English(EN) SARATHI: Decoupled Data-Free Probing and Adaptive Reconstruction for Structured LLM Pruning

新的SARATHI框架增强了结构化LLM剪枝

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员推出SARATHI，一个旨在改进大型语言模型（LLM）结构化剪枝的新颖框架。该方法将神经元选择和权重重构阶段解耦，解决了先前将这些过程耦合在一起的方法的局限性。SARATHI使用无数据的NMF残差子空间探测器进行神经元评分，并使用自适应OBS组件进行权重重构，显著降低了内存需求。偏置偏移补偿步骤通过纠正激活漂移（尤其是在LayerNorm后的架构中）进一步提高了性能。实验证明了SARATHI在各种模型和稀疏度水平上的有效性，实现了具有竞争力的困惑度和零样本准确率。 AI

影响这项研究可能通过结构化剪枝降低推理成本，从而实现更高效的LLM部署。

排序理由该集群包含一篇详细介绍LLM剪枝新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

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

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍LLM剪枝新方法的论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Sankar Behera, Dhruv Singh, Satyadev Ahlawat, Yamuna Prasad · 2026-10-15 04:00

SARATHI: 结构化大模型剪枝的解耦无数据探测与自适应重构

arXiv:2610.15514v1 Announce Type: cross Abstract: Structured pruning reduces the inference cost of large language models (LLMs) by permanently removing neurons and weight rows, yielding dense, hardware-agnostic speedup. Existing post-training methods couple neuron selection and w…

本文如何被排名

报道来源 [1]

SARATHI: 结构化大模型剪枝的解耦无数据探测与自适应重构

相关实体

相关话题