cs papers | Gist.Science

Navigating the Human-Tech Nexus: Hybrid Intelligence as a Driver of Innovation and Trust in Software Engineering Decision-Making

This study utilizes an AI-supported research platform to demonstrate that human–AI hybrid solutions are the most frequently preferred and balanced approach in software engineering decision-making, achieving high creativity while maintaining accuracy and trust comparable to human-only solutions, thereby suggesting that engineering education should focus on integrating AI as a collaborative tool rather than a substitute for human judgment.

ORKUN KOCAK, Şahin İdil, Murat Aydoğan2026-08-20

💻 computer science

Hybrid Spatio-Temporal Feature Representation for Discriminative Video Summarization

This paper proposes a hybrid spatio-temporal feature representation framework that integrates contrast-based, object-level, and scene-level features to enhance discriminative capability and temporal consistency, demonstrating improved video summarization performance on the TVSum and SumMe datasets compared to conventional approaches.

Charu Kavadia, Ashutosh Gupta, Prasun Chakrabarti, Yashoverdhan Vyas2026-08-20

💻 computer science

Dual-Diffusion Grid Texture Generation Based on Multimodal Geometric Perception

This paper proposes a dual-diffusion mesh texture generation method that integrates multimodal geometric perception to overcome UV mapping distortions and resolution limits, significantly enhancing the visual realism, geometric consistency, and diversity of generated 3D textures compared to existing approaches.

Shijie Zhao, HongJuan Gao2026-08-20

💻 computer science

QRISP: Qubit-Efficient and Resolution-Independent Quantum Image Representation for Scalable NISQ Processing

This paper proposes QRISP, a resource-efficient and resolution-independent quantum image representation framework that encodes images via statistical block descriptors to significantly reduce circuit complexity and qubit requirements for NISQ hardware while maintaining competitive classification performance.

Sumitha Valsalam, Tony Thomas2026-08-20

💻 computer science

A Unified Dual-Branch Framework for Tri-ModalMedical Image Fusion and Super-Resolution

This paper proposes a unified dual-branch framework that jointly optimizes tri-modal medical image fusion and super-resolution by employing specialized structure and function branches with a bidirectional cross-attention module to enhance complementary feature integration and produce high-quality fused representations.

Ye Liu, Yongli Chen, Ziyang Zhong, Ji Chen, Xing Wang2026-08-20

💻 computer science

Layout-Aware Curriculum Learning for Lightweight Document OCR

The paper proposes LACL-OCR, a lightweight document OCR framework that enhances performance by combining a heuristic-based curriculum learning strategy to organize training from easy to hard samples with a novel Layout-Aware Loss function, achieving state-of-the-art results on OmniDocBench without increasing model parameters or inference costs.

Shunzhi Wang, Jijun Zhu, Xiaohong Yu, Jun Wu, Kai Liu, Yuan Li, Dong Qin, Liping Cong, Xiaohuai Yang, Lina Meng, Liyang (…)2026-08-19

💻 computer science

Generative Artificial Intelligence and Linguistic Epistemic Justice for isiZulu and African Languages in Multilingual Education

This article argues that achieving linguistic-epistemic justice for isiZulu and other African languages in AI-mediated education requires moving beyond mere text generation to establish a governance framework that treats these languages as valid infrastructures for reasoning, identity, and intellectual authority through equitable data representation, teacher agency, and institutional accountability.

Stella Bolanle APATA, Itumeleng I. SETLHODI2026-08-19

💻 computer science

Complexity-Aware Model Selection for Structural Simulation Surrogates: Defining the Boundary Between Descriptor Models and Mesh-Based Graph Neural Networks

This study establishes a complexity-aware model selection framework for structural simulation surrogates by demonstrating that while descriptor-based models suffice for simple geometries, mesh-based graph neural networks become necessary and significantly more accurate as topological complexity increases, thereby defining a graded boundary for optimal surrogate choice.

Pancho Dachkinov, Tanio Tanev2026-08-19

💻 computer science

Individualized Machine Learning–Grounded Large Language Models for Within-Person Simulation of Physical Activity Psychological Mechanisms and Behavior in Adults with Prehypertension: A Methodological Evaluation

This methodological evaluation demonstrates that embedding individualized machine learning-derived behavioral rules into large language model prompts enhances the simulation of within-person psychological and physical activity patterns in adults with prehypertension, though the hybrid approach did not surpass the predictive accuracy of dedicated participant-specific machine learning models for structured exercise outcomes.

Haoming Ma, Zihao Liu, Runyuan Pei, Zhining Yang, Yuyang Zhang, Meihua Piao2026-08-19

💻 computer science

Auditable AI Assisted Semantic Completion Supports Metadata Enhancement in Digital Cultural Heritage Collections

This study presents and evaluates an auditable, reproducible AI-assisted workflow that leverages label co-occurrence and propagation techniques to effectively enhance sparse and uneven metadata in digital cultural heritage collections, achieving high recall rates for missing object-type, material, subject, and classification labels.

Ziqi Shen2026-08-19

← Previous Next →