Comment by rfv6723
12 hours ago
> using imagenet-1k for pretraining
Lecun still can't show JEPA competitive at scale with autoregressive LLM.
12 hours ago
> using imagenet-1k for pretraining
Lecun still can't show JEPA competitive at scale with autoregressive LLM.
It's ok, autoregressive LLMs are a dead end anyway.
Source: Y. LeCun.