PulseAugur
中
实时 17:55:31
English(EN) WOVEN: Weaving Visual World Modeling into Multimodal LLMs

新的WOVEN基准测试旨在解决多模态大语言模型在视觉推理方面的差距

研究人员推出WOVEN,这是一个新的基准测试和训练数据集,旨在提高多模态大语言模型(MLLMs)的视觉过渡推理能力。尽管取得了进展,但目前的MLLMs在空间、具身和时间推理方面仍存在显著缺陷,WOVEN数据集通过在各种场景、动作和推理类型中组织监督数据来解决这些问题。对包括GPT-5.4和Qwen3-VL-235B-A22B在内的38个前沿MLLMs的评估显示,与人类相比存在显著的性能差距,规模的提升带来的改进很小。然而,在WOVEN上进行训练表明,即使是小规模的数据子集也能培养出广泛迁移的可重用能力,从而提高在众多外部基准测试上的性能,并为MLLMs中的视觉世界建模提出了一种新的训练方法。 AI

影响 建立了一个新的基准测试和训练方法,以解决多模态大语言模型在视觉推理方面的根本性缺陷,有可能提高其在现实世界中的应用能力。

排序理由 发布了一篇介绍多模态大语言模型基准测试和训练数据集的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 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WOVEN基准测试旨在解决多模态大语言模型在视觉推理方面的差距

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
发布了一篇介绍多模态大语言模型基准测试和训练数据集的学术论文。[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
31 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]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    WOVEN:将视觉世界建模编织进多模态大语言模型

    Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning. We hypothesize that these failures reflect a shared deficit in visual transition reasoning, and test whether this capability can serve as a shared training primitive, one t…