Add WAM paper: Towards Predictive, Aligned, and Scalable Robot Learning

[279object]

Paper

• Title: Towards Predictive, Aligned, and Scalable Robot Learning
• Short name: TPAAS
• arXiv ID: 2607.11270v1
• Paper: https://arxiv.org/pdf/2607.11270
• Authors: Peijun Tang, Shangjin Xie, Baifu Huang, Binyan Sun, Haotian Yang, Kuncheng Luo, Weiqi Jin, Shilin Fang, Jianan Wang
• Published: 2026-07-13
• arXiv categories: cs.RO, cs.AI
• Matched keywords: WAM, world-action model

README Entry

- **TPAAS**: "Towards Predictive, Aligned, and Scalable Robot Learning", arXiv 2026. ![](https://img.shields.io/badge/Predictive--Latent-c026d3)
  [[📄 Paper](https://arxiv.org/pdf/2607.11270)]

Robot Decision

• Decision: accept
• Confidence: high
• Taxonomy: joint_autoregressive_predictive_latent
• Taxonomy confidence: medium
• README heading: ### Autoregressive Generation
• Badges: https://img.shields.io/badge/Predictive--Latent-c026d3

Reason

Introduces and evaluates a latent world-action model for robot control that predicts latent world dynamics and generates actions.

Evidence

• latent world-action model that generates actions by reasoning over world dynamics
• jointly optimizes latent world modeling and action generation for robotic manipulation

Taxonomy Evidence

• latent world-action model that generates actions by reasoning over world dynamics in latent space
• jointly optimizes latent world modeling and action generation
• anticipating future dynamics in latent space before generating actions

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