COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression
Paper
•
2602.15200
•
Published
•
5
Denis Makhov
dennismak1994
AI & ML interests
None yet
Recent Activity
authored
a paper
about 22 hours ago
COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression
authored
a paper
about 22 hours ago
ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression
authored
a paper
about 22 hours ago
COSPADI: Compressing LLMs via Calibration-Guided Sparse Dictionary
Learning
Organizations
None yet