PulseAugur
实时 08:31:29

新的对比学习课程训练多模态大语言模型以高效使用缩放工具

研究人员开发了一种新的方法来训练多模态大语言模型(MLLMs),使其能够高效地使用缩放工具,而无需进行大量的监督微调。该方法利用了 InfoNCE 风格的奖励,并以对比负面工具调用的课程作为训练信号。在 HRBenchMME-RealWorld 等基准测试上的实验表明,该方法具有竞争力且效率更高,即使在直接替代监督微调时也优于基线。还引入了一个名为 Muffin&Chihuahua 的新数据集,专门用于衡量缩放能力,结果显示召回率与最终任务性能高度相关。 AI

影响 引入了一种更高效的 MLLMs 训练方法,有望提高它们处理高分辨率图像和复杂视觉任务的能力。

排序理由 详细介绍多模态大语言模型新训练方法的学术论文。[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 →

新的对比学习课程训练多模态大语言模型以高效使用缩放工具

本文如何被排名

Signal score
17 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
详细介绍多模态大语言模型新训练方法的学术论文。[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
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) · Falko Helm, Iryna Gurevych ·

    使用对比课程高效学习Zoom

    arXiv:2609.03206v1 Announce Type: cross Abstract: Using a zoom-in tool is an important foundational part of modern visual agents, because it allows to efficiently handle tasks involving high-resolution images. Most previous methods need an extensive warm-start supervised fine-tun…