Mlp Residual Stack
1 mentions across 0 people
All mentions
Unknown speaker
Recommendedpaper · 2026-06-10
“We study the simplest architecture for which the analogy is tractable: a pure MLP residual stack trained on masked token prediction over synthetic Markov chain sequences with known spectral properties.”
Quantitative Evidence That MLP Residual Networks Implement Selective Renormaliza ↗