Performance collapse in layer-pruned LLMs stems from disrupting the Silent Phase of decision-making, which blocks the transition to correct predictions, while the later Decisive Phase is robust to pruning.
Pocketllm: Ultimate compression of large language models via meta networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
BiSCo-LLM achieves near-FP16 accuracy on Qwen3-8B at ~2 bits/weight using codebook-free binary spherical codes with residual coding and category-wise recovery distillation.
citing papers explorer
-
Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions
Performance collapse in layer-pruned LLMs stems from disrupting the Silent Phase of decision-making, which blocks the transition to correct predictions, while the later Decisive Phase is robust to pruning.
-
BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression
BiSCo-LLM achieves near-FP16 accuracy on Qwen3-8B at ~2 bits/weight using codebook-free binary spherical codes with residual coding and category-wise recovery distillation.