Geometric deep learning (graph neural networks, manifold learning) should be applied to JEPA: training JEPA architectures on graph-structured inputs has not been done yet but would be very interesting and promising to explore.

forecastpending

Speaker

Yann LeCun

Evidence Quote

Now, the connection with graph neural nets, I don't think anyone has done this yet, like train a Jepa whose input is, you know, a graph, essentially. Uh I think that would be super interesting to experiment with.

Source

Yann LeCun: Special Lecture on AI and World ModelsAl-Khwarizmi Applied Mathematics Webinar
Created: 8/12/2026, 10:03:11 PM

My Notes

Loading notes...