Conference Scope
The Federated Learning and Intelligent Computing Systems (FLICS) Conference brings together researchers, practitioners, and industry leaders to explore the convergence of federated learning with intelligent computing systems, edge AI, and autonomous workflows. As we advance toward 6G networks, pervasive edge intelligence, and decentralized cyber-physical systems, the need for collaborative, privacy-preserving learning approaches has never been more critical.

FLICS conference focuses on the intersection of federated learning systems with emerging intelligent computing paradigms, including agentic AI workflows, edge intelligence, digital twin technologies, mobile computing, and distributed machine learning. We aim to address the fundamental challenges of engineering and deploying scalable, secure, and efficient federated learning systems across diverse computational environments in various application domains, including health, energy management, industrial automation, and smart cities.

FLICS 2026 provides a unique platform for interdisciplinary collaboration, bridging theoretical foundations and practical implementations. The Conference welcomes contributions from both researchers and practitioners in the field of FL.

Topics of Interest:

We invite submissions addressing, but not limited to, the following areas:

1- Federated Learning Systems & Edge Intelligence
- FL systems automation and self-tuning capabilities
- Scalable federated learning architectures for large-scale deployments
- Cross-silo and cross-device federated learning systems
- Hardware-aware and resource-efficient federated learning
- Communication-efficient FL (quantization, sparsification, compression techniques)
- FL under client mobility, heterogeneity, and intermittent connectivity
- Network-aware optimization and system-level co-design for FL
- Benchmark and evaluation frameworks for FL systems in mobile/wireless environments
- FL deployment in UAVs, mobile edge clouds, and autonomous systems

2- Agentic Workflows and Collaborative AI
- Federated learning for agentic AI systems and autonomous workflows
- Collaborative learning in multi-agent environments
- Privacy-preserving agent-to-agent communication and coordination
- Federated training of foundation models for agentic applications
- Distributed learning for tool-use optimization and workflow adaptation
- User-agent interaction personalization through federated approaches

3- Privacy, Security, and Trust
- Privacy-enhancing technologies for federated learning
- Secure aggregation protocols and cryptographic methods
- Trustworthy and explainable federated learning systems
- Resilient and robust FL systems against attacks
- Privacy-utility trade-offs in distributed learning
- Auditable and interpretable federated learning frameworks

4- Digital Twins & Cyber-Physical Systems
- Federated intelligence for digital twin ecosystems
- Digital twin generation and maintenance in distributed networks
- Real-time federated learning for cyber-physical system monitoring
- Distributed digital twins for smart cities and industrial IoT
- Federated anomaly detection and predictive maintenance
- Live model updating and synchronization in digital twin networks
- Edge intelligence for decentralized digital twin ecosystems
- Federated optimization for cyber-physical system control

5- Mobile Computing & Wireless Networks
- Federated learning protocols for mobile, vehicular, and edge networks
- FL in 6G networks and next-generation wireless systems
- Multi-agent and swarm intelligence-based federated learning
- Energy-aware and communication-efficient federated intelligence
- Dynamic network topologies and adaptive FL protocols
- Distributed inference and online learning for mobile networks
- Cross-layer optimization for federated learning in wireless systems
- Quality of service and latency-aware federated learning

6- Applications and Real-World Deployments
- Smart cities and urban computing applications
- Autonomous vehicles and intelligent transportation systems
- Industrial IoT and manufacturing intelligence
- Healthcare and medical federated learning systems
- Financial services and fraud detection
- Swarm robotics and distributed autonomous systems
- Environmental monitoring and sustainability applications
- Real-world case studies and deployment experiences
- Economic models and incentive mechanisms for data federations
- Regulatory compliance and legal frameworks (GDPR, EU AI Act, etc.)

