💻 Category

cs

4157 papers

💻 computer science

NEPHILA: A Bio-Inspired Optimization Algorithm Based on Adaptive Interception Dynamics and Learning-Guided Search

This paper introduces NEPHILA, a bio-inspired optimization algorithm that integrates adaptive interception dynamics with learning-guided search mechanisms, demonstrating flexible performance across continuous and combinatorial problems where its effectiveness depends on the specific objective landscape, computational budget, and coordination of search components rather than universal superiority.

Gilberto Pérez Lechuga2026-11-12
💻 computer science

Gyroscope-Guided Optimal Transport for SuperGlue: A Training-Free Epipolar-Arc Prior

This paper proposes a training-free epipolar-arc prior that leverages gyroscope data to guide SuperGlue's matching process, significantly improving pose estimation accuracy—particularly under motion blur and for pipelines that ignore inertial data—by rewarding candidates based on their angular distance to the geometric arc defined by the rotation and estimated translation direction.

Ufuk Asil2026-11-12
💻 computer science

Explainable, Uncertainty-Aware Ensemble Learning for Brain Tumor Classification from MRI with a Simulated Fairness Audit

This paper presents an explainable, uncertainty-aware ensemble learning framework for brain tumor classification from MRI that achieves high accuracy and calibration while demonstrating the feasibility of integrating quantitative explanation scoring, Monte Carlo uncertainty estimation, and simulated fairness audits into medical AI development.

Md. Sajjad Ullah, Shochi Akter, Sadman Sadik Khan2026-11-12
💻 computer science

A Hybrid MA-BBO-PSO Metaheuristic Framework for Large-Scale Website Reorganization and Enhanced Web Navigation

This paper proposes a hybrid metaheuristic framework (WDR_MA_BBO_PSO) combining Memetic algorithms, Biogeography-Based Optimization, and Particle Swarm Optimization to dynamically reorganize large-scale websites and rank pages based on behavioral and structural criteria, demonstrating superior performance in precision, recall, and click-through rates compared to traditional algorithms.

Ravi Kumar, Santosh Kumar2026-11-12
💻 computer science

Attack-Path-Aware Enterprise Risk Quantification for Cloud-Native Financial Data Platforms Using AI and Cybersecurity Graphs

This paper proposes an AI-driven, attack-path-aware risk quantification framework for cloud-native financial platforms that unifies vulnerability management with financial impact analysis using cybersecurity graphs and FAIR modeling to optimize control selection, demonstrating an 85% reduction in expected annual loss compared to conventional severity-based approaches.

Gopinathan Rathinavelu2026-11-12
💻 computer science

Hybrid Visual Perception and LLM Framework for Service Robot Planning and Navigation

This paper proposes a hybrid framework that integrates fast deep-learning-based visual perception with large language model reasoning to enable efficient, low-latency task planning and navigation for service robots on lightweight embedded platforms, achieving high success rates while significantly outperforming computationally intensive vision-language model baselines.

Ahmad Ataka, Yanayir Rifai, Yusuf Badriawan, Burhanudin Burhanudin, Igi Ardiyanto, Jun Miura, Dino Accoto2026-11-12
💻 computer science

Rotated-Box Multi-Modal Vehicle Detection in Aerial Imagery: A Systematic Study with an Empirical Re-examination of Modality Misalignment

This study challenges the prevailing assumptions that spatial misalignment and IR modality are primary hurdles in aerial vehicle detection by demonstrating that, on well-registered datasets like VEDAI and DroneVehicle, the true challenges are geometric class confusion among tiny objects and that explicit alignment modules yield negligible gains compared to the significant benefits of rotated-box heads and IR fusion.

Yi Wu2026-11-12