SCHEDULE

Opening Session

• • [10:30 - 10:40] Welcome and introduction to the Green-Aware AI workshop

Paper Presentations - Session 1

• • [10:40 - 11:00] On the Environmental Impact of the Algorithm LatentOut for Unsupervised Anomaly Detection (F. Angiulli et al.)

  • [11:00 - 11:20] A Lightweight Meta-Feature Extraction Strategy for Deep Reinforcement Anomaly Detection (S. Amirato et al.)

  • [11:20 - 11:40] DPET: A Data and Parameter Efficient Training Framework for Green-AI  (F. Scala et al.)

  • [11:40 - 12:00] Exploiting Outlier Explanation to Unveil Key Aspects of High Green Comparative Advantage Nations (F. Angiulli et al.)

  • [12:00 - 12:20] Enhancing the Evaluation of Fault Detection Models in Smart Agriculture Using LLM Agents for Rule-Based Anomaly Generation (P. Lindia et al.)

Invited Talk  [45’ + 15’ Q&A]  

• • [13:40 - 14:40] AI Alignment and Normative Reasoning (Prof. Kees van Berkel, Institute for Logic and Computation, TU Wien)

Paper Presentations - Session 2

• • [14:40 - 15:00] A Declarative Framework for Temporal Reasoning in Green-Aware Applications (G. De Giacomo et al.)

  • [15:00 - 15:20] Optimizing Photosensor Placement for Energy-Efficient Lighting in Sustainable Building Design Based on Multivariate Long Short-Term Memory Models (G. Potenza et al.)