7- Emerging Paradigms & Future Directions
- Continual and lifelong learning in federated settings
- Few-shot and zero-shot federated learning
- Federated meta-learning and transfer learning
- Neural architecture search in federated environments
- Generative AI and federated learning convergence
- Quantum-enhanced federated learning
- Federated foundation models and large-scale pre-training
- Neuromorphic computing and federated learning
- Blockchain and distributed ledger technologies for FL
- Sustainable and green federated learning approaches

8- AI & Intelligent Systems for Smart Cities
- AI-driven urban mobility: traffic flow optimization, multimodal transport, autonomous vehicles
- Smart energy: predictive demand response, grid optimization, distributed energy resources
- Urban sensing & IoT: federated and privacy-preserving analytics for large-scale data
- Home and building automation: comfort, safety, and energy efficiency through edge AI
- AI for public safety, emergency response, and disaster resilience
- Urban digital twins: modeling, simulation, and real-time decision-making
- Data governance, ethics, and fairness in city-scale AI deployments
- Cross-domain integration: combining mobility, energy, health, and environment data for holistic intelligence
- Real-world case studies and lessons learned from smart city pilots

9- Communication & Resource Efficiency
- Model Compression & Quantization
- Gradient Compression Techniques
- Sparse Communication Protocols
- Energy-efficient FL
- Bandwidth-constrained Learning
- Adaptive Communication Strategies
- Hierarchical Federated Learning

10- Personalization & Fairness
- Personalized Federated Learning
- Meta-learning for FL
- Fairness-aware FL
- Bias Mitigation Techniques
- Multi-objective FL
- Clustered Federated Learning
- Demographic Parity in FL

11- Edge Computing & IoT
- Edge-Cloud Federated Learning
- IoT Device Orchestration
- Mobile Edge Computing
- Fog Computing Integration
- 5G/6G Network Optimization
- Real-time FL Systems
- Resource-constrained Devices

12- Advanced AI & ML Paradigms
- Federated Reinforcement Learning
- Federated Transfer Learning
- Federated Deep Learning
- Federated Graph Neural Networks
- Federated Generative Models
- Large Language Models in FL
- Neuro-symbolic FL

13- Applications & Use Cases
- Healthcare & Medical AI
- Financial Services & FinTech
- Autonomous Vehicles
- Smart Cities & Infrastructure
- Industrial IoT & Manufacturing
- Natural Language Processing
- Computer Vision Applications

14- Systems & Infrastructure
- FL Frameworks & Platforms
- Distributed System Design
- Hardware Acceleration
- Blockchain-based FL
- Benchmarking & Evaluation
- Simulation Environments
- Performance Optimization

15- Emerging & Interdisciplinary
- Quantum Federated Learning
- Federated Continual Learning
- Cross-modal Federated Learning
- Federated Causal Inference
- Sustainable & Green FL
- Human-in-the-loop FL
- Federated Explainable AI

Submission Types:
- Research Papers (up to 8 pages): novel methods/systems with rigorous evaluation.
- Short Papers (up to 6 pages): promising early results, negative results with analysis, replication.
- Poster (up to 2 pages)
- Artifacts & Demonstrations (up to 6 pages).

Format:

Paper format All papers should be in PDF format. Please make use of the appropriate IEEE template for conference proceedings to prepare your revised manuscript. Failure to do so may result in excluding your paper from the conference proceedings. IEEE Word template can be found here (IEEE Conference Word Template). IEEE Latex template can be found here (IEEE Conference Latex Template). IEEE Overleaf Latex template can be found here (IEEE Overleaf Conference Latex Template).

Important Dates Paper submission:
- February 20th, 2026
- Notification of acceptance: April 15th, 2026
- Camera-ready deadline: May 5th, 2026
All deadlines are in Anywhere on Earth (AoE) time.

- Submission Portal Papers should be submitted through Easychair at: https://easychair.org/conferences/?conf=flics2026
- For submission guidelines, please visit: https://flics-conference.org/submission.php

Contact Information For questions about submissions, please contact: intelligent.systems2026@gmail.com Sadi Alawadi: sadi.alawadi@bth.se

We look forward to receiving your contributions and to seeing you at FLICS 2026!