cs papers | Gist.Science

Temporal Dynamics and Explainable Risk Factors of Traffic Fatalities: A Large-Scale Study Using PRF Brazil Data (2020-2024)

This study utilizes a large-scale dataset from the Brazilian Federal Highway Police (2020–2024) to demonstrate that a cost-sensitive LightGBM model, validated through rigorous temporal splitting and SHAP-based interpretability, outperforms other ensemble methods in predicting traffic fatalities while identifying key risk factors to inform proactive safety policies.

Rossi Passarella, Nabilla Suci Febriani, Mastura Diana Marieska, Yusuf Passarella2026-08-19

💻 computer science

Enhancing Medical Image Reconstruction Using RSA-OAEP and Hybrid RSA-AES Encryption

This paper proposes a hybrid RSA-OAEP and AES-128-CBC encryption framework with SHA-256 integrity validation that ensures secure, lossless medical image reconstruction while significantly outperforming pure RSA in computational efficiency and demonstrating robust recovery capabilities against pixel-loss corruption.

Fatma Gamal, Aya Mamdouh, Hussein Aly Jad2026-08-19

💻 computer science

DL-TUS: A Frequency-Aware Deep Learning Framework for Thyroid Nodule Classification in Ultrasound Images

The paper proposes DL-TUS, a frequency-aware deep learning framework that leverages wavelet transforms and multi-scale dilated convolutions to effectively classify thyroid nodules in ultrasound images, achieving high accuracy and robustness against noise and micro-nodule challenges.

Liping Xiao, Yujuan Che, Zengming Li, Jianqiang Yang, Dan Chen, Huan Wang2026-08-19

💻 computer science

Does Fallback-Anchored Uncertainty Gating Help Off-Policy Reinforcement Learning? A Short Study Combining DCUG-Style Gating with TD3

This study demonstrates that applying a fallback-anchored uncertainty gating mechanism, which previously stabilized on-policy PPO training, provides no statistical benefit to off-policy TD3, indicating that the mechanism's value is specific to correcting on-policy training collapse rather than serving as a general robustness booster.

Md Hasibuzzaman, Gene Eu Jan, Chan-Yun Yang, Md Shetu Mia2026-08-19

💻 computer science

Protocol-Dependent Resolution in Finite-Sample Model Selection

This paper demonstrates that the maximum generation length in evaluation protocols critically determines whether model checkpoints appear distinguishable or indistinguishable by truncating chain-of-thought reasoning, a factor often omitted in fine-tuning research that can lead to misleading conclusions about model performance and trends.

Yaoping Wang2026-08-19

💻 computer science

How to Make AI Generative Design for Building Façade Renovation More Controllable: A Case Study on a Historic District in Zhejiang, China

This study proposes a dual-control generative design framework integrating Stable Diffusion, ControlNet, MLSD, and LoRA to balance historic preservation with commercial revitalization in Zhejiang's historic districts, achieving high structural fidelity and functional responsiveness for façade renovation across diverse business formats.

Xiaoyu Ying, Jiamei Bei, Hui Zhao, Jiajing Wu, Yujie Zhao2026-08-19

💻 computer science

Target Relocalization-Driven Weakly Supervised Segmentation for Crohn's Disease via Auxiliary Anatomical Priors

This paper proposes a weakly supervised segmentation method for Crohn's disease that leverages image-level annotations enhanced by an auxiliary anatomical prior dataset and a target re-localization mechanism to generate high-quality pseudo-labels, thereby reducing annotation costs while significantly improving lesion segmentation accuracy.

Jiaxu Xu, Shu Fang, Xuekun Zhang, Jiao She, Jianguo Ju, Xuesong Zhao2026-08-19

💻 computer science

SWH-SegFormer: A Signal-Preserving Framework for Joint Optic Disc and Cup Segmentation and Reliable Cup-to-Disc Ratio Estimation

This paper proposes SWH-SegFormer, a signal-preserving framework that integrates channel recalibration, Haar wavelet downsampling, and hierarchical reciprocal attention to overcome segmentation challenges and achieve accurate joint optic disc and cup segmentation for reliable glaucoma assessment via cup-to-disc ratio estimation.

Xiaohu liu, Qian Ma, JIAJIA WANG, JING LI, biao yan, Zhenhua Wang2026-08-19

💻 computer science

Construction of Collaborative Cultivation Mechanism for Internationalized Talents: Parallel Scheduling of Global Educational Resources Based on IACO-SFLA Algorithm

This paper proposes an improved hybrid IACO-SFLA algorithm to optimize the parallel scheduling of global educational resources, demonstrating through simulations and empirical analysis that this approach effectively enhances collaborative international talent cultivation by reducing task delays and supporting multi-dimensional educational mechanisms.

Yan He2026-08-19

💻 computer science

A Neurosymbolic Multiagent Framework for Culturally Responsive Personalised Explainable and Fair AI Tutoring

This conceptual paper introduces KAIROS, a neurosymbolic multi-agent framework that ensures culturally responsive, fair, and explainable AI tutoring by formally decoupling pedagogical decisions from cultural presentation within a constrained decision-making process, while specifying a rigorous evaluation protocol to validate its theoretical guarantees without presenting empirical results.

Nikita Srivastava, Deepa Mehta2026-08-19

← Previous Next →