# Light-WAM: Efficient World Action Models with State-Fusion Action Decoding

arXiv: https://arxiv.org/abs/2606.08242 · HTML: https://mlsanity.com/paper/2606.08242/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 35 of its 38 references that are in the map.
- First posted on arXiv 6 Jun 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation](https://mlsanity.com/paper/2312.13139/) (2023)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [Causal World Modeling for Robot Control](https://mlsanity.com/paper/2601.21998/) (2026)
- [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://mlsanity.com/paper/2510.10274/) (2025)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations](https://mlsanity.com/paper/2412.14803/) (2024)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [Real-Time Execution of Action Chunking Flow Policies](https://mlsanity.com/paper/2506.07339/) (2025)
- [Unified Video Action Model](https://mlsanity.com/paper/2503.00200/) (2025)

## Built on by (most cited first, 23 of 23)

- [Show-Harness: Just a VLM Agent Can Play Robots](https://mlsanity.com/paper/2609.10522/) (2026)
- [Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models](https://mlsanity.com/paper/2608.04404/) (2026)
- [Faster-WAM: Do World Action Models Need Deep Action Modules?](https://mlsanity.com/paper/2608.02365/) (2026)
- [Test-Time Scaling for World Action Models via Zero-Shot Geometric Evaluation](https://mlsanity.com/paper/2607.17454/) (2026)
- [GlanceWAM: Sparse Test-Time Imagination for World-Action Models](https://mlsanity.com/paper/2608.23927/) (2026)
- [UniNav: A Unified World-Action Diffusion Model for Visual Navigation](https://mlsanity.com/paper/2608.03244/) (2026)
- [DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation](https://mlsanity.com/paper/2608.22067/) (2026)
- [Robust Bimanual Vision-Language-Action Models via Embarrassingly Simple Modality Masking](https://mlsanity.com/paper/2608.22419/) (2026)
- [Streaming-WAM: Action-Conditioned World-Action Model for Asynchronous Robot Manipulation](https://mlsanity.com/paper/2609.28927/) (2026)
- [Learning to Use Imagination: Progress-Conditioned Future Utilization for World Action Models](https://mlsanity.com/paper/2609.06578/) (2026)
- [Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies](https://mlsanity.com/paper/2609.24682/) (2026)
- [DualWAM: Dual-System World Action Models for Asynchronous Global Planning and Local Refinement](https://mlsanity.com/paper/2609.24868/) (2026)
- [DeltaWAM: Change-Centric Visual Foresight via Delta Tokens for an Efficient World-Action Model](https://mlsanity.com/paper/2609.33177/) (2026)
- [What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling](https://mlsanity.com/paper/2609.34981/) (2026)
- [Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models](https://mlsanity.com/paper/2609.35439/) (2026)
- [LIBERO-MAX: Do Robot Policies Adapt When the World Changes?](https://mlsanity.com/paper/2609.36518/) (2026)
- [Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination](https://mlsanity.com/paper/2609.38984/) (2026)
- [DeepJEPA: Scaling World Models from Within](https://mlsanity.com/paper/2610.00368/) (2026)
- [WAMJET: A Harness for World Action Model Acceleration](https://mlsanity.com/paper/2610.03797/) (2026)
- [RealtimeWAM: One-Step Asynchronous World Action Models](https://mlsanity.com/paper/2610.06617/) (2026)
- [OpenWAM: An Open Framework for Composable World-Action Models](https://mlsanity.com/paper/2610.07922/) (2026)
- [WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models](https://mlsanity.com/paper/2610.11401/) (2026)
- [SmolWAM: A Latent World-Action Model for Robotic Manipulation on Edge Devices](https://mlsanity.com/paper/2610.13740/) (2026)

## Abstract (arXiv)

World Action Models (WAMs) extend robot policy learning by incorporating future prediction as an additional training objective, encouraging the policy to encode task-relevant temporal structure in its representations. Current WAMs often rely on large-scale generative architectures that incur high training costs and inference latency, making them difficult to deploy as efficient closed-loop policies. We propose Light-WAM, a lightweight World Action Model for efficient robot manipulation. Specifically, it is built with a compact video backbone and performs future-video supervision in a downsampled latent space, reducing the cost of video co-training while retaining its benefits for representation learning. For action prediction, Light-WAM introduces the StateFusionActionExpert, which reads adapted states from multiple backbone layers, fuses them through learned-query pooling, and directly predicts action chunks in a single forward pass. This design provides an efficient interface between video backbone representations and robot actions, avoiding the need for heavy generative action experts. Experiments demonstrate that Light-WAM maintains strong performance on LIBERO and achieves usable multi-task performance on RoboTwin 2.0, while using only 0.44B trainable parameters. It also achieves 72.03ms inference latency with 4.1GiB peak GPU memory and improved training throughput.