I ran across this two-part interview with Yann Le Cunn and I thought it gave a pretty good broad overview/background into JEPA: https://www.youtube.com/watch?v=kYkIdXwW2AE

Are there any pre-trained models / implementations of this, like vllm style, or are we still early into this architecture?

It looks like LeJEPA is sub-1B params and tested on vision tasks? (https://github.com/galilai-group/lejepa)

I had assumed the JEPA family will also be multimodal and agentic capable, perhaps just needs them scaling laws applied?

LeCun's new paper takes a new approach to building JEPA, which he named LeJEPA -- https://arxiv.org/abs/2511.08544 It's not that different in the underlying theory but he removes the EMA and the twin tower, makes the whole thing more straightforward.

It's mentioned in the article

Okay I see it now, but it's briefly mentioned without describing the mechanism. The author didn't annotate it the same way they annotated JEPA. I feel like LeJEPA should take precedence in the article since it supersedes JEPA.

LeCun's even newer paper takes a new approach to building JEPA, which he named Ada-JEPA: https://arxiv.org/html/2606.32026v1

No AdaJEPA is a deployment-time mechanism, it's not about building JEPA at all

Seems like a pretty good article to sit down and type out the code and spend an afternoon learning.

What's the tell? It doesn't seem AI generated to me but I may not be a great judge.

There's no tell. Some people just have an overactive imagination and are hallucinating AI authorship wherever they go. I think the HN audience is especially susceptible to this given the amount of comments like GP. Don't get me wrong, there is certainly AI-slop to go around, but this is just a very well-written article in my opinion. At most, lightly edited. It reads like a human wrote it, but maybe I'm just gullible.

"To keep the discussion concrete,"