cs papers | Gist.Science

AI-Driven Collective Adaptation Testbed: A Multi-Agent Architecture Grounded in Dual-Inheritance Theory

This paper introduces the Collective Adaptation Testbed (CAT), a multi-agent software architecture grounded in Dual-Inheritance Theory that resolves the governance paradox of quantitative metrics by intercepting team decisions to distinguish between blind conformity and expertise-driven dissent, thereby enabling the system to autonomously revise its own rules based on retrospective outcome data.

Volkan Aşkun2026-07-15

💻 computer science

Artifact-Aware Lightweight Dermoscopic Lesion Segmentation with Reproducible Corruption Robustness Evaluation

This paper proposes an artifact-aware lightweight U-shaped segmentation framework and a reproducible corruption benchmark to enhance the robustness and accuracy of dermoscopic lesion segmentation in the presence of acquisition artifacts like hair and specular highlights.

Haixiao Gong, Cuijiao Yin, Jie He, Hui Guo, Mei Tang, Linting Meng, Chengchen Gong2026-07-15

💻 computer science

Interpretable-Aware Privacy Preserving Framework for Deepfake Detection using Federated ResNet and Explainable AI Techniques

This paper proposes a privacy-preserving deepfake detection framework that integrates Federated Learning with ResNet-18 and the FedProx algorithm to achieve high accuracy (97.20%) on the FaceForensics++ dataset while ensuring data security and model interpretability without transferring raw images.

Pochampally Chandra Sekhar Reddy, Kongara Srinivasa Rao2026-07-15

💻 computer science

Gesture-based Smart Home Control for Special Needs Individuals Using Computer Vision

This paper presents an end-to-end, real-time smart home control system for individuals with speech impairments that integrates a CNN-based hand gesture recognition model with an OpenCV inference pipeline and modular action layer to translate live camera inputs into executable device commands.

Kareem Mohamed, Walaa Abo Elenin, Yiming Ji2026-07-15

💻 computer science

Uncertainty-Aware Assessment of LLM-Enhanced Topic Models: An Experton-Based Approach to Interpretability

This study introduces an uncertainty-aware evaluation framework based on the Theory of Expertons to assess topic models in specialized tourism corpora, demonstrating that LLM-enhanced BERTopic outperforms traditional and neural approaches while revealing that decoding temperature significantly impacts interpretability.

Eddy Soria, Antonio Moreno, Jordi Pascual, Ana Beatriz Hernández-Lara2026-07-15

💻 computer science

A New Meta-Heuristic for Improving General Multi-Start Procedures, With an Application to the Planar p-Median Location Problem

This paper proposes a general, low-cost post-optimization meta-heuristic that enhances multi-start algorithms by iteratively generating and improving offspring from an elite set of solutions, successfully improving the best-known results for all 48 tested planar p-median instances within comparable run times.

Zvi Drezner, Jack Brimberg2026-07-15

💻 computer science

Robust Score-Based Generative Modelling withTsallis–Gaussian Perturbations

This paper proposes a robust score-based generative modelling framework using Tsallis–Gaussian perturbations and a dual-head neural architecture to effectively mitigate the impact of heavy-tailed data and contamination while maintaining competitive generative performance.

Shenghan Gao, Spiridon Penev, Libo Li2026-07-15

💻 computer science

Multi-view Patch Inference with Frozen DINOv3 for Industrial Anomaly Detection

This paper proposes a framework for industrial anomaly detection that combines a frozen DINOv3 backbone with a Multi-view Patch Inference strategy to overcome boundary information loss and a Multi-scale Reconstruction Fusion Transformer to model normal feature distributions, achieving state-of-the-art performance on multiple benchmark datasets.

Chaoqun Wang, Wenjing Zhang, Bo Qi, Xiaoyu Huang, Ning He2026-07-15

💻 computer science

LAR-Net: A Lightweight Adaptive Receptive Field Network for Point Cloud Segmentation of Pharmaceutical Deposits on Reactor Inner Walls

This paper proposes LAR-Net, a lightweight adaptive receptive field network built on the LitePT backbone that dynamically adjusts to local geometric complexities to achieve high-precision point cloud segmentation of pharmaceutical deposits on reactor inner walls, thereby overcoming the limitations of conventional inspection methods and enabling automated intelligent cleaning.

Jiajia Liu, Haiyang Wang, Zhongli Ma, Yuedong Shi, Bingyu Chen, Sidong Wu, Ting Zhang2026-07-15

💻 computer science

Captioning Daily Activity Images in Early Childhood Education: Benchmark and Algorithm

This paper introduces KinderMM-Cap, a specialized multimedia captioning system for early childhood education that leverages the ECAC benchmark and a novel reward-conditional hybrid training framework (RSRS) to significantly improve the accuracy of generating educationally meaningful captions for complex classroom scenes and teaching toys.

Sixing Li, Zhibin Gu, Ziqi Zhang, Weiguo Pan, Bing Li, Ying Wang, Hongzhe Liu2026-07-15

← Previous Next →