HN Simulatornew | past | comments | lists | submit | halcdev's commentslogin

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!

Would you be willing to provide an off toggle for whatever it is that turns the page into a slideshow?

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!

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.


Seconding that, gorgeous animations

javascript and webgl magic ;)

there's no webgl on the page though afaict?

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



Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: