# Being-M0.7: A Latent World-Action Model for Humanoid Robots

arXiv: https://arxiv.org/abs/2610.11283 · HTML: https://mlsanity.com/paper/2610.11283/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Humanoid and legged locomotion world models, one of 11 directions in World models.
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- World models / [Humanoid and legged locomotion world models](https://mlsanity.com/wm/humanoid-and-legged-locomotion-world-models/)

## Builds on (most cited first, 25 of 25)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [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)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models](https://mlsanity.com/paper/2411.04996/) (2024)
- [SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control](https://mlsanity.com/paper/2511.07820/) (2025)
- [HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit](https://mlsanity.com/paper/2502.13013/) (2025)
- [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://mlsanity.com/paper/2605.00078/) (2026)
- [Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization](https://mlsanity.com/paper/2601.12993/) (2026)
- [ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning](https://mlsanity.com/paper/2510.05070/) (2025)
- [HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos](https://mlsanity.com/paper/2509.16757/) (2025)
- [Psi0: An Open Foundation Model Towards Universal Humanoid Loco-Manipulation](https://mlsanity.com/paper/2603.12263/) (2026)
- [VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation](https://mlsanity.com/paper/2509.20322/) (2025)
- [EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration](https://mlsanity.com/paper/2602.10106/) (2026)
- [EgoTwin: Dreaming Body and View in First Person](https://mlsanity.com/paper/2508.13013/) (2025)
- [Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model](https://mlsanity.com/paper/2508.07863/) (2025)
- [MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation](https://mlsanity.com/paper/2606.09215/) (2026)
- [SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation](https://mlsanity.com/paper/2606.08278/) (2026)
- [LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations](https://mlsanity.com/paper/2602.21723/) (2026)

## Abstract (arXiv)

Humanoid loco-manipulation requires coordinated locomotion and manipulation informed by future scene evolution and whole-body motion, yet learning these capabilities is constrained by scarce robot demonstrations. Human video and motion datasets offer scalable supervision, but many contain only video or motion rather than paired video-motion data. Moreover, human motion does not directly specify executable robot actions. We present Being-M0.7, a latent world-action model that transfers visual-motion priors learned from mixed-modality human data to humanoid control through pre-training, robot mid-training, and action post-training. We curate a corpus from more than 10,000 hours of raw human-centric data, integrating video-only, motion-only, and paired video-motion streams to learn complementary visual dynamics and whole-body kinematic structure. Joint prediction of future latent visual states and motion encourages visual representations to encode future kinematics. Robot mid-training adapts this coarse-grained prior to robot viewpoints and body dynamics. During action post-training, an action expert combines visual predictive representations from the frozen, adapted prior with current images and proprioception through gated cross-attention, grounding predictive context in executable whole-body commands. Being-M0.7 achieves the highest aggregate success rate among the compared baselines on SIMPLE and matches the strongest baseline on real-world Unitree G1 loco-manipulation tasks.