Hazy shows an MLP can be initialized with knowledge and queried by a transformer

andrew_n_carr · x · 2026-07-23

A post highlights a Hazy research result suggesting that an MLP can be initialized with knowledge already inside it, without any training, and that a transformer can then query and use that knowledge properly.

The implication is that knowledge can be embedded into the network at initialization time rather than learned only through gradient descent. The poster frames it as an intriguing step toward continual learning.

Related event: Hazy Research Reveals Knowledge Injection via MLP Initialization(2 posts)→

Original post →

More from Research

Research channel →