English(EN) Errors as Data: How RSI Helps OXR Achieve SOTA Accuracy and Speed in Document Parsing

OXR-1.0模型使用递归自我改进进行文档解析

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 00:01

一款名为OXR-1.0的新文档解析模型采用了递归自我改进（RSI）技术，以实现最先进的准确性和速度。该方法涉及模型识别其在未标记文档中的自身错误和不确定性，然后根据这些已识别的弱点生成有针对性的训练数据。此过程无需对生成的数据进行手动标注，即可使OXR-1.0在文档解析基准测试中持续改进其性能。 AI

影响该模型从错误中学习的方法有望为专业AI任务的训练效率设定新标准。

排序理由新模型发布，附带性能基准测试。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

在 Towards 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: 51 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Significant; 新模型发布，附带性能基准测试。[lever_c_demoted from frontier_release: 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: model release, product; 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]

Towards AI TIER_1 English(EN) · Binyang · 2026-10-28 00:01

错误即数据：RSI如何助力OXR在文档解析中实现SOTA准确性和速度

<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*_E2af_d1vxwuzgPQccjZ8Q.png" /></figure><blockquote>xxSummary: What if every document a model gets wrong told you what to train on next? That’s the loop behind OXR, a 1.3B model that …

本文如何被排名

报道来源 [1]

错误即数据：RSI如何助力OXR在文档解析中实现SOTA准确性和速度

相关实体

相关话题