GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch

  • 类型:arxiv
  • 标识:2607.13960
  • 链接:https://arxiv.org/abs/2607.13960
  • 主分类:llm-infra
  • 形态:application
  • 被引:1
  • 被引来源:Semantic Scholar
  • S2被引:1
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:GigaWorld-Policy-0.5 preserves the training benefits of future visual dynamics while improving inference efficiency for robot control, and introduces a Mixture-of-Transformers architecture that separates visual dynamics modeling and action generation into specialized experts.
  • OpenAlex ID:W7169043940
  • OpenAlex DOI:10.48550/arxiv.2607.13960
  • DOI:10.48550/arxiv.2607.13960
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.13960
  • OpenAlex更新:2026-07-19
  • 副分类:engineering
  • 待LLM分类:否
  • 标题中文:GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
  • TLDR中文:GigaWorld-Policy-0.5 在保留未来视觉动力学训练收益的同时提升了机器人控制的推理效率,并引入 Mixture-of-Transformers 架构,将视觉动力学建模与动作生成分离到专门的专家模块中。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-16-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]