BudgetMem: Training-Free Selective Memory for Cost-Efficient Long-Context Processing in Language Models
BudgetMem is introduced, a training-free architecture that keeps only high-salience content under an explicit memory budget that makes chunk-level keep-or-discard decisions from interpretable features: entity density, TF-IDF importance, position, numerical density, discourse markers, and question presence.
Chandra Vamsi Krishna Alla, Harish Naidu Gaddam, Manohar Kommi et al.
· 0 citations