Research

Papers

Research papers from arXiv and related sources

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

UniScale: Synergistic Entire Space Data and Model Scaling for Search Ranking

Recent advances in Large Language Models (LLMs) have inspired a surge of scaling law research in industrial search, advertising, and recommendation systems. However, existing approaches focus mainl...

Liren Yu, Caiyuan Li, Feiyi Dong, Tao Zhang, Zhixuan Zhang, Dan Ou, Haihong Tang, Bo Zheng

2603.24226 2026-03-25
AI LLM

RVLM: Recursive Vision-Language Models with Adaptive Depth

Medical AI systems face two fundamental limitations. First, conventional vision-language models (VLMs) perform single-pass inference, yielding black-box predictions that cannot be audited or explai...

Nicanor Mayumu, Zeenath Khan, Melodena Stephens, Patrick Mukala, Farhad Oroumchian

2603.24224 2026-03-25
TESTING

Variation is the Norm: Embracing Sociolinguistics in NLP

In Natural Language Processing (NLP), variation is typically seen as noise and "normalised away" before processing, even though it is an integral part of language. Conversely, studying language var...

Anne-Marie Lutgen, Alistair Plum, Verena Blaschke, Barbara Plank, Christoph Purschke

2603.24222 2026-03-25
AI LLM

Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testing

The increasing complexity and interconnectivity of digital infrastructures make scalable and reliable security assessment methods essential. Robotic systems represent a particularly important class...

Michael Somma, Markus Großpointner, Paul Zabalegui, Eppu Heilimo, Branka Stojanović

2603.24221 2026-03-25
AI LLM

Who Benefits from RAG? The Role of Exposure, Utility and Attribution Bias

Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have achieved substantial improvements in accuracy by grounding their responses in external documents that are releva...

Mahdi Dehghan, Graham McDonald

2603.24218 2026-03-25
AI LLM

Where Do Your Citations Come From? Citation-Constellation: A Free, Open-Source, No-Code, and Auditable Tool for Citation Network Decomposition with Complementary BARON and HEROCON Scores

Standard citation metrics treat all citations as equal, obscuring the social and structural pathways through which scholarly influence propagates. I introduce Citation-Constellation, a freely avail...

Mahbub Ul Alam

2603.24216 2026-03-25
AI LLM

Powerful Teachers Matter: Text-Guided Multi-view Knowledge Distillation with Visual Prior Enhancement

Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies, they often overl...

Xin Zhang, Jianyang Xu, Hao Peng, Dongjing Wang, Jingyuan Zheng, Yu Li, Yuyu Yin, Hongbo Wang

2603.24208 2026-03-25
AI LLM

SumRank: Aligning Summarization Models for Long-Document Listwise Reranking

Large Language Models (LLMs) have demonstrated superior performance in listwise passage reranking task. However, directly applying them to rank long-form documents introduces both effectiveness and...

Jincheng Feng, Wenhan Liu, Zhicheng Dou

2603.24204 2026-03-25
AI LLM

Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search

Recent advances in the Model Context Protocol (MCP) have enabled large language models (LLMs) to invoke external tools with unprecedented ease. This creates a new class of powerful and tool augment...

Yulin Shen, Xudong Pan, Geng Hong, Min Yang

2603.24203 2026-03-25
AI LLM

The First Generation of AI-Assisted Programming Learners: Gendered Patterns in Critical Thinking and AI Ethics of German Secondary School Students

The first generation of students is learning to program alongside GenAI (Generative Artificial Intelligence) tools, raising questions about how young learners critically engage with them and percei...

Isabella Graßl

2603.24197 2026-03-25
AI LLM

Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection

Current Large Vision Language Models (LVLMs) excel at many zero-shot tasks like image captioning, visual question answering and OCR. However, these same models suffer from poor performance at image...

Adhemar de Senneville, Xavier Bou, Jérémy Anger, Rafael Grompone, Gabriele Facciolo

2603.24181 2026-03-25
TESTING

Refractive multi-conjugate adaptive optics for wide-field atmospheric turbulence correction

Multi-Conjugate Adaptive Optics (MCAO) is essential for increasing the corrected Field-of-View (FoV) in astronomical imaging and potentially for free-space optical communications, particularly for ...

Tommaso Furieri, Stefano Bonora

2603.24174 2026-03-25
TESTING

Walma: Learning to See Memory Corruption in WebAssembly

WebAssembly's (Wasm) monolithic linear memory model facilitates memory corruption attacks that can escalate to cross-site scripting in browsers or go undetected when a malicious host tampers with a...

Oussama Draissi, Mark Günzel, Ahmad-Reza Sadeghi, Lucas Davi

2603.24167 2026-03-25
AI LLM

Towards Automated Crowdsourced Testing via Personified-LLM

The rapid proliferation and increasing complexity of software demand robust quality assurance, with graphical user interface (GUI) testing playing a pivotal role. Crowdsourced testing has proven ef...

Shengcheng Yu, Yuchen Ling, Chunrong Fang, Zhenyu Chen, Chunyang Chen

2603.24160 2026-03-25
TESTING

The Geometry of Risk: Path-Dependent Regulation and Anticipatory Hedging via the SigSwap

This paper introduces a transformative framework for managing path-dependent financial risk by shifting from traditional distribution-centric models to a geometry-based approach. We propose the Sig...

Daniel Bloch

2603.24154 2026-03-25
TESTING

On the explicit formula linking a function to the order of its fractional derivative

In this paper, given a certain regularity of a function $v$, we derive an explicit formula relating the order $ν_0\in(0,1)$ of the leading fractional derivative in a fractional differential operato...

Vasyl Semenov, Nataliya Vasylyeva

2603.24149 2026-03-25
AI LLM

Linking Global Science Funding to Research Publications

Funding acknowledgments in scholarly publications provide large-scale trace data on organizations that support scientific research. We present a dataset for linking global science funding organizat...

Jacob Aarup Dalsgaard, Filipi Nascimento Silva, Jin AI

2603.24147 2026-03-25
AI LLM

Semantic-Aware Interruption Detection in Spoken Dialogue Systems: Benchmark, Metric, and Model

Achieving natural full-duplex interaction in spoken dialogue systems (SDS) remains a challenge due to the difficulty of accurately detecting user interruptions. Current solutions are polarized betw...

Kangxiang Xia, Bingshen Mu, Xian Shi, Jin Xu, Lei Xie

2603.24144 2026-03-25
TESTING

Linear-Nonlinear Fusion Neural Operator for Partial Differential Equations

Neural operator learning directly constructs the mapping relationship from the equation parameter space to the solution space, enabling efficient direct inference in practical applications without ...

Heng Wu, Junjie Wang, Benzhuo Lu

2603.24143 2026-03-25
AI LLM

Sequence-aware Large Language Models for Explainable Recommendation

Large Language Models (LLMs) have shown strong potential in generating natural language explanations for recommender systems. However, existing methods often overlook the sequential dynamics of use...

Gangyi Zhang, Runzhe Teng, Chongming Gao

2603.24136 2026-03-25