Showing 2025Show all
3 papers · 1 filter
cs.CE2025
Compressing Large Language Models with PCA Without Performance Loss
Magnus Bengtsson
We demonstrate that Principal Component Analysis (PCA), when applied in a structured manner, either to polar-transformed images or segment-wise to token sequences, enables extreme…
cs.LG2025
C2G-KD: PCA-Constrained Generator for Data-Free Knowledge Distillation
Magnus Bengtsson, Kenneth Östberg
We introduce C2G-KD, a data-free knowledge distillation framework where a class-conditional generator is trained to produce synthetic samples guided by a frozen teacher model and g…
math.OC2025
Warehouse storage and retrieval optimization via clustering, dynamical systems modeling, and GPU-accelerated routing
Magnus Bengtsson, Jens Wittsten, Jonas Waidringer
This paper introduces a warehouse optimization procedure aimed at enhancing the efficiency of product storage and retrieval. By representing product locations and order flows withi…