English(EN) ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures

新的ONNX-Net系统实现了通用的神经架构表示

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-27 04:00

研究人员开发了ONNX-Net，这是一种创建神经架构通用表示的新方法，旨在克服现有方法受限于特定搜索空间的局限性。该系统利用ONNX文件以统一格式表示各种神经网络，从而允许单个性能预测器跨不同架构进行泛化。基于文本的编码可以容纳任意的层类型和参数，从而能够通过强大的零样本性能即时评估架构。 AI

影响能够跨不同搜索空间更快、更灵活地评估神经网络架构。

排序理由该集群包含一篇学术论文，详细介绍了神经架构表示和性能预测的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

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: 23 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了神经架构表示和性能预测的新方法。[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。

arXiv cs.CL TIER_1 English(EN) · Shiwen Qin, Alexander Auras, Shay B. Cohen, Elliot J. Crowley, Michael Moeller, Linus Ericsson, Jovita Lukasik · 2026-08-27 04:00

ONNX-Net：面向神经网络架构的通用表示和即时性能预测

arXiv:2510.04938v2 Announce Type: replace-cross Abstract: Neural architecture search (NAS) automates the design process of high-performing architectures, but remains bottlenecked by expensive performance evaluation. Most existing studies that achieve faster evaluation are mostly …