Showing 2026Show all
3 papers · 1 filter
cs.LG2026
GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression
Baher Mohammad, Ammar Ali, Stamatios Lefkimmiatis
Transformer architectures exhibit cross-layer redundancies, yet post-training compression pipelines typically optimize layers in isolation or rely on heuristic grouping strategies…
cs.LG2026
COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression
Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip +3
Post-training compression of transformer models commonly relies on truncated singular value decomposition (SVD) strategies leading to low-rank approximations of the original model…
cs.LG2026
ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression
Ammar Ali, Baher Mohammad, Denis Makhov +3
We present ROCKET, a training-free model compression method that achieves state-of-the-art performance in comparison with factorization, structured-sparsification and dynamic compr…