PulseAugur
中
实时 06:01:53
English(EN) DIVE: Benchmarking Full-Duplex Interaction with Visual Engagement in Continuous Streams

新的DIVE基准测试实时多模态LLM交互

研究人员推出了DIVE,这是一个旨在评估多模态大语言模型(MLLM)在连续、实时交互场景中的新基准。与专注于带时间戳问答的现有基准不同,DIVE评估了模型在不断变化的视听流中识别相关线索、决定何时响应以及保持参与的能力。该基准包括在三种交互场景(主动干预、持续参与和交互协调)中的六项任务,使用了525个带注释的音频/视频样本。对当前实时模型的初步实验显示了亚秒级的响应延迟,但表明在将持续响应调整为新信息方面存在挑战,平均窗口响应率不超过53.77%。 AI

影响 该基准测试有望推动更自然、更强大的实时多模态交互式AI系统的进步。

排序理由 该集群包含一篇介绍用于评估AI模型的新基准的研究论文。

在 arXiv cs.AI 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DIVE基准测试实时多模态LLM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
Tool
该集群包含一篇介绍用于评估AI模型的新基准的研究论文。
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, 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
4 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. arXiv cs.AI TIER_1 English(EN) · Yuhang Chen, Guangyue Liu, Shilong Liu ·

    DIVE:在连续流中通过视觉参与对全双工交互进行基准测试

    arXiv:2610.28405v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) have substantially improved spoken interaction and video understanding. Existing online and streaming benchmarks primarily assess causal multimodal perception through times…