RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination

  • 类型:arxiv
  • 标识:2607.14187
  • 链接:https://arxiv.org/abs/2607.14187
  • 主分类:agent
  • 形态:method
  • 被引:1
  • 被引来源:Semantic Scholar
  • S2被引:1
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:Hy-Embodied-RxBrain, an embodied cognition foundation model with joint language-visual reasoning and imagination, is introduced and extended to continuous robot action generation, where it shows promising real-robot performance without large-scale action-data pretraining.
  • OpenAlex ID:W7169544825
  • OpenAlex DOI:10.48550/arxiv.2607.14187
  • DOI:10.48550/arxiv.2607.14187
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.14187
  • OpenAlex更新:2026-07-19
  • 待LLM分类:否
  • 标题中文:RxBrain:具备语言-视觉联合推理与想象的具身认知基础模型
  • TLDR中文:提出 Hy-Embodied-RxBrain,一个具备语言-视觉联合推理与想象的具身认知基础模型,并将其扩展到连续机器人动作生成,在无需大规模动作数据预训练的情况下展现出可观的真实机器人性能。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-18-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • /inbox/tom/_candidates/2026-07-19-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]
  • /inbox/tom/_candidates/2026-07-20-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-07-20-agent-memory-tool-use-candidates.json