Add WAM paper: Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation

[279object]

Paper

• Title: Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation
• Short name: Pondering the Way
• arXiv ID: 2606.29908v1
• Paper: https://arxiv.org/pdf/2606.29908
• Authors: Hong Chen, Daqi Liu, Zehan Zhang, Haiguang Wang, Tianhao Lu, Longfei Yan, Haiyang Sun, Fangzhen Li, Hongwei Xie, Bing Wang, Guang Chen, Hangjun Ye, Yihua Tan
• Published: 2026-06-29
• arXiv categories: cs.RO, cs.AI
• Matched keywords: world action model

README Entry

- **Pondering the Way**: "Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation", arXiv 2026. ![](https://img.shields.io/badge/Unified--DiT-be123c) ![](https://img.shields.io/badge/Explicit-f43f5e)
  [[📄 Paper](https://arxiv.org/pdf/2606.29908)]

Robot Decision

• Decision: accept
• Confidence: high
• Taxonomy: joint_diffusion_unified_explicit
• Taxonomy confidence: high
• README heading: ### Diffusion-based Generation
• Badges: https://img.shields.io/badge/Unified--DiT-be123c, https://img.shields.io/badge/Explicit-f43f5e

Reason

The paper explicitly proposes a World Action Model for embodied visual navigation that jointly generates future observations and action trajectories for planning.

Evidence

• SWAM performs single-pass inference to simultaneously generate intermediate RGB-D sequences and corresponding action trajectories
• goal-conditioned visual navigation and planning with joint observation-action generation
• models conditional distribution over future observations and actions

Taxonomy Evidence

• single-pass inference to simultaneously generate intermediate RGB-D sequences and corresponding action trajectories
• latent diffusion model jointly generates an RGBD observation sequence and action sequence
• extends pretrained Diffusion Transformer of CogVideoX to jointly produce RGB-D frame latents and action tokens

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