MiniWorld: Democratizing the Training of Video World Models from Scratch

  • 类型：arxiv
  • 标识：2608.01127
  • 链接：https://arxiv.org/abs/2608.01127
  • 主分类：multimodal
  • 形态：method
  • 被引：0
  • 被引来源：Semantic Scholar
  • S2被引：0
  • 影响力被引：0
  • TLDR：MiniWorld is presented, a reproducible framework for training streaming video world models from scratch that adopts a chunk-wise non-decreasing noise schedule and two-stage continued training to improve temporal modeling and stability and will facilitate future research on video world modeling.
  • 副分类：engineering
  • 待LLM分类：否
  • 标题中文：MiniWorld：降低视频世界模型从零训练的门槛
  • TLDR中文：提出 MiniWorld，一个从零训练流式视频世界模型的可复现框架，采用 chunk-wise 非递减噪声调度与两阶段继续训练，提升时间建模与稳定性，将促进未来视频世界模型的研究。
  • 来源文件：
  • /inbox/tom/_candidates/2026-08-05-agent-rag-longcontext-candidates.json
  • [S2 enrich]