Can JEPA Bridge Graphs and Language?

Tuesday 11 Nov 2025, 09:00 → 10:00 Europe/Berlin

• Speaker: Nicolo Brandizzi
• Abstract: This presentation will introduce the core concepts of the Joint Embedding Predictive Architecture (JEPA) framework proposed by Yann LeCun, highlighting its shift from reconstruction-based to predictive latent modeling as a foundation for autonomous and energy-efficient AI systems.
  
  Building on these ideas, I will outline an experimental extension that applies JEPA principles to align graph and text representations. The approach combines a graph encoder (e.g., Graph Neural Network) and a text encoder (e.g., MiniLM or LLM embedding layer) trained with a predictive latent objective, e.g. encouraging mutual consistency between structural and semantic information.