PulseAugur
中
实时 17:36:19
English(EN) World-in-Context: Interactive Video World Modeling with In-Context Conditioning

World-in-Context 框架统一视频控制以实现交互式建模

研究人员推出了一种新颖的交互式视频世界建模框架 World-in-Context (WiC),该框架统一了视角、动作和相机控制。与之前隐式处理或通过碎片化路径处理这些控制的方法不同,WiC 将它们作为显式 token 集成到共享的自注意力空间中。这种方法能够从单视图数据中涌现出视角切换能力,并通过一种称为 Interaction-Transport RoPE (IT-RoPE) 的新参数化方法提高了时间连续性。在 WBench 基准测试的评估中,World-in-Context-5B 模型实现了与更大模型相当的导航性能,并显著提高了视角切换的成功率。 AI

影响 该框架通过改进对观看视角和动作的控制,有望增强交互式视频生成和导航。

排序理由 该集群描述了一篇关于视频世界建模的新颖框架和方法的研究论文。

在 Hugging Face Daily Papers 阅读 →

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

World-in-Context 框架统一视频控制以实现交互式建模

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
该集群描述了一篇关于视频世界建模的新颖框架和方法的研究论文。
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
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 [2]

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

    World-in-Context:具有上下文条件的交互式视频世界建模

    World-in-Context unifies view, action, and camera controls via explicit tokens and interaction-aware positional encoding to improve interactive video generation and navigation.

  2. arXiv cs.CV TIER_1 English(EN) · Harold Haodong Chen, Rui Peng, Rongjin Guo, Lingteng Qiu, Kejie Qiu, Chao Xu, Zilong Dong ·

    World-in-Context:具有上下文条件的交互式视频世界建模

    arXiv:2610.33169v1 Announce Type: new Abstract: Interactive video world models require coordinated control over viewing perspectives, character actions, and camera motion. Existing methods typically leave view modes implicit in text captions, conflate action with camera motion, a…