FINALITY Training Event 2 INRIA PhD Summer School – September 8-11, 2026

FINALITY Training Event 1 – Avignon, April 20-24, 2026
26 March 2026

Training Event programme: 

September 8, 2026 - day 1


9:00-10:30

Keynote: Distributed AI at the Edge - Alexandru Dobrila (Hivenet/Antimatter)

10:30-11:00

Coffee break

11:00-12:30

Distributed inference in the edge-network-cloud continuum - Frédéric Giroire (CNRS)

12:00-14:00

Lunch

14:00-15:30

The Road to Autonomous Networks: AI/ML Foundations and Frontiers - Farnaz Moradi (Ericsson)

15:30-15:45

Coffee break

15:45-17:00

Students Presentations (Session 1)

 

September 9, 2026 - day 2


9:00-10:30

Keynote: AI in radio access networks: challenges and open problems - Zwi Altman (Orange Lab)

10:30-11:00

Coffee break

11:00-12:30

Bayesian optimization: Theory and applications to telecommunications - Lorenzo Maggi (NVIDIA)

12:00-14:00

Lunch

14:00-15:30

Panel: Application and Role of AI in Industry

Panelists:

- Zwi Altman (Orange)

- Alexandru Dobrila (Hivenet/Antimatter)

- Lorenzo Maggi (NVIDIA)

- Farnaz Moradi (Ericsson)


15:30-15:45

Coffee break

15:45-17:00

Students Presentations (Session 2)

19:00

Social Dinner at restaurant: l’Atelier 67

 

September 10, 2026 - day 3


9:00-10:30

Robust Machine Learning: A Quest to Learning in Untrusted Environment (I) - Nirupam Gupta (University of Copenhagen)

10:30-11:00

Coffee break

11:00-12:30

Reinforcement learning: from bandits to structured MDPs (I) - Bruno Gaujal (Inria)

12:00-14:00

Lunch

14:00-15:30

Student Presentations (Session 3)


15:30-15:45

Coffee break

15:45-17:00

Students Presentations (Session 4)

 

September 11, 2026 - day 4


9:00-10:30

Robust Machine Learning: A Quest to Learning in Untrusted Environment (II) - Nirupam Gupta (University of Copenhagen)

10:30-11:00

Coffee break

11:00-12:30

Reinforcement learning: from bandits to structured MDPs (II) - Bruno Gaujal (Inria)

12:00-14:00

Lunch

14:00-15:30

Student Presentations (Session 5)


15:30-16:00

Coffee break

 

 

Student Presentations: 

September 8, 2026

Session 1: Efficient Edge Inference

Léo Bernard (INRIA)

Threshold-based Routing for Energy-efficient Experts

Kyrylo Tymchenko (INRIA)

Confidence-Shaped Regression Cascades for Efficient Edge Inference

 

September 9, 2026

Session 2: Resource Allocation and Efficient Training

Isidoor Pinillo Esquivel (DC8 FINALITY)

Quantized Online Gradient Descent for Constant-Time Caching with Dynamic Regret Guarantees

Mariya Peter (DC15 FINALITY)

Fairness-Aware Optimal Transport Framework for Flow Allocation in Interconnected Network Systems

Nicolas Helson (Avignon Université)

Network-Adaptive Gradient Compression for Faster ML Model Training in Datacenters

 

September 10, 2026

Session 3: Federated Learning: Fairness, Robustness, and Unlearning

Neeraja Sudhakaran (DC14 FINALITY)

Towards Fair Federated Learning: Analyzing the Impact of Data Heterogeneity and Data Repair

Jingye Wang (DC7 FINALITY)

The Praetorian Guard: Unveiling the Vulnerability of Trust-Based Defense in Federated Learning

Florian Zimmer (Fraunhofer)

Enabling Decentralised Federated Unlearning in Industrial Cross-Organisational Environments

Panos Raptis (DC3 FINALITY)

Dynamic Fairness in Multi-Task Edge Learning

 

September 10, 2026

Session 4: Reinforcement Learning and AI-Driven Network Intelligence

Sooraj Skanda (DC11 FINALITY)

Model-Based Multi-Agent Reinforcement Learning for Integrated Sensing and Communication

Andreas Pattichis (DC13 FINALITY)

Continual Learning from Streams of Unlabeled Data in LLM Systems

Michele Simeone (DC6 FINALITY)

Exploring KPI Trade-offs in O-RAN Conflict Resolution with Deep Reinforcement Learning

Luigi Rachiele (DC5 FINALITY)

From Fixed Pipelines to Agentic Decisions: An LLM Orchestrator for Anomaly Detection in Mobile Network Drive Tests

 

September 11, 2026

Session 5: Learning and Control under Resource Constraints

Muyun Li (DC10 FINALITY)

RL-based Edge Access Control for Time-Sensitive Tasks under Resource Contention

Oihan Azkarate Iriarte (DC1 FINALITY)

Optimal Control and Learning of Tandem Queues with Transfer Costs

Haoming Lin (DC7 FINALITY)

Structure of Optimal Admission Control under Resource Constraints

Berfin Dinc (DC2 FINALITY)

Closed-Loop Control with Delayed Information