Research

Papers

Research papers from arXiv and related sources

Total: 4694 AI/LLM: 2583 Testing: 2111
TESTING

Pairwise Negative Correlation for Uniform Spanning Subgraphs of the Complete Graph

We investigate the pairwise negative correlation (p-NC) property for uniform probability measures on several families of spanning subgraphs of the complete graph $K_n$. Motivated by conjectured neg...

Pengfei Tang, Zibo Zhang

2603.10738 2026-03-11
AI LLM

CacheSolidarity: Preventing Prefix Caching Side Channels in Multi-tenant LLM Serving Systems

Large Language Models (LLMs) rely on optimizations like Automatic Prefix Caching (APC) to accelerate inference. APC works by reusing previously computed states for the beginning part of a request (...

Panagiotis Georgios Pennas, Konstantinos Papaioannou, Marco Guarnieri, Thaleia Dimitra Doudali

2603.10726 2026-03-11
TESTING

Probabilistic Verification of Voice Anti-Spoofing Models

Recent advances in generative models have amplified the risk of malicious misuse of speech synthesis technologies, enabling adversaries to impersonate target speakers and access sensitive resources...

Evgeny Kushnir, Alexandr Kozodaev, Dmitrii Korzh, Mikhail Pautov, Oleg Kiriukhin, Oleg Y. Rogov

2603.10713 2026-03-11
AI LLM

Believing vs. Achieving -- The Disconnect between Efficacy Beliefs and Collaborative Outcomes

As artificial intelligence (AI) becomes increasingly integrated into workflows, humans must decide when to rely on AI advice. These decisions depend on general efficacy beliefs, i.e., humans' confi...

Philipp Spitzer, Joshua Holstein

2603.10708 2026-03-11
TESTING

Hybrid Photonic Quantum Reservoir Computing for High-Dimensional Financial Surface Prediction

We propose a hybrid photonic quantum reservoir computing (QRC) framework for swaption surface prediction. The pipeline compresses 224-dimensional surfaces to a 20-dimensional latent space via a spa...

Fyodor Amanov, Azamkhon Azamov

2603.10707 2026-03-11
TESTING

Thermodynamic Non-Uniformities Behind Incident and Reflected Shocks in a Single-Diaphragm Shock Tube

Shock tubes provide well-controlled high-temperature and high-pressure conditions for chemical kinetics studies, yet the region behind the reflected shock is seldom perfectly homogeneous. Axial and...

Touqeer Anwar Kashif, Janardhanraj Subburaj, Aamir Farooq

2603.10706 2026-03-11
AI LLM

Prism-$Δ$: Differential Subspace Steering for Prompt Highlighting in Large Language Models

Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge is extracting steering directions that capture the difference between re...

Yuyao Ge, Shenghua Liu, Yiwei Wang, Tianyu Liu, Baolong Bi, Lingrui Mei, Jiayu Yao, Jiafeng Guo, ...

2603.10705 2026-03-11
AI LLM

Structured Linked Data as a Memory Layer for Agent-Orchestrated Retrieval

Retrieval-Augmented Generation (RAG) systems typically treat documents as flat text, ignoring the structured metadata and linked relationships that knowledge graphs provide. In this paper, we inves...

Andrea Volpini, Elie Raad, Beatrice Gamba, David Riccitelli

2603.10700 2026-03-11
AI LLM

EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution

Neural text-to-SQL models, which translate natural language questions (NLQs) into SQL queries given a database schema, have achieved remarkable performance. However, database schemas frequently evo...

Tianshu Zhang, Kun Qian, Siddhartha Sahai, Yuan Tian, Shaddy Garg, Huan Sun, Yunyao Li

2603.10697 2026-03-11
TESTING

RandMark: On Random Watermarking of Visual Foundation Models

Being trained on large and diverse datasets, visual foundation models (VFMs) can be fine-tuned to achieve remarkable performance and efficiency in various downstream computer vision tasks. The high...

