# BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning

arXiv: https://arxiv.org/abs/2511.04131 · HTML: https://mlsanity.com/paper/2511.04131/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- First posted on arXiv 6 Nov 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Built on by (most cited first, 30 of 38)

- [TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control](https://mlsanity.com/paper/2602.07439/) (2026)
- [Action Images: End-to-End Policy Learning via Multiview Video Generation](https://mlsanity.com/paper/2604.06168/) (2026)
- [ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation](https://mlsanity.com/paper/2603.03279/) (2026)
- [Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents](https://mlsanity.com/paper/2607.19190/) (2026)
- [Compositional Planning with Jumpy World Models](https://mlsanity.com/paper/2602.19634/) (2026)
- [Heracles: Bridging Precise Tracking and Generative Synthesis for General Humanoid Control](https://mlsanity.com/paper/2603.27756/) (2026)
- [Vesta: A Generalist Embodied Reasoning Model](https://mlsanity.com/paper/2606.20905/) (2026)
- [CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperation](https://mlsanity.com/paper/2602.15060/) (2026)
- [Can We Really Learn One Representation to Optimize All Rewards?](https://mlsanity.com/paper/2602.11399/) (2026)
- [Zero-Shot Off-Policy Learning](https://mlsanity.com/paper/2602.01962/) (2026)
- [Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models](https://mlsanity.com/paper/2603.15857/) (2026)
- [PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking](https://mlsanity.com/paper/2603.19305/) (2026)
- [Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors](https://mlsanity.com/paper/2605.22272/) (2026)
- [Scaling Behavior Foundation Model for Humanoid Robots](https://mlsanity.com/paper/2607.15163/) (2026)
- [GenTrack: Physical Alignment for Robot-Native Motion Generation and Zero-Shot Humanoid Tracking](https://mlsanity.com/paper/2608.01410/) (2026)
- [Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning](https://mlsanity.com/paper/2603.25464/) (2026)
- [PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitation](https://mlsanity.com/paper/2606.26741/) (2026)
- [AnyBody: Free-Form Whole-Body Humanoid Control from Arbitrary Keypoint Guidance](https://mlsanity.com/paper/2606.29209/) (2026)
- [Exploration and Online Transfer with Behavioral Foundation Models](https://mlsanity.com/paper/2606.29980/) (2026)
- [ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control](https://mlsanity.com/paper/2606.30362/) (2026)
- [HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL](https://mlsanity.com/paper/2608.16837/) (2026)
- [BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI](https://mlsanity.com/paper/2609.03497/) (2026)
- [Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking](https://mlsanity.com/paper/2605.23733/) (2026)
- [Plan, Don't Pose: Long Composite Motion Generation with Text-Aligned BFM](https://mlsanity.com/paper/2605.29906/) (2026)
- [Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids](https://mlsanity.com/paper/2606.12814/) (2026)
- [Kine2Go: Kinematic dataset for the Unitree Go2 robot with diverse gaits and motions](https://mlsanity.com/paper/2606.14433/) (2026)
- [VENOM: Versatile Embodied Network for Omni-bodied Motion tracking](https://mlsanity.com/paper/2606.16696/) (2026)
- [Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report](https://mlsanity.com/paper/2607.07370/) (2026)
- [GaitSpan: Growing Humanoid Locomotion from Walking to Running](https://mlsanity.com/paper/2607.12114/) (2026)
- [Human-Centric Intelligence in the Era of Foundation Models: A Survey](https://mlsanity.com/paper/2608.18184/) (2026)

## Abstract (arXiv)

Building Behavioral Foundation Models (BFMs) for humanoid robots has the potential to unify diverse control tasks under a single, promptable generalist policy. However, existing approaches are either exclusively deployed on simulated humanoid characters, or specialized to specific tasks such as tracking. We propose BFM-Zero, a framework that learns an effective shared latent representation that embeds motions, goals, and rewards into a common space, enabling a single policy to be prompted for multiple downstream tasks without retraining. This well-structured latent space in BFM-Zero enables versatile and robust whole-body skills on a Unitree G1 humanoid in the real world, via diverse inference methods, including zero-shot motion tracking, goal reaching, and reward optimization, and few-shot optimization-based adaptation. Unlike prior on-policy reinforcement learning (RL) frameworks, BFM-Zero builds upon recent advancements in unsupervised RL and Forward-Backward (FB) models, which offer an objective-centric, explainable, and smooth latent representation of whole-body motions. We further extend BFM-Zero with critical reward shaping, domain randomization, and history-dependent asymmetric learning to bridge the sim-to-real gap. Those key design choices are quantitatively ablated in simulation. A first-of-its-kind model, BFM-Zero establishes a step toward scalable, promptable behavioral foundation models for whole-body humanoid control.