←back to thread

789 points MindBreaker2605 | 1 comments | | HN request time: 0.306s | source
Show context
gregjw ◴[] No.45897653[source]
Interesting he isn't just working with Feifei Li if he's really interested in 'world models'.
replies(3): >>45897794 #>>45898810 #>>45905955 #
dauertewigkeit ◴[] No.45898810[source]
Correct me if I'm wrong but LeCun is focused on learning from video, whereas Fei-Fei Li is doing robotic simulations. Also I think Fei-Fei Li's approach is still using transformers and not buying into JEPA.
replies(1): >>45903109 #
Legend2440 ◴[] No.45903109[source]
JEPA is not an alternative to transformers, it is built out of transformers.
replies(1): >>45905511 #
1. HarHarVeryFunny ◴[] No.45905511[source]
JEPA is trying to learn real world regularities by predicting internal perceptual representations (using a transformer).

It seems a good direction to go in, but tbh he doesn't seem to have taken it very far, and it is the transformer doing all the heavy lifting.