AIBullisharXiv – CS AI · 18h ago6/10
🧠
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
Researchers introduce Ghosted Layers, a training-free method to recover performance degradation in layer-pruned large language models by solving an activation alignment problem through optimal linear operators. The technique uses a small calibration set to reconstruct hidden state mismatches introduced by pruning, maintaining efficiency gains while improving accuracy and perplexity across multiple LLM architectures.
🏢 Perplexity