PulseAugur
中
实时 21:32:00
English(EN) Single-prompt evals can't surface stateful failures. YANAMI is a new multimodal dataset and benchmark built for multiturn, stateful interaction — the eval desig

新的 YANAMI 数据集针对多模态人工智能模型中的有状态交互

研究人员推出了 YANAMI,这是一个新的大规模多模态数据集和基准,旨在评估统一多模态模型 (UMMs) 中的有状态交互。当前的 UMM 在需要跟踪多轮对话中不断变化的对话状态的任务时经常遇到困难,YANAMI 旨在解决这一局限性。该数据集包含 400,000 个对话和超过 200 万张图像,涵盖图像编辑和视觉推理等场景,并评估对话状态理解和视觉实现。 AI

影响 该数据集可以通过更好地评估多模态人工智能代理在交互过程中保持上下文和状态的能力来推动其改进。

排序理由 该集群描述了一个用于评估多模态人工智能模型的新数据集和基准,属于研究范畴。

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的 YANAMI 数据集针对多模态人工智能模型中的有状态交互

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
Research
该集群描述了一个用于评估多模态人工智能模型的新数据集和基准,属于研究范畴。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
7 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 [2]

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

    YANAMI:面向多轮有状态交互的大规模多模态数据集和基准测试

    YANAMI introduces a large-scale multimodal dialogue dataset and benchmark for stateful interaction, requiring models to track and realize evolving dialogue states across turns, and reveals that current unified multimodal models still struggle with this task.

  2. Mastodon — mastodon.social TIER_1 English(EN) · vinpatel ·

    单提示评估无法暴露有状态的失败。YANAMI 是一个新构建的多模态数据集和基准,用于多轮、有状态交互——评估设计

    Single-prompt evals can't surface stateful failures. YANAMI is a new multimodal dataset and benchmark built for multiturn, stateful interaction — the eval design that agentic model testing has been missing. Worth a close look if you're working on LLMs or agentic # AI # LLM https:…