PulseAugur
中
实时 08:51:42
English(EN) Automatic Tensor-level Execution of Abstract Interpreters for Neural Networks

Neuton框架自动化神经网络认证器创建

一个名为Neuton的新框架已被开发出来,可自动将神经网络的神经元级抽象解释器规范转换为张量级可执行文件。这项创新旨在通过消除手动张量编程的需求来简化新DNN认证器的创建。Neuton引入了一个具有形状分析的中间表示,用于处理隐式张量操作,用于优化的特定领域重写规则,以及一种称为gBCSR的新型稀疏张量格式。评估表明,Neuton可以编译现有认证器并实现新的认证器,提供精度-运行时权衡,并与手动优化的库相比具有竞争力。 AI

影响 简化了新DNN认证器的开发,可能加速AI中形式化验证方法的研究和应用。

排序理由 研究论文,详细介绍了用于自动化神经网络认证器创建的新框架。[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 →

Neuton框架自动化神经网络认证器创建

本文如何被排名

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
研究论文,详细介绍了用于自动化神经网络认证器创建的新框架。[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]

  1. arXiv cs.CL TIER_1 English(EN) · Avaljot Singh, Yasmin Chandini Sarita, Aditya Mishra, Gagandeep Singh, Charith Mendis ·

    面向神经网络的抽象解释器的自动张量级执行

    arXiv:2507.20055v2 Announce Type: replace Abstract: Developing new abstract interpretation-based DNN certifiers is difficult because their mathematical design is expressed at the neuron level, while implementations must operate at the tensor level. Existing libraries such as auto…