OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining

  • 类型：arxiv
  • 标识：2609.07398
  • 链接：https://arxiv.org/abs/2609.07398
  • 主分类：engineering
  • 形态：method
  • TLDR：World-Action Models inherit world knowledge from video-generative priors, and channel it into executable control signals through embodied experience. Existing systems, however, are monolithic: the generative backbone, visual representation, architecture, information flow, inference procedure, and training data are tightly coupled, obscuring which design choices matter and why. We introduce OpenWAM, an open research stack that turns world-action pretraining into a controlled experimental program. OpenWAM-Infra factorizes the WAM design space into composable modules with unified training, infere
  • 待LLM分类：否
  • 标题中文：OpenWAM：面向系统化世界-动作模型预训练的开源模块化探索
  • TLDR中文：世界-动作模型（World-Action Models）从视频生成先验中继承世界知识，并通过具身经验将其引导至可执行的控制信号。然而现有系统是单体式的：生成骨干、视觉表示、架构、信息流、推理流程与训练数据紧密耦合，掩盖了哪些设计选择真正关键以及原因所在。我们提出 OpenWAM，一个将世界-动作预训练转化为可控实验计划的开源研究栈。OpenWAM-Infra 将 WAM 设计空间分解为可组合模块，并提供统一训练、推理……
  • 来源文件：
  • /inbox/tom/_candidates/2026-09-09-agent-rag-longcontext-candidates.json