-band and ...

Po Ma, Shao-Yu Fu, Linhui Wu, Wei-Hua Lei, Qiang Yuan

2602.22040 2026-02-25
TESTING

Ab initio calculations of nuclear charge radii across and beyond ${}^{132}$Sn: Putting chiral EFT nuclear interactions to the test

Charge radii are investigated along the Tin isotopic chain via ab initio Bogoliubov coupled cluster calculations at the singles and doubles level. In addition to the reproduction of absolute radii,...

Pepijn Demol, Urban Vernik, Thomas Duguet, Alexander Tichai

2602.22030 2026-02-25
AI LLM

RGB-Event HyperGraph Prompt for Kilometer Marker Recognition based on Pre-trained Foundation Models

Metro trains often operate in highly complex environments, characterized by illumination variations, high-speed motion, and adverse weather conditions. These factors pose significant challenges for...

Xiaoyu Xian, Shiao Wang, Xiao Wang, Daxin Tian, Yan Tian

2602.22026 2026-02-25
AI LLM

Detecting UX smells in Visual Studio Code using LLMs

Integrated Development Environments shape developers' daily experience, yet the empirical study of their usability and user experience (UX) remains limited. This work presents an LLM-assisted appro...

Andrés Rodriguez, Juan Cruz Gardey, Alejandra Garrido

2602.22020 2026-02-25
AI LLM

IOAgent: Democratizing Trustworthy HPC I/O Performance Diagnosis Capability via LLMs

As the complexity of the HPC storage stack rapidly grows, domain scientists face increasing challenges in effectively utilizing HPC storage systems to achieve their desired I/O performance. To iden...

Chris Egersdoerfer, Arnav Sareen, Jean Luca Bez, Suren Byna, Dongkuan, Xu, Dong Dai

2602.22017 2026-02-25
AI LLM

Are Foundation Models the Route to Full-Stack Transfer in Robotics?

In humans and robots alike, transfer learning occurs at different levels of abstraction, from high-level linguistic transfer to low-level transfer of motor skills. In this article, we provide an ov...

Freek Stulp, Samuel Bustamante, João Silvério, Alin Albu-Schäffer, Jeannette Bohg, Shuran Song

2602.22001 2026-02-25
AI LLM

The Governance of Intimacy: A Preliminary Policy Analysis of Romantic AI Platforms

Romantic AI platforms invite intimate emotional disclosure, yet their data governance practices remain underexamined. This preliminary study analyses the Privacy Policies and Terms of Service of si...

Xiao Zhan, Yifan Xu, Rongjun Ma, Shijing He, Jose Luis Martin-Navarro, Jose Such

2602.22000 2026-02-25
AI LLM

Enhancing LLM-Based Test Generation by Eliminating Covered Code

Automated test generation is essential for software quality assurance, with coverage rate serving as a key metric to ensure thorough testing. Recent advancements in Large Language Models (LLMs) hav...

WeiZhe Xu, Mengyu Liu, Fanxin Kong

2602.21997 2026-02-25
AI LLM

CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models

Recent work has examined language models from a linguistic perspective to better understand how they acquire language. Most existing benchmarks focus on judging grammatical acceptability, whereas t...

Miyu Oba, Saku Sugawara

2602.21978 2026-02-25
AI LLM

When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters

Low-Rank Adaptation (LoRA) has emerged as a leading technique for efficiently fine-tuning text-to-image diffusion models, and its widespread adoption on open-source platforms has fostered a vibrant...

Liangwei Lyu, Jiaqi Xu, Jianwei Ding, Qiyao Deng

2602.21977 2026-02-25
TESTING

How does a MOND cosmology fare on Gpc scales? - Collisionless $N$-body simulations of $ν$HDM

We present the largest collisionless $N$-body cosmological simulations in a MOdified Newtonian Dynamics (MOND) cosmology to date. Our 4 simulations cover $Λ$CDM as a baseline, a MOND with hot dark ...

Alfie Russell, Indranil Banik, Oscar Cray, Hongsheng Zhao

2602.21975 2026-02-25
TESTING

Estimation of the complexity of a network under a Gaussian graphical model

The proportion of edges in a Gaussian graphical model (GGM) characterizes the complexity of its conditional dependence structure. Since edge presence corresponds to a nonzero entry of the precision...

Nabaneet Das, Thorsten Dickhaus

2602.21969 2026-02-25
TESTING

Global-Aware Edge Prioritization for Pose Graph Initialization

The pose graph is a core component of Structure-from-Motion (SfM), where images act as nodes and edges encode relative poses. Since geometric verification is expensive, SfM pipelines restrict the p...

Tong Wei, Giorgos Tolias, Jiri Matas, Daniel Barath

2602.21963 2026-02-25
AI LLM

Estimation and Optimization of Ship Fuel Consumption in Maritime: Review, Challenges and Future Directions

To reduce carbon emissions and minimize shipping costs, improving the fuel efficiency of ships is crucial. Various measures are taken to reduce the total fuel consumption of ships, including optimi...

Dusica Marijan, Hamza Haruna Mohammed, Bakht Zaman

2602.21959 2026-02-25
TESTING

Detecting Logic Bugs of Join Optimizations in DBMS

Generation-based testing techniques have shown their effectiveness in detecting logic bugs of DBMS, which are often caused by improper implementation of query optimizers. Nonetheless, existing gene...

Xiu Tang, Sai Wu, Dongxiang Zhang, Feifei Li, Gang Chen

2602.21955 2026-02-25
AI LLM

RADAR: Reasoning as Discrimination with Aligned Representations for LLM-based Knowledge Graph Reasoning

Knowledge graph reasoning (KGR) infers missing facts, with recent advances increasingly harnessing the semantic priors and reasoning abilities of Large Language Models (LLMs). However, prevailing g...

Bo Xue, Yuan Jin, Luoyi Fu, Jiaxin Ding, Xinbing Wang

2602.21951 2026-02-25
AI LLM

Large Language Models are Algorithmically Blind

Large language models (LLMs) demonstrate remarkable breadth of knowledge, yet their ability to reason about computational processes remains poorly understood. Closing this gap matters for practitio...

Sohan Venkatesh, Ashish Mahendran Kurapath, Tejas Melkote

2602.21947 2026-02-25
AI LLM

Hidden Topics: Measuring Sensitive AI Beliefs with List Experiments

How can researchers identify beliefs that large language models (LLMs) hide? As LLMs become more sophisticated and the prevalence of alignment faking increases, combined with their growing integrat...

Maxim Chupilkin

2602.21939 2026-02-25