cs papers | Gist.Science

Artificial Intelligence-Driven Flight Disruption Management: A Scoping Review and Critical Evidence Synthesis for Predictive Decision Support in Airline Operations Control Centers

This scoping review synthesizes evidence on AI-driven flight disruption management, revealing that while predictive and mathematical recovery methods are mature, a critical gap remains in translating high-accuracy forecasts into feasible, explainable, and uncertainty-aware decision support for real-world Airline Operations Control Centers.

Jamil Akhtar2026-08-20

💻 computer science

How Do Rendering Optimization Techniques Balance Visual Fidelity, Computational Performance, and Educational Usability in Virtual Reality Systems? A Systematic Review

This systematic review analyzes how rendering optimization techniques balance visual fidelity, computational performance, and educational usability in virtual reality, revealing that stable high-frame-rate operation with moderate detail often supports learning more effectively than maximal realism while highlighting critical gaps in cross-device benchmarks and education-specific validation.

Thom luis2026-08-20

💻 computer science

Demand Forecasting for Internet Bandwidth using Machine Learning to Enhance Resource Management in Nepal

This research proposes the development and deployment of advanced machine learning models to accurately forecast internet bandwidth demand in Nepal's Kathmandu Valley, enabling ISPs to optimize resource allocation, mitigate network congestion, and improve overall service quality through data-driven decision-making.

Sachin Maharjan, Shankar Ghimire2026-08-20

💻 computer science

Meaningful Ambiguation as a Generative Mechanism in Language Model Architectures

This paper proposes and experimentally validates an architectural intervention called "meaningful ambiguation," which applies an aesthetic-theory-inspired transform to language model pipelines to generate outputs that simultaneously achieve high diversity, structural coherence, and seed locality—capabilities that standard sampling methods like temperature adjustments fail to replicate.

Richard Taylor2026-08-20

💻 computer science

SkeletonGraph: A Zero-LLM Structural Retrieval Engine for Coding Agents, and Why Its Gains Land in the Cost Tail, Not the Median

This paper introduces SkeletonGraph, a structural retrieval engine that significantly improves function-level code localization and reduces costs for coding agents in the expensive tail of task distributions, yet fails to lower median costs or boost solve rates because its effectiveness is constrained by repository familiarity and cannot replace the agent's own learning from reading code.

Yash Doke2026-08-20

💻 computer science

Ask Twice, Look Twice: Training-Free Consistency Filtering for Reliable Medical VQA

This paper introduces "Ask Twice, Look Twice," a training-free, model-agnostic consistency filtering framework that leverages semantically equivalent question augmentation and visual perturbations to significantly enhance the reliability and trustworthiness of Medical Visual Question Answering systems in clinical settings without requiring additional model training.

Yongpei Ma, Zhuoran Duan, Pengyu Wang, Adam G. Dunn, Usman Naseem, Jinman Kim2026-08-20

💻 computer science

Open Sign Bibles (OSB): An Open-Access Multilingual Sign Language Bibles Dataset

This paper introduces the Open Sign Bibles (OSB), the largest legally unencumbered multilingual dataset of its kind, comprising over 700 hours of openly licensed Bible videos in 20 sign languages aligned with parallel text in over 800 spoken languages to facilitate multimodal retrieval and contrastive learning research.

Colin Leong, Joshua Nemecek, Kavitha Raju, Joel Mathew, Vijayan Asari, Elisabeth Leong2026-08-20

💻 computer science

Deep Reinforcement Learning Framework for Multi-UAV Collision-Free Navigation and Cooperative Control

This paper proposes a Proximal Policy Optimization-based Deep Reinforcement Learning framework that enables multiple UAVs to autonomously navigate complex urban environments, effectively avoiding collisions and cooperating to reach targets in both static and dynamic scenarios.

Jailsingh Bhookya, Abhishek Mondal, Suvam Das2026-08-20

💻 computer science

Research on table tennis motion recognition under limb occlusion

This paper presents a reliable table tennis motion dataset and proposes a spatio-temporal graph convolutional neural network model that effectively predicts occluded joint positions to improve motion recognition accuracy under limb occlusion.

Jun Zhang, Yu Xing, Yongxuan Wang, Zhaoxia Lu, Jie Ren2026-08-20

💻 computer science

Linear Gaussian Kernel Cycle Generative Adversarial Networks based Transformer Learning for Early-Stage Stroke Prediction with Parkinson and Skin Disease

This paper proposes a Linear Gaussian Kernel Cycle Generative Adversarial Networks-based Transformer Learning (LGKCGAN-TL) model that integrates image denoising, GAN-based data augmentation, and Rosenthal Correlative Transformer Learning to achieve high-accuracy, low-latency early-stage stroke prediction by leveraging data from Parkinson's and skin disease datasets.

T Haritha, A.V. Santhosh Babu, B Sharmila, K Sasikala2026-08-20

← Previous Next →