VIS-Ground: Video Interactive Storytelling with Contextual Grounding
- 类型：arxiv
- 标识：2610.09326
- 链接：https://arxiv.org/abs/2610.09326
- 主分类：multimodal
- 形态：method
- TLDR：Video interactive storytelling enables viewers to actively steer how a video unfolds. However, once we allow viewers to intervene during generation, a new challenge arises: The viewer's request can have latent dependencies on both the grounding source and the current rendered video state. These dependencies may not be explicitly stated in any individual input, but emerge only when the source, rendered history, and new viewer intent are considered jointly. Existing interactive video generation systems primarily emphasize following viewer instructions, while source-grounded video generation meth
- 待LLM分类：否
- 标题中文：VIS-Ground：基于上下文 Grounding 的视频交互式叙事
- TLDR中文：视频交互式叙事使观众能够主动引导视频的展开方式。然而，一旦允许观众在生成过程中进行干预，便出现新的挑战：观众的请求可能潜在依赖于 grounding source 与当前渲染的视频状态。这些依赖关系可能并未在任何单一输入中显式说明，而仅在 source、渲染历史与新观众意图被联合考量时才会浮现。现有交互式视频生成系统主要强调遵循观众指令，而 source-grounded 视频生成方法
- 来源文件：
- /inbox/tom/_candidates/2026-10-13-agent-rag-longcontext-candidates.json