PulseAugur
中
实时 22:17:23
English(EN) Prox: Training-Free FFN Activation Sparsity via Approximate Intermediate-Channel Salience in LLMs

新的Prox方法通过前馈网络激活稀疏性提高LLM效率

研究人员开发了一种名为Prox的新型无训练方法,通过稀疏化其前馈网络(FFNs)来提高大型语言模型(LLMs)的效率。Prox利用SwiGLU激活的中间状态作为通道选择信号,并对其进行近似以降低计算成本。这种方法可以在模型质量没有显著下降的情况下实现FFN的稀疏执行,在各种LLM上优于现有的无训练方法,并实现了显著的加速。 AI

影响 该方法通过优化大型语言模型的计算路径,可以显著降低其推理成本和延迟。

排序理由 详细介绍LLM效率新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的Prox方法通过前馈网络激活稀疏性提高LLM效率

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍LLM效率新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
69 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Jinyi Liu, Wei Chen, Pengyu Chen, Xinyi Yuan, Minghe Bai, Guoquan Wu, Jun Wei ·

    Prox:LLM中通过近似中间通道显著性进行无训练的FFN激活稀疏性

    arXiv:2607.27591v1 Announce Type: cross Abstract: Feed-forward networks (FFNs) dominate memory traffic and computation in large language model (LLM) inference, making them a primary target for activation sparsification. However, existing training-free methods suffer substantial m…