Buch, Englisch, 971 Seiten, Format (B × H): 155 mm x 235 mm
First International Conference, NGEN-AI 2026, Trento, Italy, September 1–4, 2026, Proceedings
Buch, Englisch, 971 Seiten, Format (B × H): 155 mm x 235 mm
Reihe: Communications in Computer and Information Science
ISBN: 978-3-032-45664-9
Verlag: Springer
This book constitutes the refereed proceedings of the First International Conference on Next Generation AI Systems, NGEN-AI 2026, held in Trento, Italy, during September 1-4, 2026.
The 52 full papers and 8 short papers presented in this book were carefully selected and reviewed from 116 submissions. These papers have been organized in the following topical sections:
Learning Methods and Model Efficiency
Edge AI and Hardware Acceleration
Language Models, Retrieval, and Language Technologies
Agentic AI and Multi-Agent Systems
Trustworthy AI, Security, Fairness, and Privacy
AI Engineering, Operations, and Governance
AI for Health and Care
AI for Education and Accessibility
Human-Centered AI, Culture, and Society
AI Applications in Organizations and Smart Environments
Zielgruppe
Research
Autoren/Hrsg.
Fachgebiete
Weitere Infos & Material
.- Learning Methods and Model Efficiency.
.- Search for Z/2 eigenfunctions on the sphere using machine learning.
.- No Universal Recipe for QLoRA: Multi-Seed Evidence for Model-Specific Precision Effects in Efficient LLM Adaptation.
.- Efficient Compression of Large Language Models Through Structured and Unstructured Pruning: A Comparative Evaluation on Benchmark NLP Tasks.
.- FT-DSL: Resilient Dynamic Split Learning with Adaptive Checkpointing .
.- Communication Interval and Source Specific Stability Patterns in FedAvg-DDQN under MDP Level Heterogeneity.
.- BW-FedSMU: Adaptive Bit-Rate Compression for Heterogeneous Federated Learning.
.- Edge AI and Hardware Acceleration.
.- SimA-MCU: Softmax-Free Attention on Microcontrollers for Real-Time EEG Decoding.
.- Per-Head Power and Energy Profiling of a Multi-Task HydraNet on Edge Devices.
.- FreeMult: A Multiplier-Free FPGA Accelerator for CNNs .
.- Language Models, Retrieval, and Language Technologies.
.- Resolving Intent-Content Conflict in Retrieval: An Emotion-Aware Knowledge Graph Framework.
.- RAG-NIMBF: A Non-Invasive, Modular Benchmarking Framework for Automated RAG Configuration Analysis.
.- Before and After Temperature: A Distributional View of Creative LLM Generation.
.- Estimating Dialogue Interaction Quality: Multi-Turn Linguistic Indicators Across Heterogeneous Corpora.
.- BayanLM: Morphological Priors and Embedding Enrichment for Character-Level Arabic Diacritization.
.- FDA-Tokenizer: A Factorized Full-Diacritic-Aware Tokenization Framework for Classical Arabic .
.- Agentic AI and Multi-Agent Systems.
.- Robust Function Calling for LLM Agents Under Interface Drift .
.- Early Industry Adoption of the Model Context Protocol: An Empirical Study.
.- Cross Agent Context Anchoring.
.- Jenius Agent: Towards Experience-Driven Accuracy Optimization in Real-World Scenarios.
.- Designing Intelligent Enterprise Agents: A Capability-Aligned Multi-Agent Architecture.
.- Smart Request: An Agentic LLM Framework for Interactive Requirement Engineering and Governance-Compliant Backlog Generation.
.- Smart Request: An Agentic LLM Framework for Interactive Requirement Engineering and Governance-Compliant Backlog Generation.
.- Towards Reliable Multi-Agent Unit Test Generation through Verification and Iterative Refinement.
.- Trustworthy AI, Security, Fairness, and Privacy.
