neuron-pruning

Tag

Cards List
#neuron-pruning

GS-MoE: Training-Free MoE Compression via Groupwise Subspace Sharing and Pruning

arXiv cs.LG ↗ · 2026-10-27 Cached

GS-MoE 介绍了一种免训练的 MoE 压缩框架,通过分组子空间共享(低秩)与基于 Nyström 的神经元剪枝两条压缩轴同时削减专家参数;在 DeepSeek-MoE-16B-Base 上以 60% 参数压缩保留约 90% 的推理性能,优于 D2-MoE 的 73%。

0 favorites 0 likes
#neuron-pruning

Prune the Leaky Neurons: Mitigating Private Data Leakage in Fine-Tuned LLMs via Joint-Embedding-Guided Pruning

arXiv cs.CL ↗ · 2026-10-19 Cached

提出JEPA-Prune框架,通过联合嵌入引导的后验神经元剪枝,在仅剪枝1.6%神经元的情况下将PII推断准确率降低最多7.4倍,同时基本保持模型效用。

0 favorites 0 likes
#neuron-pruning

TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts

arXiv cs.LG ↗ · 2026-06-10 Cached

TENP proposes a structured pruning framework for Mixture-of-Experts LLMs that retains important experts and applies neuron pruning to less important ones, achieving high sparsity with minimal accuracy loss on Qwen and DeepSeek models.

0 favorites 0 likes
← Back to home

Submit Feedback