Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

  • 类型:arxiv
  • 标识:2607.07675
  • 链接:https://arxiv.org/abs/2607.07675
  • 主分类:multimodal
  • 形态:method
  • 被引:4
  • 被引来源:Semantic Scholar
  • S2被引:4
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:LingBot-Video is presented, a DiT-based video pretraining paradigm specifically tailored for embodied intelligence, and is contributed as the inaugural large-scale, open-source MoE video foundation model to the community, in a pioneering effort to bridge digital creativity and physical actuation.
  • OpenAlex ID:W7167854203
  • OpenAlex DOI:10.48550/arxiv.2607.07675
  • DOI:10.48550/arxiv.2607.07675
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.07675
  • OpenAlex更新:2026-07-19
  • 副分类:engineering
  • 待LLM分类:否
  • 标题中文:面向具身智能的 Mixture-of-Experts 视频预训练规模化
  • TLDR中文:提出 LingBot-Video,一种专为具身智能设计的基于 DiT 的视频预训练范式,并将其作为首个大规模开源 MoE 视频基础模型贡献给社区,致力于在数字创意与物理执行之间搭建桥梁。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-09-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]