🜂 kompress.vaked.dev learnable context compression · open science

kompress ∞

Asymmetric Loss Modulation Resolves the Voting Ensemble Paradox in Learned Context-Pruning Ensembles. An open-science manuscript: formalised, proven, and fixed — with every model, dataset and line of code in the open.

17 models · 8 teachers · 4 architectures · $38.95 total

the manuscript

the number

0.955heretic-exact @ 15% compression
0.993exact-keep rate
~78%token savings
149MModernBERT base

everything else