English(EN) MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization

新的MARR技术提升了LLM和ViT的低比特量化性能

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-18 07:51

研究人员开发了一种名为模块自适应残差重构（MARR）的新技术，以改进大型语言模型和视觉变换器的低比特训练后量化。MARR通过自适应地平衡不同模型模块之间的误差校正和偏差来解决现有方法的局限性。该方法使用特定于模块的缩放系数和基于PID的更新策略来优化系数，从而在4位或更低的量化级别上带来显著的性能提升。 AI

影响通过改进低比特量化技术，提高了LLM和ViT的效率。

排序理由详细介绍模型量化新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍模型量化新方法的学术论文。[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, model release; 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: 142 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]

arXiv cs.CV TIER_1 English(EN) · Zhi Jin · 2026-05-18 07:51

MARR：低比特训练后量化的模块自适应残差重构

Recently, residual reconstruction-based model quantization methods have achieved promising performance in low-bit post-training quantization (PTQ) by introducing cross-layer residuals to reduce error accumulated from previous layers.However, these residuals may also introduce add…

本文如何被排名

报道来源 [1]

MARR：低比特训练后量化的模块自适应残差重构

相关实体

相关话题