cs papers | Gist.Science

A Federated Graph-Based Intrusion Detection Framework for Unknown Attack Detection in Internet of Medical Things(IoMT)

This paper proposes a privacy-preserving Federated Graph-Based Intrusion Detection framework that integrates Graph Convolutional Networks and Graph Attention Networks to effectively detect both known and unseen cyberattacks in Internet of Medical Things (IoMT) environments, achieving high accuracy through cross-dataset validation while safeguarding sensitive patient data.

Bhagyasri Bora, Dharitri Brahma, Amitava Nag2026-08-05

💻 computer science

ProSocial AI as a Catalyst of Quality of Life: A Multilevel Framework for Pro-People, Pro-Planet, and Pro-Potential Futures

This conceptual article introduces the ProSocial AI-Quality of Life Catalyst Model (PAI-QOL), a multilevel framework that defines ProSocial AI as a disciplined approach to innovation which, through specific conversion pathways and enabling conditions, systematically generates fair, multidimensional quality-of-life gains for people, the planet, and future potential.

Cornelia Walther2026-08-05

💻 computer science

GAAR: Runtime Governance for Scalable Agentic Retrieval and Tool- Orchestrated Enterprise AI Systems

This paper introduces GAAR, a runtime governance architecture positioned between planner agents and tool execution that significantly reduces policy violations and unsafe tool calls while improving faithfulness and audit compliance in enterprise AI systems, albeit with a modest increase in latency, as demonstrated through extensive synthetic benchmarking.

Abhradeep Chatterjee2026-08-05

💻 computer science

Blockchain-Enabled Decision Intelligence for Post-Implementation ERP Value Realization: A Framework for Trust, Process Transparency, Smart Contracts, and Enterprise Performance Optimization

This paper proposes a four-layer framework integrating blockchain infrastructure and decision intelligence to address post-implementation ERP value realization challenges by enhancing data trust, process transparency, and automated governance through smart contracts.

Joshua Babatola2026-08-05

💻 computer science

Dynamic Sparse Attention and Mixture-of-Experts for Iterative Visual Classification

This paper proposes a Dynamic Sparse Attention and Mixture-of-Experts transformer for iterative visual classification that achieves competitive accuracy on standard benchmarks while significantly reducing active parameters and training time through recursive refinement and conditional computation.

Ahsan Umar2026-08-05

💻 computer science

Closed-Form Residual-Space Rotation for Offline Transformer Width Growth

This paper proposes an offline recipe for progressively expanding Transformer width that combines a closed-form Small Residual Integration Operator (SRIO) with block-specific expansion policies and a scalar warmup gate to significantly improve training loss and preserve learned behaviors during model growth.

Ramasubramanian B2026-08-05

💻 computer science

Fundus Image Super-Resolution Based on SRGAN with Efficient Channel Attention and Composite Degradation Modelin

This paper proposes an SRGAN-based super-resolution method enhanced with Efficient Channel Attention and a composite degradation model to improve the clarity of blurred fundus images, demonstrating superior performance in both synthetic and real-world clinical scenarios through comprehensive pixel, structural, and perceptual evaluations.

Ziheng Cheng, Kai Liu, Zhengqian Li, Bing Fu, Xusan Yang2026-08-05

💻 computer science

Efficient Test-Time Adaptation for Dynamic Distribution Shifts

This paper proposes an efficient online test-time adaptation framework that combines dynamic confidence screening, branch-level incremental tuning, and temporal distribution smoothness to achieve robust, low-latency performance on streaming data with dynamic distribution shifts.

Wenjuan Guo, Wentao Zhang, Shuyuan Wang, Ruiqi Liu2026-08-05

💻 computer science

Uncertainty-Aware Adaptive Debate for Robust and Efficient Large Language Model Reasoning

This paper introduces Uncertainty-Aware Adaptive Debate (UAAD), a simulation-based framework that dynamically optimizes LLM reasoning by localizing uncertainty and adjusting debate parameters to achieve significant accuracy gains and reduced computational costs, though its reported improvements remain hypothetical pending live-model validation.

Ruiqi Liu, Wenjuan Guo, Tian Liao, Xiaotian Fang2026-08-05

💻 computer science

Generative Artificial Intelligence in Laboratory-Based Health Sciences Education: A Scoping Review of an Emerging Evidence Base

This scoping review of nine recent studies reveals that while generative AI in laboratory-based health sciences education primarily enhances efficiency and supports individual inquiry and acquisition activities, its integration is currently limited by a small evidence base, risks of factual inaccuracy, and a notable lack of collaborative applications, underscoring the need for further comparative research and expert oversight.

Kiran Zahid2026-08-05

← Previous Next →