ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts

  • 类型:arxiv
  • 标识:2607.28993
  • 链接:https://arxiv.org/abs/2607.28993
  • 主分类:engineering
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:Semantic-Temporal WAM (ST-WAM) is proposed to improve action robustness by using DINOv3 as a shared semantic representation for future prediction and history retrieval while retaining fine-grained VAE dynamics, demonstrating that semantic-temporal modeling effectively complements pixel-generative dynamics for robust manipulation.
  • 待LLM分类:否
  • 标题中文:ST-WAM:面向视觉分布偏移下鲁棒操作的语义-时序世界动作模型
  • TLDR中文:提出 Semantic-Temporal WAM (ST-WAM),使用 DINOv3 作为未来预测与历史检索的共享语义表示,同时保留细粒度 VAE 动力学,以提升动作鲁棒性;证明语义-时间建模能有效补充像素生成动力学,实现稳健的操作。
  • 来源文件
  • /inbox/tom/_candidates/2026-08-05-agent-rag-longcontext-candidates.json
  • [S2 enrich]