💻 Category

cs

2787 papers

💻 computer science

A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model

This paper proposes novel classical and quantum online reinforcement learning algorithms for finite- and infinite-horizon Markov Decision Processes under a generative model that bypass traditional paradigms like optimism in the face of uncertainty to directly compute optimal policies, achieving improved regret bounds including a polylogarithmic dependence on time steps for quantum methods.

Andris Ambainis, Joao F. Doriguello, Debbie Lim2026-08-14
💻 computer science

mapgis2shp: an open-source Python reader for the MapGIS 6.x/67 binary vector formats, validated against the native export

This paper introduces **mapgis2shp**, an open-source Python library that reverse-engineers the undocumented MapGIS 6.x/67 binary vector formats to convert them into standard geospatial data, achieving near-perfect validation against the proprietary software's native export in terms of geometry, attributes, and coordinate reference systems.

Shijie Li, Haiyang He, Xu Sun, Haoyang Qin, Xiaoyu Liu, Yilin Feng, Zengyun Zuo2026-08-14
💻 computer science

PLFD-YOLO: A Lightweight Multi-Scale Detector for Power Line Defects in UAV Imagery

This paper introduces PLFD-YOLO, a lightweight multi-scale detector featuring a four-head PAFPN with high-resolution branches, deformable convolutions, and specialized attention mechanisms that achieves state-of-the-art accuracy in detecting power line defects on UAV imagery while maintaining high inference speed suitable for embedded deployment.

Shibo Gao, Ji Liu, Hongmei Fei, Xuening Liu, Jinghui Liu, Jiangpeng Li, Yao Zhang2026-08-14
💻 computer science

Uncertainty-Aware Variational Quantum Feature Learning for Reliable High-Dimensional Classification

This paper introduces Uncertainty-Aware Variational Quantum Feature Learning (UVQFL), a hybrid framework that enhances high-dimensional classification reliability by integrating adaptive feature weighting and uncertainty estimation into variational quantum encoding, achieving a best validation accuracy of 84.62% on the MNIST dataset.

Syed Basha Shaik, Srihari Varma Mantena, Shaik Janbhasha, V. Malsoru, Ravikiran Reddy Kandadi, RADHAKRISHNAN S, Santhi T (…)2026-08-14
💻 computer science

PSCD-GS: Role-Aware Perception-Structure Collaborative Densification for 3D Gaussian Splatting

This paper proposes PSCD-GS, a novel framework that enhances 3D Gaussian Splatting by integrating image-space perceptual responses with multi-view structural evidence to enable role-aware, collaborative densification that improves the preservation of fine textures, boundaries, and thin structures while maintaining a controlled representation.

Deyong Shang, Jiaxin Shi, Lianyu Mu2026-08-14
💻 computer science

Architecture-Dependent Utility of Variational Quantum Gates in Recurrent Weather Forecasting: A Controlled QGRU–QLSTM Evaluation

This study demonstrates that the predictive utility of variational quantum gates in recurrent weather forecasting is architecture-dependent, with Quantum GRUs outperforming both compact and exact classical surrogates while Quantum LSTMs achieve comparable performance to their classical counterparts only when matched in parameter count and structure.

Abhishek Tiwari, Bhushan Kape, Pankaj Tyagi, Sachin Kumar, Geeta Singh2026-08-14
💻 computer science

Hybrid Post-quantum Secure Wireless Healthcare Network Using Ml-kem, Ml-dsa, Blockchain Audit Logging and Ai-based Intrusion Detection

This paper presents a hybrid post-quantum secure framework for Wireless Body Area Networks that integrates NIST-standardized ML-KEM and ML-DSA algorithms, blockchain-based audit logging, and AI-driven intrusion detection to protect sensitive patient data against both current and future quantum threats while achieving low latency and high accuracy in threat classification.

Veera Venkata Ravi Teja Sunnam, D. Latha2026-08-14
💻 computer science

MACRDR: Enhancing Interest Discovery and Diversity in News Recommendation via Multi-Agent Reflection

This paper proposes MACRDR, a multi-agent collaboration and reflection framework that enhances news recommendation diversity and interest discovery by reformulating the process as a dynamic intent calibration mechanism, where predictive and reflective agents collaboratively adjust user profiles to mitigate filter bubbles and capture evolving preferences.

XiaoLong Zhang, Shuang Feng2026-08-14