.- DeepContext: Stateful Real-Time Detection of Multi-Turn Adversarial Intent Drift in LLMs.
.- Red-Teaming an Enterprise RAG System: A Multi-Dimensional Evaluation of Security, Fairness, and Coherence.
.- Toward Trustworthy and Explainable AI-Assisted Cybersecurity for Everyday Users.
.- Emotion-Centred Forensic Reasoning for Zero-Shot DeepFake Video Detection.
.- When fairness metrics fail: An utility-based perspective.
.- BiasGuard: Real-Time Bias Detection and Mitigation in AI Responses.
.- Toward Privacy-by-Design for LLM Applications for Children .
.- Data Fusion Challenges Privacy: What Can Privacy Regulation Do? .
.- Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI.
.- AI Engineering, Operations, and Governance.
.- AI Application Operations - A Socio-Technical Framework for Data-driven Organizations.
.- KPIs for Productionizing AI and Agentic AI Solutions: An Archetype-Matched Measurement Discipline.
.- Architecture-Grounded Data Contract Viewpoint for Data Governance in Data-Intensive Systems.
.- RabbitQA: A Multi-Agentic AI Platform for Digital Product Quality and Autonomous Risk Discovery.
.- ShaperAI: A Governed Agentic Architecture for Enterprise Digital Cost Management.
.- AI for Health and Care.
.- Intelligent Early Detection of Type 2 Diabetes: A Comparative Study of Machine Learning and Feature Selection Strategies.
.- A gender perspective on explainable predictive modeling of self-perceived health in institutionalized older adults with visual disabilities.
.- Investigating Loss Functions for Long-Tail Mental-Health Topic Classification in Bangla Empathetic Conversations.
.- Addressing the Cold-Start Problem in Clinical Vocabulary Mapping through Federated Analytics.
.- CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs.
.- AI for Education and Accessibility.
.- Ed-AID: Education in an AI-Dominated World.
.- Designing Explanation Artifacts for LLM-Based Question Answering in Education: Supporting Students’ Provenance Understanding and Verification of Generated Answers.
.- Confidence Indicators and Trust Calibration in AI-Assisted Learning:A Study Across Educational Experience Levels.
.- StudyBuddy: Designing an LLM-Powered Reading Support System for Dyslexic University Students.
.- Human-Centered AI, Culture, and Society.
.- Attitudes towards AI and the Demand for eXplainable AI: Does Spirituality Matter?.
.- The Way We Prompt, the Way We Depend: Motivation, Interaction Styles, and Trust as Predictors of LLM Dependency.
.- Generative AI and the Civilisation of Operational Dependence – Towards a Semiotics of Next-Generation AI Systems.
.- Plurification in/of language technology. The integration of ‘culture’ in next-generation AI.
.- Exploring Implicit Human Social Relationships through CNN-Based Algorithms.
.- Speak for Themselves or Spoken About: Unequal Representational Autonomy in Text-to-Image Depictions of Material Culture.
.- The LUMI Visibility Index (LVI): A Composite Framework for Measuring Brand Representation Across Frontier Generative AI Systems.
.- In The Eyes Of: An Offline-First System for Geolocalized Expert Narration in Heritage Interpretation.
.- AI Applications in Organizations and Smart Environments.
.- Leveraging Generative Artificial Intelligence to Enhance Customer Service Email Replies.
.- Interpretable, Unsupervised Anomaly Detection for Early Refrigerant Leak Mitigation in Commercial HVAC Systems.
.- A Closed-Loop Agentic Revenue Management System for Self-Storage: Architecture, Behavioral Churn Prediction, and Dynamic Pricing.
.- AquiLLM: An Architecture for Supporting Tacit Knowledge Capture in Research Groups.
.- An LLM-Based Multi-Agent Framework for Natural Language Interrogation and Exploitation of Smart City Services.
.- Agentic Autonomous Pedestrians: Integrating Reactive Kinematics with Generative Social Reasoning.