Anna Chistyakova, Mikhail Pautov

2603.10695 2026-03-11
TESTING

Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learning

While Secure Aggregation (SA) protects update confidentiality in Cross-silo Federated Learning, it fails to guarantee aggregation integrity, allowing malicious servers to silently omit or tamper wi...

Xian Qin, Xue Yang, Xiaohu Tang

2603.10692 2026-03-11
TESTING

Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model?

Black-box adversarial attacks are widely used as tools to test the robustness of deep neural networks against malicious perturbations of input data aimed at a specific change in the output of the m...

Anna Chistyakova, Mikhail Pautov

2603.10689 2026-03-11
TESTING

Investigations of Heterogeneity in Diagnostic Test Accuracy Meta-Analysis: A Methodological Review

Background: Subgroup analyses and meta-regression are commonly used to investigate heterogeneity in diagnostic test accuracy (DTA) meta-analyses (MA), but adherence to methodological guidance is un...

Lukas Mischinger, Angela Ernst, Bernhard Haller, Alexey Formenko, Zekeriya Aktuerk, Alexander Hap...

2603.10686 2026-03-11
AI LLM

A Platform-Agnostic Multimodal Digital Human Modelling Framework: Neurophysiological Sensing in Game-Based Interaction

Digital Human Modelling (DHM) is increasingly shaped by advances in AI, wearable biosensing, and interactive digital environments, particularly in research addressing accessibility and inclusion. H...

Daniel J. Buxton, Mufti Mahmud, Jordan J. Bird, Thomas Hughes-Roberts, David J. Brown

2603.10680 2026-03-11
AI LLM

From Education to Evidence: A Collaborative Practice Research Platform for AI-Integrated Agile Development

Agile software development evolves so rapidly that research struggles to remain timely and transferable - an issue heightened by the swift adoption of generative AI and agentic tools. Earlier discu...

Tobias Geger, Andreas Rausch, Ina Schiering, Frauke Stenzel, Stefan Wittek

2603.10679 2026-03-11
TESTING

Surrogate models for nuclear fusion with parametric Shallow Recurrent Decoder Networks: applications to magnetohydrodynamics

Magnetohydrodynamic (MHD) effects play a key role in the design and operation of nuclear fusion systems, where electrically conducting fluids (such as liquid metals or molten salts in reactor blank...

M. Lo Verso, C. Introini, E. Cervi, L. Savoldi, J. N. Kutz, A. Cammi

2603.10678 2026-03-11
AI LLM

Emulating Clinician Cognition via Self-Evolving Deep Clinical Research

Clinical diagnosis is a complex cognitive process, grounded in dynamic cue acquisition and continuous expertise accumulation. Yet most current artificial intelligence (AI) systems are misaligned wi...

Ruiyang Ren, Yuhao Wang, Yunsen Liang, Lan Luo, Jing Liu, Haifeng Wang, Cong Feng, Yinan Zhang, C...

2603.10677 2026-03-11
TESTING

Conformal prediction for high-dimensional functional time series: Applications to subnational mortality

In statistics, forecast uncertainty is often quantified using a specified statistical model, though such approaches may be vulnerable to model misspecification, selection bias, and limited finite-s...

Han Lin Shang

2603.10674 2026-03-11
AI LLM

Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation

Recent advances in large language models (LLMs) have stimulated growing interest in agent-based recommender systems, enabling language-driven interaction and reasoning for more expressive preferenc...

Yaxin Gong, Chongming Gao, Chenxiao Fan, Wenjie Wang, Fuli Feng, Xiangnan He

2603.10673 2026-03-11
AI LLM

Terminal Is All You Need: Design Properties for Human-AI Agent Collaboration

While research on AI agents focuses on enabling them to operate graphical user interfaces, the most effective and widely adopted agent tools in practice are terminal-based. We argue that this conve...

Alexandre De Masi

2603.10664 2026-03-11