PulseAugur
中
实时 09:46:26
English(EN) Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning

新基准评估AI的主观视角视频操控和工具使用技能

研究人员推出了Ego2Act,这是一个旨在评估视频生成模型在主观视角视频中执行目标导向操作能力的新基准。该基准包含跨越110个现实世界任务的2,640个视频,突显了当前模型在多步物理推理方面遇到的困难,常常会跳过或不完整地执行动作。为解决在现实世界主观视角视频中对工具使用理解的需求,已开发出EgoTools,它包含一个大型数据集和一个诊断基准。虽然Gemini-3.1 Pro等模型显示出潜力,但它们在将工具使用与视觉证据联系起来方面仍有不足,表明该领域需要进一步发展。 AI

影响 这些基准将推动AI理解和生成逼真主观视角视频能力的发展,这对于具身AI和机器人技术至关重要。

排序理由 该集群包含两篇研究论文,介绍了用于评估AI模型在主观视角视频生成和工具使用理解方面的新基准和数据集。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 7 个来源。 我们如何撰写摘要 →

新基准评估AI的主观视角视频操控和工具使用技能

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
该集群包含两篇研究论文,介绍了用于评估AI模型在主观视角视频生成和工具使用理解方面的新基准和数据集。
Source corroboration
7 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
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
53 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+2 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [7]

  1. arXiv cs.AI TIER_1 English(EN) · Qinchuan Cheng, Zhantao Gong, Pengzhan Sun, Angela Yao, Xulei Yang, Shijie Li ·

    Ego2World:将以自我为中心的烹饪视频编译成可执行世界,用于信念状态规划

    arXiv:2605.13335v2 Announce Type: replace Abstract: Embodied agents in household environments must plan under partial observation: they need to remember objects, track state changes, and recover when actions fail. Existing benchmarks only partially test this ability. Egocentric v…

  2. arXiv cs.AI TIER_1 English(EN) · Qinchuan Cheng, Zhantao Gong, Pengzhan Sun, Angela Yao, Shijie Li ·

    Ego2World:将以自我为中心的烹饪视频编译成可执行世界,用于信念状态规划

    arXiv:2610.02715v1 Announce Type: new Abstract: Egocentric videos capture how people carry out everyday activities, yet testing an agent requires evaluating the consequences of actions it chooses itself. We introduce Ego2World, a benchmark that turns annotated cooking activities …

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

    Ego2Act:评估以自我为中心的视频生成中的目标导向操纵

    Video generation models are increasingly being explored as world simulators for embodied planning and learning. To do so effectively, these models must not only generate visually appealing frames, but also predict how environments dynamically evolve when executing goal-directed a…

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

    EgoTools:迈向真实世界自我中心视频中的以工具为中心的推理

    Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolving object and task states. Tool use sits at the heart of such tasks, as many everyday and professional activities are tool-mediate…

  5. arXiv cs.CV TIER_1 English(EN) · Yifan Shen, Jiateng Liu, Xinzhuo Li, Yuanzhe Liu, Bingxuan Li, Houze Yang, Wenqi Jia, Yijiang Li, Tianjiao Yu, James Matthew Rehg, Xu Cao, Ismini Lourentzou ·

    EgoForge:目标导向的自我中心世界模拟器

    arXiv:2603.20169v2 Announce Type: replace Abstract: Generative world models have shown promise for simulating dynamic environments, yet egocentric video remains challenging due to rapid viewpoint changes, frequent hand-object interactions, and goal-directed procedures whose evolu…

  6. arXiv cs.CV TIER_1 English(EN) · Patrick Amadeus Irawan, Iskandar Muda Rizky Parlambang, Rava Maulana, Qinrong Cui, Erland Hilman Fuadi, Zayd M. K. Zuhri, Nanda Ryaas Absar, Ahmed Elshabrawy, Wilfried Ariel Mulyawan, Shoubin Yu, Yue Zhang, Mohit Bansal, Alham Fikri Aji ·

    Ego2Act:评估以自我为中心的视频生成中的目标导向操纵

    arXiv:2610.01092v1 Announce Type: new Abstract: Video generation models are increasingly being explored as world simulators for embodied planning and learning. To do so effectively, these models must not only generate visually appealing frames, but also predict how environments d…

  7. arXiv cs.CV TIER_1 English(EN) · Shulin Tian, Junsu Kim, Shuai Liu, Hao Li, Yujiao Shen, Sihan Li, Zhe Yang, Yeongon Kim, Feiyu Li, Jialin Wu, Yichi Zhang, Wenhui Wang, Runmao Yao, Yuhao Dong, Zhaoxi Chen, Fangzhou Hong, Antonino Furnari, Jingkang Yang, Hongyuan Zhu, Ziwei Liu ·

    EgoTools:迈向真实世界自我中心视频中的工具中心推理

    arXiv:2609.39378v1 Announce Type: new Abstract: Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolving object and task states. Tool use sits at the heart of such tasks, as many every…