Where Grokking Happens: Distributed Utility and Fourier Recoding Without a Module Switch
This story is from 2026-09-17. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.17571v1 Announce Type: new Abstract: Where in a Transformer is the change from memorization to generalization functionally expressed? We introduce Transition Games--behavior-aligned exact activation games with paired non-generalizing controls--and find distributed utility gain with a pro…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-17 04:00 · arXiv cs.LG
Where Grokking Happens: Distributed Utility and Fourier Recoding Without a Module Switch