Faster-WAM

A world action model for language-guided robot manipulation. It computes a representation of future observations once and reuses it during action denoising. The authors provide separate LIBERO and RoboTwin checkpoints.

Papers & reports (1)

Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models

Paper available

arXiv: 2608.04404DOI: 10.48550/arxiv.2608.04404
Authors & affiliations (8)

Author order: Original order

  1. Weiheng Zhao

    Huazhong University of Science and Technology

  2. Haoyi Jiang

    Huazhong University of Science and Technology

  3. Xin Shi

    D-Robotics

  4. Liu Liu

    Horizon Robotics

  5. Fan Huang

    Xiamen University

  6. Zhizhong Su

    Horizon Robotics

  7. Wei Sui

    D-Robotics

  8. Xinggang Wang

    Huazhong University of Science and Technology

First published
2026-08-05
Latest paper revision
v1 · 2026-08-05
Venue
Not provided

Covered model versions

Paper ↗PDF ↗

How to access and use

Public code resources
Public access
Model files
Public access

Code and training / fine-tuning

Access
Public access

Verified on · 2026-11-20

Code license
Apache License 2.0

Verified on · 2026-11-20

Model files

Model files
LIBERO / LIBERO-Plus · step 021700AccessWeights license
MIT
RoboTwin 2.0 · step 029355AccessWeights license
MIT
Release information

SourceVerified on · 2026-11-20

Checks before deployment

Available weights or code do not establish plug-and-play robot compatibility. Check the required configuration, data and interfaces in the source documentation.

Architecture and inputs / outputs

Model type
Action policy
Architecture
WAM

Scope and training

Functional purpose

action_control

Submit a source or correction