# Motus2: A Self-Evolving General World Model for Dexterous Manipulation

arXiv: https://arxiv.org/abs/2608.30237 · HTML: https://mlsanity.com/paper/2608.30237/

## Key facts

- Cited by 9 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 44 of its 49 references that are in the map.
- First posted on arXiv 31 Aug 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 44)

- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [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)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.06503/) (2022)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [DiffusionNFT: Online Diffusion Reinforcement with Forward Process](https://mlsanity.com/paper/2509.16117/) (2025)
- [One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale](https://mlsanity.com/paper/2303.06555/) (2023)
- [Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling](https://mlsanity.com/paper/2209.14548/) (2022)
- [Ctrl-World: A Controllable Generative World Model for Robot Manipulation](https://mlsanity.com/paper/2510.10125/) (2025)
- [Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models](https://mlsanity.com/paper/2405.04233/) (2024)
- [Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning](https://mlsanity.com/paper/2304.12824/) (2023)
- [GigaWorld-Policy: An Efficient Action-Centered World--Action Model](https://mlsanity.com/paper/2603.17240/) (2026)
- [DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos](https://mlsanity.com/paper/2602.06949/) (2026)
- [EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos](https://mlsanity.com/paper/2507.12440/) (2025)
- [DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning](https://mlsanity.com/paper/2410.24185/) (2024)
- [RELIC: Interactive Video World Model with Long-Horizon Memory](https://mlsanity.com/paper/2512.04040/) (2025)
- [EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data](https://mlsanity.com/paper/2602.16710/) (2026)
- [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://mlsanity.com/paper/2605.00078/) (2026)
- [Score Regularized Policy Optimization through Diffusion Behavior](https://mlsanity.com/paper/2310.07297/) (2023)
- [WMPO: World Model-based Policy Optimization for Vision-Language-Action Models](https://mlsanity.com/paper/2511.09515/) (2025)
- [Motubrain: An Advanced World Action Model for Robot Control](https://mlsanity.com/paper/2604.27792/) (2026)

## Built on by (most cited first, 9 of 9)

- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [World-Action Models for Robot Learning and Control: A Survey](https://mlsanity.com/paper/2609.16074/) (2026)
- [XPACE: Joint World and Action Modeling from Heterogeneous Experience](https://mlsanity.com/paper/2609.17372/) (2026)
- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)
- [ME-Dex 1.0: Bringing Heterogeneous Tactile Sensing into World Action Modeling](https://mlsanity.com/paper/2609.21449/) (2026)
- [Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation](https://mlsanity.com/paper/2609.37398/) (2026)
- [Ego4WAM: What Matters When Scaling Egocentric Human Data for Robot Learning?](https://mlsanity.com/paper/2609.40341/) (2026)
- [Native Action-Prior Learning from Videos for World Action Models](https://mlsanity.com/paper/2610.03391/) (2026)
- [OpenWAM: An Open Framework for Composable World-Action Models](https://mlsanity.com/paper/2610.07922/) (2026)

## Abstract (arXiv)

General embodied agents should perceive, predict, act, evaluate, and improve within a unified system. World models have shown great promise in building such agents, yet existing models typically append an action output head to a world simulator, without coupling them into a closed decision-and-learning loop for policy improvement. We present Motus2, a self-evolving general world model for dexterous manipulation. Motus2 advances world modeling through model scaling and data scaling. For model scaling, a single model with shared weights exposes three control interfaces: a policy (world-action model), a simulator (action-conditioned world model), and an evaluator (value model). The policy proposes candidate action chunks, the simulator predicts their visual consequences, and the evaluator assesses the predicted outcomes. Their coupling forms a closed decision-and-learning loop for policy improvement. This formulation uses curated expert demonstrations for action learning, while failed and suboptimal interactions provide valuable evidence for dynamics modeling and value learning. For data scaling, Motus2 progresses from large-scale monocular egocentric data to synchronized stereo egocentric data, followed by robot-domain adaptation with robot trajectories and supplementary human-robot alignment data. Motus2 further studies global-autoregressive and hybrid-memory extensions of its sliding-window context, adds tactile feedback for contact-aware control, and is instantiated on a fully biomimetic platform with stereo vision, dual arms, dual dexterous hands, and tactile sensing. Together, egocentric data scaling and closed-loop general world model scaling provide a general path toward self-evolving dexterous manipulation.