09:00– 10:00
NGEN-AI 2026
Conference Program
Preliminary ProgramA four-day program of keynotes, technical sessions, and research presentations advancing the next generation of AI systems.
1–4 September 2026
Trento, Italy · Online over Zoom
Times shown in CEST
Explore the schedule
Select a day to view its sessions and presentations.
Onsite
Online
61 papers
Tuesday, 1 September
10:00– 11:00
Keynote address
Backpropagating from Customer Success: The Case of Enterprise Knowledge Bases
Prof. Fabio Casati
Aula Magna A101
Join on Zoom
11:00– 11:30
Morning coffee break
11:30– 13:00
Session 1
Small & Large Language Models and Generative AI
Session chair: Jacopo Staiano
- Smart Request: An Agentic LLM Framework for Interactive Requirement Engineering and Governance-Compliant Backlog Generation
- A Closed-Loop Agentic Revenue Management System for Self-Storage: Architecture, Behavioral Churn Prediction, and Dynamic Pricing
- Designing Explanation Artifacts for LLM-Based Question Answering in Education: Supporting Students' Provenance Understanding and Verification of Generated Answers
- An LLM-Based Multi-Agent Framework for Natural Language Interrogation and Exploitation of Smart City Services
13:00– 14:00
Lunch break
14:00– 15:30
Session 2
Agentic AI
Session chair: Bellur Srikar
- CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
- RabbitQA: A Multi-Agentic AI Platform for Digital Product Quality and Autonomous Risk Discovery
- Towards Reliable Multi-Agent Unit Test Generation through Verification and Iterative Refinement
- Agentic Autonomous Pedestrians: Integrating Reactive Kinematics with Generative Social Reasoning
15:30– 16:00
Afternoon coffee break
16:00– 17:30
Session 3
Applications & Societal Impact of Next Generation AI
Session chair: Ahmad Nauman Ghazi
- Ed-AID: Education in an AI-Dominated World
- BayanLM: Morphological Priors and Embedding Enrichment for Character-Level Arabic Diacritization
- In The Eyes Of: An Offline-First System for Geolocalized Expert Narration in Heritage Interpretation
Wednesday, 2 September
09:00– 10:00
Registration
10:00– 11:00
Keynote address
Digital Addiction: From Social Media to AI
Prof. Raian Ali
Aula Magna A101
Join on Zoom
11:00– 11:30
Morning coffee break
11:30– 13:00
Session 4
Small & Large Language Models and Generative AI
Session chair: Reihaneh Tarlani
- Spec-Driven Compilation, Hierarchical Routing, and Coverage Refusal for a Deployed Multi-Tool MCP Assistant in Fire & Rescue Services
- The Way We Prompt, the Way We Depend: Motivation, Interaction Styles, and Trust as Predictors of LLM Dependency
- AquiLLM: An Architecture for Supporting Tacit Knowledge Capture in Research Groups
- ShaperAI: A Governed Agentic Architecture for Enterprise Digital Cost Management
13:00– 14:00
Lunch break
14:00– 15:30
Session 5
Applications & Societal Impact of Next Generation AI
Session chair: Raian Ali and Daniel Jönsson
- AI Application Operations - A Socio-Technical Framework for Data-driven Organizations
- Interpretable, Unsupervised Anomaly Detection for Early Refrigerant Leak Mitigation in Commercial HVAC Systems
- Exploring Implicit Human Social Relationships through CNN-Based Algorithms
- Attitudes towards AI and the Demand for eXplainable AI: Does Spirituality Matter?
15:30– 16:00
Afternoon coffee break
16:00– 17:30
Session 6
Cross-track Spotlight: Federated Learning / Agentic AI / Explainable AI (XAI) & Transparency / Trustworthy, Responsible & Sustainable AI
Session chair: Grazziela Figueredo
- Red-Teaming an Enterprise RAG System: A Multi-Dimensional Evaluation of Security, Fairness, and Coherence
- Addressing the Cold-Start Problem in Clinical Vocabulary Mapping through Federated Analytics
Thursday, 3 September
09:00– 10:00
Registration
10:00– 11:00
Keynote address
iQuantum: Innovative Software Systems for Next-Gen Quantum ComputingKeynote
Prof. Rajkumar Buyya
Aula Magna A101
Join on Zoom
11:00– 11:30
Morning coffee break
11:30– 13:00
Session 7
Small & Large Language Models and Generative AI
Session chair: To be confirmed
- DeepContext: Stateful Real-Time Detection of Multi-Turn Adversarial Intent Drift in LLMs
- Robust Function Calling for LLM Agents Under Interface Drift
- Leveraging Generative Artificial Intelligence to Enhance Customer Service Email Replies
- No Universal Recipe for QLoRA: Multi-Seed Evidence for Model-Specific Precision Effects in Efficient LLM Adaptation
11:30– 13:00
Session 8
Applications & Societal Impact of Next Generation AI
Session chair: Mathieu Léonardon
- Early Industry Adoption of the Model Context Protocol: An Empirical Study
- SimA-MCU: Softmax-Free Attention on Microcontrollers forReal-Time EEG Decoding
