cs papers | Gist.Science

SGRI-HF: A Semantic Group-Aware Gated Residual Interaction and Heterogeneous Fusion Framework for College Student Mental Health Risk Identification

This paper proposes the SGRI-HF framework, which leverages semantic group modeling, adaptive gating, and heterogeneous fusion to effectively identify college student mental health risks by capturing complex cross-domain dependencies and individual differences in questionnaire data, achieving superior performance and interpretability compared to existing methods.

Fengyue Zhang, Chunlei Shi, Junfeng Zhang2026-08-24

💻 computer science

A Cautionary Evaluation of LLMs for TLS Normative Requirement Classification

This paper evaluates large language models for automating TLS normative requirement classification using NIST SP 800-52 Rev. 2, finding that while ensemble methods achieve 93.75% accuracy, systematic confusion between "SHOULD NOT" and "MAY" language renders current LLMs insufficiently reliable for standalone compliance auditing.

Majid Mollaeefar, Riccardo Germenia, Salvatore Manfredi, Silvio Ranise2026-08-24

💻 computer science

From obligation to enforcement: mapping EU AI Act and CRA cybersecurity requirements to technical controls for LLM-based autonomous agents

This paper bridges the gap between the outcome-oriented cybersecurity obligations of the EU AI Act and Cyber Resilience Act and practical implementation by mapping their provisions to concrete technical controls and verification evidence specifically tailored for LLM-based autonomous agents.

Abayomi Ogayemi2026-08-24

💻 computer science

Design and Evaluation of a Lightweight Real-Time Facial Expression Recognition System: A PyTorch Mini-Xception Implementation Trained on FERPlus.

This paper presents a lightweight, real-time facial expression recognition system using a custom PyTorch "Mini-Xception" model trained on the FERPlus dataset with square root inverse frequency weighting, which achieves a balanced 75.40% test accuracy and 30 FPS on an Apple M1 Pro without requiring significant GPU resources.

Debanjan Chakraborty2026-08-24

💻 computer science

Task-Adaptive Calibration for Multimodal Long-Context Extension

This paper introduces Task-Adaptive Calibration (TAC), a lightweight module that combines task-conditioned cross-modal rectification with distance-aware redistribution to significantly improve multimodal long-context understanding and evidence localization accuracy while maintaining minimal computational overhead.

Xiang Li, Zhenning Guo, Ruiqi Liu2026-08-24

💻 computer science

Topological Materialization of Deterministic Intelligence: Bypassing Energy-Latency Limits of Generative AI via Phase-Resonant Mersenne Lattice

This paper claims to have realized a revolutionary "Reproductive AI" system that bypasses the energy and latency limits of traditional generative AI by using a topological Mersenne lattice and phase-resonant circuits to achieve deterministic, zero-memory intelligence retrieval with zero hallucinations and drastically reduced power consumption.

Min Ho Jung2026-08-24

💻 computer science

MoEMory: Long-Term User Memory as a Routing Policy on Frozen Mixture-of-Experts Language Models

MoEMory introduces a novel long-term memory paradigm for frozen Mixture-of-Experts language models that stores per-user information as a routing bias to selectively activate existing capabilities without injecting new tokens or parameters, thereby achieving near-zero leakage into unrelated queries while remaining orthogonal and complementary to traditional injection-based memory methods.

Chenxi He2026-08-24

💻 computer science

AI-generated Academic Publications and Research Integrity: A Cross-National Analysis of Trends, Detection Methods, and Policy Responses (India vs. Global Standards, 2020-2026)

This cross-national study (2020–2026) analyzes the rapid rise of AI-generated academic submissions in India and globally, revealing comparable vulnerability rates but significant policy gaps in India, and proposes evidence-based, multi-method detection and institutional accountability frameworks to safeguard research integrity.

JAINISH BHAGAT2026-08-24

💻 computer science

YOLO-Based Deep Learning for Citrus Fruit Detection, Counting, and Yield Estimation in Complex Orchard Environments: A Systematic Review

This systematic review of 88 studies utilizing YOLO-based deep learning for citrus fruit detection and yield estimation reveals that while the field has converged on a common technical toolkit achieving high average precision, it critically lacks standardized benchmarks, diverse datasets, and rigorous statistical validation, resulting in a high overall risk of bias.

Paola D'Antonio, Luis Alcino Conceição, Danilo Travascia, Lucas Santos Santana, Josiane Maria da Silva, Francesco Toscan (…)2026-08-24

💻 computer science

Transaction Intent Graph: Semantic Cross-LayerDefense Orchestration for Microservices PaymentSystem

This paper introduces TIG-CDO, a semantic cross-layer defense orchestration framework that constructs transaction intent graphs to detect and mitigate Composite Slow-Degradation Attacks (CSDA) in microservices payment systems by shifting analysis from individual HTTP requests to causally ordered multi-step transactions, achieving 99.9% SLA compliance and significantly reduced false positives compared to traditional layered defenses.

Amit Rangari2026-08-24

← Previous Next →