Thanks! Glad to know it works for most people. I reduced the bg animation intensity.

Sorry about that- will investigate. What OS/browser are you using?

Older intel macs initially have quite large blank areas of scroll while the figures later in the page render.

Much better after scrolling through and then reloading.

Android and firefox

Let me know if you have any questions

Let me know if you have any questions!

I knew close to nothing about JEPA before reading your post, but i was under the impression this was supposed to be a contender for LLM's limitations, a way to do things "properly".

However, based on this article, i have the feeling that on the contrary, JEPA is filling a super niche problem, and is pretty much only trying to improve robotic motions in space.

Which of the two ideas is it ? Can JEPA technics be applied to a much more wide range of problems ? (like LLM and transformers)

JEPA can be applied to text as well in the sense you can use it to build text embedding models, freeze your JEPA text embedder, then train a decoder over the top of that.

OF course your decoder model could end up doing a lot of the heavy lifting if your decoder loss was based on text reconstruction methods (which almost all LLMs use for eval purposes)

For certain tasks, you do need pixel/token level reconstruction fidelity to do a lot of things. Like image generation or text generation.

For other tasks, having a coherent representation of the world that can be computed quickly and intuitively is more salient. I suspect the human mind works more like JEPA than like an autoregressive LLM. Human children train on far less data to achieve extreme fidelity on a lot of tasks generative reconstruction loss based AI/ML techniques struggle with.

I wanted to know how you made these animations, they look gorgeous!

Seconding that, gorgeous animations

javascript and webgl magic ;)

there's no webgl on the page though afaict?

The animations use custom vanilla JS, Canvas 2D, SVG, and a WebGL shader.

https://haddyalchaer.com/stories/jepa/figures.js

Based on the colors and how it looks, it seems like Astra generated them.

Thanks for doing this!

Basic question: couldn't something like probabilistic roadmaps [1] trivially solve this? Or am I missing something about the limitations of PRM's?

And if so, is that the best test for JEPA?

[1]:https://en.wikipedia.org/wiki/Probabilistic_roadmap

Surely it's a bit more distributed than that, right?

Like how AWS has global datacenters, but everyone uses us-east-1.

and every other region's control plane is in us-east-1

Nope.

https://xkcd.com/908/

The original : https://eprint.gacr.info/2025/001/

He finally defeated life

While normally making jokes after a person's death would be socially questionable, in this case Chuck Norris himself loved the Chuck Norris jokes. For me at least, a good sense of humor is maybe the most endearing personality trait. RIP

Fundamentally, I'd argue that very little should ever be unreasonable or out of bounds to make jokes about; what is important is that it's good humour.

Case in point: https://theonion.com/hijackers-surprised-to-find-selves-in-h...

And, as you say, in Chuck Norris' case, it's virtually obligatory.

> Fundamentally, I'd argue that very little should ever be unreasonable or out of bounds to make jokes about; what is important is that it's good humour.

On a personal level, I couldn't agree more. I do hope that culturally we get to that point at some time :-)

I mean, jokes are made to uplift, intent in joking is important and punching up is preferable to punching down, this being said this didn't apply to chuck Norris that would have already got to the punchline without throwing a single fist.

Giving people reason to laugh while you are old and dying is a superpower. I wish i will have it, too.

52k members... wow

You are obviously wrong, but that's not the issue here. One can't help wondering what prompted you to say such an unkind thing in the extreme about 1.2 billion monthly active users. On second thought, no need to answer that here. It's the kind of food for thought that is best left undebated.

being unkind doesn't mean being wrong.

Imagine if you could come up with a way to get ‘em to cough up a dollar.

Created by R74N, not Neal. Has been live on http://sandboxels.r74n.com as an independent project for several years. Just now hosted by Neal. Important distinction.

R74N wrote about its new home here https://sandboxels.r74n.com/new-home

it doesn't answer the first question I have, which is basically "why". not in any sort of hostile sense, just that it would be very interesting to hear the back story behind this move.

I thought I remembered something about that

Hello