Research

Papers

Research papers from arXiv and related sources

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

Local Shapley: Model-Induced Locality and Optimal Reuse in Data Valuation

The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space. Existing accelerations remain global and ignore a str...

Xuan Yang, Hsi-Wen Chen, Ming-Syan Chen, Jian Pei

2603.03672 2026-03-04
TESTING

InEdit-Bench: Benchmarking Intermediate Logical Pathways for Intelligent Image Editing Models

Multimodal generative models have made significant strides in image editing, demonstrating impressive performance on a variety of static tasks. However, their proficiency typically does not extend ...

Zhiqiang Sheng, Xumeng Han, Zhiwei Zhang, Zenghui Xiong, Yifan Ding, Aoxiang Ping, Xiang Li, Tong...

2603.03657 2026-03-04
TESTING

Exploring Multiple Converged States of Network Configurations

Due to the policy-rich BGP, multiple stable forwarding states might exist for the same network topology and configuration, rendering the network convergence non-deterministic. This paper proves tha...

Shunyu Yang, Dan Wang, Peng Zhang

2603.03638 2026-03-04
TESTING

Empirical Evaluation of No Free Lunch Violations in Permutation-Based Optimization

The No Free Lunch (NFL) theorem guarantees equal average performance only under uniform sampling of a function space closed under permutation (c.u.p.). We ask when this averaging ceases to reflect ...

Grzegorz Sroka

2603.03613 2026-03-04
TESTING

Tracking Feral Horses in Aerial Video Using Oriented Bounding Boxes

The social structures of group-living animals such as feral horses are diverse and remain insufficiently understood, even within a single species. To investigate group dynamics, aerial videos are o...

Saeko Takizawa, Tamao Maeda, Shinya Yamamoto, Hiroaki Kawashima

2603.03604 2026-03-04
TESTING

SENTINEL: Stagewise Integrity Verification for Pipeline Parallel Decentralized Training

Decentralized training introduces critical security risks when executed across untrusted, geographically distributed nodes. While existing Byzantine-tolerant literature addresses data parallel (DP)...

Hadi Mohaghegh Dolatabadi, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Chamin P Hewa Koneputugod...

2603.03592 2026-03-03
TESTING

Mutation Rate Variation Across Genomic Regions in \textit{Arabidopsis thaliana}

In population genetics, mutation rate is often treated as a homogeneous parameter across the genome. Empirical evidence, however, shows systematic variation across genomic contexts associated with ...

Elisa Heinrich-Mora, Marcus W. Feldman

2603.03591 2026-03-03
TESTING

Safety-Centered Scenario Generation for Autonomous Vehicles

This paper presents a scenario generation framework that creates diverse, parametrized, and safety-critical driving situations to validate the safety features of autonomous vehicles in simulation ...

Kiruthiga Chandra Shekar, Aliasghar Moj Arab

2603.03574 2026-03-03
TESTING

A Pathway Selection Process for Dynamically Self-Organizing Systems

Self-organization creates new order and shifts sub-boundaries while reorganizing energy and entropy within a control volume. This article examines pathway selection and tests whether maximizing the...

J. A. Sekhar

2603.03557 2026-03-03
TESTING

PinCLIP: Large-scale Foundational Multimodal Representation at Pinterest

While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems remains a challenge, ...

Josh Beal, Eric Kim, Jinfeng Rao, Rex Wu, Dmitry Kislyuk, Charles Rosenberg

2603.03544 2026-03-03
TESTING

Passive Phase-Oriented Impedance Shaping for Rapid Acceleration in Soft Robotic Swimmers

Rapid acceleration and burst maneuvers in underwater robots depend less on maintaining precise resonance and more on force--velocity phase alignment during thrust generation. In this work, we inves...

Qimin Feng, Orion A. Roberts, Qiang Zhong

2603.03537 2026-03-03
TESTING

Test-Time Meta-Adaptation with Self-Synthesis

As strong general reasoners, large language models (LLMs) encounter diverse domains and tasks, where the ability to adapt and self-improve at test time is valuable. We introduce MASS, a meta-learni...

Zeyneb N. Kaya, Nick Rui

2603.03524 2026-03-03
TESTING

Most open clusters follow the radial acceleration relation (RAR) and the baryonic Tully-Fisher relation (BTFR)

We test whether parsec-scale stellar systems in the Milky Way follow the galactic radial acceleration relation (RAR) or the baryonic TullyFisher relation (BTFR). We analyse 5646 Gaia DR3 open clust...

Mark D. Huisjes, X. Hernandez

2603.03522 2026-03-03
TESTING

Baseline Performance of AI Tools in Classifying Cognitive Demand of Mathematical Tasks

Teachers face increasing demands on their time, particularly in adapting mathematics curricula to meet individual student needs while maintaining cognitive rigor. This study evaluates whether AI to...

Danielle S. Fox, Brenda L. Robles, Elizabeth DiPietro Brovey, Christian D. Schunn

2603.03512 2026-03-03
TESTING

FusionCut: Boundary Representation (B-Rep) Based and Cloud-Ready Cutter Workpiece Engagement (CWE) for Virtual Machining

Cutter-workpiece engagement (CWE) is the instantaneous contact geometry between the cutter and the in-process workpiece, playing a fundamental role in machining process simulation and directly affe...

H. Sinan Bank, N. Bircan Bugdayci

2603.03504 2026-03-03
TESTING

Navigating in Uncertain Environments with Heterogeneous Visibility

Navigating an environment with uncertain connectivity requires a strategic balance between minimizing the cost of traversal and seeking information to resolve map ambiguities. Unlike previous appro...

Jongann Lee, Melkior Ornik

2603.03495 2026-03-03
TESTING

When Small Variations Become Big Failures: Reliability Challenges in Compute-in-Memory Neural Accelerators

Compute-in-memory (CiM) architectures promise significant improvements in energy efficiency and throughput for deep neural network acceleration by alleviating the von Neumann bottleneck. However, t...

Yifan Qin, Jiahao Zheng, Zheyu Yan, Wujie Wen, Xiaobo Sharon Hu, Yiyu Shi

2603.03491 2026-03-03
TESTING

DKD-KAN: A Lightweight knowledge-distilled KAN intrusion detection framework, based on MLP and KAN

Cyber-security systems often operate in resource-constrained environments, such as edge environments and real-time monitoring systems, where model size and inference time are crucial. A light-weigh...

Mohammad Alikhani

2603.03486 2026-03-03
TESTING

The PARLO Dementia Corpus: A German Multi-Center Resource for Alzheimer's Disease

Early and accessible detection of Alzheimer's disease (AD) remains a major challenge, as current diagnostic methods often rely on costly and invasive biomarkers. Speech and language analysis has em...

Franziska Braun, Christopher Witzl, Florian Hönig, Elmar Nöth, Tobias Bocklet, Korbinian Riedhammer

2603.03471 2026-03-03
TESTING

Biased Generalization in Diffusion Models

Generalization in generative modeling is defined as the ability to learn an underlying distribution from a finite dataset and produce novel samples, with evaluation largely driven by held-out perfo...

Jerome Garnier-Brun, Luca Biggio, Davide Beltrame, Marc Mézard, Luca Saglietti

2603.03469 2026-03-03