Research

Papers

Research papers from arXiv and related sources

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

Compartmentalization-Aware Automated Program Repair

Software compartmentalization breaks down an application into compartments isolated from each other: an attacker taking over a compartment will be confined to it, limiting the damage they can cause...

Jia Hu, Youcheng Sun, Pierre Olivier

2603.09544 2026-03-10
AI LLM

Dynamic Multimodal Expression Generation for LLM-Driven Pedagogical Agents: From User Experience Perspective

In virtual reality (VR) educational scenarios, Pedagogical agents (PAs) enhance immersive learning through realistic appearances and interactive behaviors. However, most existing PAs rely on static...

Ninghao Wan, Jiarun Song, Fuzheng Yang

2603.09536 2026-03-10
TESTING

CTPX1: A Highly Integrated and High-Throughput Data-Driven Camera Based on Timepix4

The upgrade of the China Spallation Neutron Source (CSNS-II) will raise the proton beam power to 500 kW. Consequently, the existing Timepix3-based detector systems, limited to a count rate of 80 Mh...

Qicai Li, Hongbin Liu, Xingfen Jiang, Jianrong Zhou, Yujie Zhou, Haoran Guo, Dongcheng Cai, Weile...

2603.09534 2026-03-10
AI LLM

Enhancing Debunking Effectiveness through LLM-based Personality Adaptation

This study proposes a novel methodology for generating personalized fake news debunking messages by prompting Large Language Models (LLMs) with persona-based inputs aligned to the Big Five personal...

Pietro Dell'Oglio, Alessandro Bondielli, Francesco Marcelloni, Lucia C. Passaro

2603.09533 2026-03-10
AI LLM

Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation

Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft models for every...

Luxi Lin, Zhihang Lin, Zhanpeng Zeng, Yuhao Chen, Qingyu Zhang, Jixiang Luo, Xuelong Li, Rongrong Ji

2603.09527 2026-03-10
AI LLM

You Didn't Have to Say It like That: Subliminal Learning from Faithful Paraphrases

When language models are trained on synthetic data, they (student model) can covertly acquire behavioral traits from the data-generating model (teacher model). Subliminal learning refers to the tra...

Isaia Gisler, Zhonghao He, Tianyi Qiu

2603.09517 2026-03-10
AI LLM

Beyond Short-Horizon: VQ-Memory for Robust Long-Horizon Manipulation in Non-Markovian Simulation Benchmarks

The high cost of collecting real-robot data has made robotic simulation a scalable platform for both evaluation and data generation. Yet most existing benchmarks concentrate on simple manipulation ...

Wang Honghui, Jing Zhi, Ao Jicong, Song Shiji, Li Xuelong, Huang Gao, Bai Chenjia

2603.09513 2026-03-10
TESTING

Backward problem for a degenerate viscous Hamilton-Jacobi equation: stability and numerical identification

This work is devoted to the analysis of the backward problem for a viscous Hamilton-Jacobi equation with degenerate diffusion and a general Hamiltonian that is not necessarily quadratic. First, we ...

S. E. Chorfi, A. Habbal, M. Jahid, L. Maniar, A. Ratnani

2603.09509 2026-03-10
TESTING

Context-Nav: Context-Driven Exploration and Viewpoint-Aware 3D Spatial Reasoning for Instance Navigation

Text-goal instance navigation (TGIN) asks an agent to resolve a single, free-form description into actions that reach the correct object instance among same-category distractors. We present \textit...

Won Shik Jang, Ue-Hwan Kim

2603.09506 2026-03-10
TESTING

Avoiding Big Integers: Parallel Multimodular Algebraic Verification of Arithmetic Circuits

Word-level verification of arithmetic circuits with large operands typically relies on arbitrary-precision arithmetic, which can lead to significant computational overhead as word sizes grow. In th...

Clemens Hofstadler, Daniela Kaufmann, Chen Chen

2603.09501 2026-03-10
TESTING

Development of Readout Electronics for a High-Speed Event-Driven Neutron Imaging Detector Based on Timepix4

As the Chinese Spallation Neutron Source enters Phase II, the increase in proton beam power will lead to a further boost in the intensity of pulsed neutron beams. To address the demand for higher e...

Qicai Li, Hongbin Liu, Dongcheng Cai, Haoran Guo, Xingfen Jiang, Haiyun Teng, Kai Wang, Xiuku Wan...

2603.09499 2026-03-10
AI LLM

EmbC-Test: How to Speed Up Embedded Software Testing Using LLMs and RAG

Manual development of automatic tests for embedded C software is a strenuous and time-consuming task that does not scale well. With the accelerating pace of software release cycles, verification in...

Maximilian Harnot, Sebastian Komarnicki, Michal Polok, Timo Oksanen

2603.09497 2026-03-10
AI LLM

Evolving Prompt Adaptation for Vision-Language Models

The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. While parameter-efficient prompt learning methods offer a ...

Enming Zhang, Jiayang Li, Yanru Wu, Zhenyu Liu, Yang Li

2603.09493 2026-03-10
AI LLM

Vibe-Creation: The Epistemology of Human-AI Emergent Cognition

The encounter between human reasoning and generative artificial intelligence (GenAI) cannot be adequately described by inherited metaphors of tool use, augmentation, or collaborative partnership. T...

Ilya Levin

2603.09486 2026-03-10
AI LLM

GenePlan: Evolving Better Generalized PDDL Plans using Large Language Models

We present GenePlan (GENeralized Evolutionary Planner), a novel framework that leverages large language model (LLM) assisted evolutionary algorithms to generate domain-dependent generalized planner...

Andrew Murray, Danial Dervovic, Alberto Pozanco, Michael Cashmore

2603.09481 2026-03-10
TESTING

Enhanced security in Quantum Token protocols using Hybrid Spin-Photon Interfaces

Quantum token protocols enable unforgeable quantum tokens promising unconditional security beyond classical cryptographic assumptions. We show here that the three stages of the Quantum token protoc...

Durga Bhaktavatsala Rao Dasari, Yang Wang, Jörg Wrachtrup

2603.09479 2026-03-10
TESTING

OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks

Vision-Language Models (VLMs) have demonstrated effective perception and reasoning capabilities on general-domain tasks, leading to growing interest in their application to Earth observation. Howev...

Ronghao Fu, Haoran Liu, Weijie Zhang, Zhiwen Lin, Xiao Yang, Peng Zhang, Bo Yang

2603.09471 2026-03-10
AI LLM

The Patrologia Graeca Corpus: OCR, Annotation, and Open Release of Noisy Nineteenth-Century Polytonic Greek Editions

We present the Patrologia Graeca Corpus, the first large-scale open OCR and linguistic resource for nineteenthcentury editions of Ancient Greek. The collection covers the remaining undigitized volu...

Chahan Vidal-Gorène, Bastien Kindt

2603.09470 2026-03-10
AI LLM

TopoOR: A Unified Topological Scene Representation for the Operating Room

Surgical Scene Graphs abstract the complexity of surgical operating rooms (OR) into a structure of entities and their relations, but existing paradigms suffer from strictly dyadic structural limita...

Tony Danjun Wang, Ka Young Kim, Tolga Birdal, Nassir Navab, Lennart Bastian

2603.09466 2026-03-10
AI LLM

An Empirical Study and Theoretical Explanation on Task-Level Model-Merging Collapse

Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we observe that mergi...

Yuan Cao, Dezhi Ran, Yuzhe Guo, Mengzhou Wu, Simin Chen, Linyi Li, Wei Yang, Tao Xie

2603.09463 2026-03-10