Add WAM paper: From World Models to World Action Models: A Concise Tutorial for Robotics

[279object]

Paper

• Title: From World Models to World Action Models: A Concise Tutorial for Robotics
• Short name: FWMTW
• arXiv ID: 2607.00836v1
• Paper: https://arxiv.org/pdf/2607.00836
• Authors: Xiaoxiong Zhang, Xiong Zeng, Wei Zhang
• Published: 2026-07-01
• arXiv categories: cs.RO, cs.AI, eess.SY
• Matched keywords: world action model, world action models

README Entry

- **FWMTW**: "From World Models to World Action Models: A Concise Tutorial for Robotics", arXiv 2026. ![](https://img.shields.io/badge/Needs--Taxonomy--Review-64748b)
  [[📄 Paper](https://arxiv.org/pdf/2607.00836)]

Robot Decision

• Decision: accept
• Confidence: high
• Taxonomy: uncertain
• Taxonomy confidence: high
• README heading: ## World Action Model
• Badges: https://img.shields.io/badge/Needs--Taxonomy--Review-64748b

Reason

Tutorial explicitly defines and surveys world action models for robotics and embodied prediction/control.

Evidence

• introduce world action models connecting predicted futures with executable robot actions
• world models defined as action-conditioned predictive models for embodied AI tasks
• taxonomy covers imagine-then-execute, action prediction, joint video-action modeling, policy learning

Taxonomy Evidence

• presents a design-space view of world models
• summarize four representative paradigms
• goal is to clarify conceptual scope and provide a structured taxonomy

Needs taxonomy review: fallback README heading/badge was used because taxonomy.toml has no README mapping for this classification.

Human Review Checklist

• This paper belongs in the WAM survey
• README section is correct
• Badges are correct
• Short name is correct
• Paper link is correct
• Merge this PR if accepted