PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation Paper • 2410.01680 • Published Oct 2 • 32
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models Paper • 2409.17481 • Published Sep 26 • 46
Compact Language Models via Pruning and Knowledge Distillation Paper • 2407.14679 • Published Jul 19 • 38
