Add WAM paper: FAWAM: Force-Aware World Action Models for Closed-Loop Contact-Rich Manipulation

[279object]

Paper

• Title: FAWAM: Force-Aware World Action Models for Closed-Loop Contact-Rich Manipulation
• Short name: FAWAM
• arXiv ID: 2606.08555v1
• Paper: https://arxiv.org/pdf/2606.08555
• Authors: Haotian He, Zeyu Yan, Qipeng Liu, Ning Guo, Wenzhao Lian
• Published: 2026-06-07
• arXiv categories: cs.RO
• Matched keywords: world action model, world action models

README Entry

- **FAWAM**: "FAWAM: Force-Aware World Action Models for Closed-Loop Contact-Rich Manipulation", arXiv 2026. ![](https://img.shields.io/badge/Implicit-ea580c)
  [[📄 Paper](https://arxiv.org/pdf/2606.08555)]

Robot Decision

• Decision: accept
• Confidence: high
• Taxonomy: cascaded_implicit_latent
• Taxonomy confidence: medium
• README heading: ### Cascaded World-Action-Model
• Badges: https://img.shields.io/badge/Implicit-ea580c

Reason

The paper explicitly proposes and evaluates a force-aware world action model for robotic manipulation, modeling action-conditioned contact dynamics and using predictions for closed-loop control.

Evidence

• proposes FAWAM, a force-aware world action model
• jointly predicts future actions and end-effector wrenches to model contact evolution
• uses predicted wrench trajectory for execution-time residual correction
• real-world contact-rich robotic manipulation experiments

Taxonomy Evidence

• decodes action trajectories from future visual latent representations
• freeze the video world model and train the force-aware action decoder
• jointly predicts future actions and end-effector wrenches

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