That is pretty cool. I found a follow up work that applies this technique to LLM...

		mlajtos on Aug 4, 2024 \| parent \| context \| favorite \| on: Self-Compressing Neural Networks That is pretty cool. I found a follow up work that applies this technique to LLM: https://konczer.github.io/doc/Poster_EEML23_JozsefKonczer.pd...