- Jenius Agent: Towards Experience-Driven Accuracy Optimization in Real-World Scenarios
- Gabor Erdelyi, Olivia Erdelyi and Andreas W. Kempa-Liehr
13:00– 14:00
Lunch break
14:00– 15:00
Keynote address
The Future of Quantum Computing: From Quantum Cloud Platforms to Intelligent and Sustainable Solutions
Prof. Sukhpal Singh Gill
Main Hall
Join on Zoom
15:30– 16:00
Afternoon coffee break
16:00– 17:30
Session 9
AI Systems, Hardware & Edge/Cloud Infrastructures
Session chair: Ali A. Alwan Al-juboori
- Resolving Intent-Content Conßict in Retrieval: An Emotion-Aware Knowledge Graph Framework
- Search for Z/2 eigenfunctions on the sphere using machine learning
- Per-Head Power and Energy Profiling of a Multi-Task HydraNet on Edge Devices
- FreeMult: A Multiplier-Free FPGA Accelerator for CNNs
16:00– 17:30
Session 10
Cross-track Spotlight: Federated Learning / Small & Large Language Models and Generative AI / Deep Learning Architectures & Representation Learning / Explainable AI (XAI) & Transparency
Session chair: Tania Afroz Toma
- A gender perspective on explainable predictive modeling of self-perceived health in institutionalized older adults with visual disabilities
- BW-FedSMU: Adaptive Bit-Rate Compression for Heterogeneous Federated Learning
- RAG-NIMBF: A Non-Invasive, Modular Benchmarking Framework for Automated RAG Configuration Analysis
- Speak for Themselves or Spoken About: Unequal Representational Autonomy in Text-to-Image Depictions of Material Culture
20:00– 20:02
Gala Dinner, Antico Pozzo, Vicolo della Sat, 6, 38122 Trento TN, Italy
Friday, 4 September
09:00– 10:00
Registration
10:00– 11:00
Session 11
Agentic AI
Session chair: Ubaida Fatima
- Emotion-Centred Forensic Reasoning for Zero-Shot DeepFake Video Detection
- FDA-Tokenizer: A Factorized Full-Diacritic-Aware Tokenization Framework for Classical Arabic
10:00– 11:00
Session 12
Applications & Societal Impact of Next Generation AI
Session chair: Md Nahid Sultan
- FT-DSL: Resilient Dynamic Split Learning with AdaptiveCheckpointing
- KPIs for Productionizing AI and Agentic AI Solutions: An Archetype-Matched Measurement Discipline
- Investigating Loss Functions for Long-Tail Mental-Health Topic Classification in Bangla Empathetic Conversations
11:00– 11:30
Morning coffee break
11:30– 13:00
Session 13
Small & Large Language Models and Generative AI
Session chair: Abdurrahman Gülbeyaz
- Before and After Temperature: A Distributional View of Creative LLM Generation
- Generative AI and the Civilisation of Operational Dependence – Towards a Semiotics of Next-Generation AI Systems
- StudyBuddy: Designing an LLM-Powered Reading Support System for Dyslexic University Students
- Toward Privacy-by-Design for LLM Applications for Children
11:30– 13:00
Session 14
Applications & Societal Impact of Next Generation AI
Session chair: Gertraud Koch
- Cross Agent Context Anchoring
- Plurification in/of language technology. The integration of ÔcultureÕ in next-generation AI
- Estimating Dialogue Interaction Quality: Multi-Turn Linguistic Indicators Across Heterogeneous Corpora
- Confidence Indicators and Trust Calibration in AI-Assisted Learning: A Study Across Educational Experience Levels
13:00– 14:00
Lunch break
14:00– 15:30
Session 15
Trustworthy, Responsible & Sustainable AI
Session chair: Igor Bernik
- Toward Trustworthy and Explainable AI-Assisted Cybersecurity for Everyday Users
- When fairness metrics fail: An utility-based perspective
- Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI
- Efficient Compression of Large Language Models ThroughStructured and Unstructured Pruning: A ComparativeEvaluation on Benchmark NLP Tasks
14:00– 15:30
Session 16
Applications & Societal Impact of Next Generation AI
Session chair: Moamin Abughazala
- BiasGuard: Real-Time Bias Detection and Mitigation in AI Responses
- Architecture-Grounded Data Contract Viewpoint for DataGovernance in Data-Intensive Systems
- The LUMI Visibility Index (LVI): A Composite Framework forMeasuring Brand Representation Across Frontier GenerativeAI Systems
15:30– 16:00
Afternoon coffee break
16:00– 17:30
Session 17
Applications & Societal Impact of Next Generation AI
Session chair: Ubaida Fatima
- Intelligent Early Detection of Type 2 Diabetes: A Comparative Study of Machine Learning and Feature Selection Strategies
- Communication Interval and Source Specific Stability Patterns in FedAvg-DDQN under MDP Level Heterogeneity
- Designing Intelligent Enterprise Agents: A Capability-Aligned Multi-Agent Architecture
The program is subject to minor changes. Please check this page again before the conference for the latest schedule.