COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression Paper • 2602.15200 • Published Feb 16 • 8
ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression Paper • 2602.11008 • Published Feb 11 • 18
ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization Paper • 2505.02819 • Published Feb 19 • 26
Iterative Self-Training for Code Generation via Reinforced Re-Ranking Paper • 2504.09643 • Published Apr 13, 2025 • 34
