# HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL arXiv: https://arxiv.org/abs/2608.16837 · HTML: https://mlsanity.com/paper/2608.16837/ ## Key facts - Cited by 1 papers in the map (data through 14 Oct 2026). - Placed in Tactile, force-aware and humanoid VLA, one of 13 directions in Vision-language-action models. - Builds on 36 of its 45 references that are in the map. - First posted on arXiv 17 Aug 2026. ## Placed in - Vision-language-action models / [Tactile, force-aware and humanoid VLA](https://mlsanity.com/vla/tactile-force-aware-and-humanoid-vla/) - Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/) ## Builds on (most cited first, 30 of 36) - [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018) - [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024) - [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024) - [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025) - [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023) - [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025) - [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024) - [Efficient Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2302.02948/) (2023) - [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://mlsanity.com/paper/2510.10274/) (2025) - [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026) - [Diffusion Policy Policy Optimization](https://mlsanity.com/paper/2409.00588/) (2024) - [OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning](https://mlsanity.com/paper/2406.08858/) (2024) - [Steering Your Diffusion Policy with Latent Space Reinforcement Learning](https://mlsanity.com/paper/2506.15799/) (2025) - [BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion](https://mlsanity.com/paper/2508.08241/) (2025) - [SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning](https://mlsanity.com/paper/2401.16013/) (2024) - [Flow Matching Policy Gradients](https://mlsanity.com/paper/2507.21053/) (2025) - [ExBody2: Advanced Expressive Humanoid Whole-Body Control](https://mlsanity.com/paper/2412.13196/) (2024) - [HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit](https://mlsanity.com/paper/2502.13013/) (2025) - [RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning](https://mlsanity.com/paper/2510.14830/) (2025) - [Residual Off-Policy RL for Finetuning Behavior Cloning Policies](https://mlsanity.com/paper/2509.19301/) (2025) - [Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning](https://mlsanity.com/paper/2310.15145/) (2023) - [Generalizable Humanoid Manipulation with 3D Diffusion Policies](https://mlsanity.com/paper/2410.10803/) (2024) - [AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control](https://mlsanity.com/paper/2505.03738/) (2025) - [Humanoid-VLA: Towards Universal Humanoid Control with Visual Integration](https://mlsanity.com/paper/2502.14795/) (2025) - [LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction](https://mlsanity.com/paper/2506.13751/) (2025) - [FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation](https://mlsanity.com/paper/2505.06776/) (2025) - [BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning](https://mlsanity.com/paper/2511.04131/) (2025) - [WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control](https://mlsanity.com/paper/2512.11047/) (2025) - [EXPO: Stable Reinforcement Learning with Expressive Policies](https://mlsanity.com/paper/2507.07986/) (2025) - [BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities](https://mlsanity.com/paper/2503.05652/) (2025) ## Built on by (most cited first, 1 of 1) - [WholeBodyWAM: Learning Whole-Body World Action Models with Scalable Motion Priors](https://mlsanity.com/paper/2609.18197/) (2026) ## Abstract (arXiv) Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it challenging for conventional single-stage VLA architectures to coordinate locomotion, waist posture, and dual-arm manipulation effectively. Moreover, policies trained through offline behavior cloning can remain suboptimal during real-world deployment. Although online reinforcement learning can refine policies through real-world interaction, directly tuning large VLA backbones demands excessive computation and may introduce safety risks during real-robot exploration. To address these bottlenecks, we introduce HAF (Humanoid Adaptation Framework), a two-part framework consisting of HAF-VLA and HAF-Steer that transfers off-the-shelf generalist VLA foundation models to humanoid whole-body loco-manipulation. HAF-VLA is a hierarchical action-flow generator built on a pretrained flow-matching VLA. It splits full-body action denoising into three sequential stages with stage embeddings and cross-stage KV caches that retain kinematic dependencies, avoiding incoherent whole-body actions from one-shot generation. On top of the frozen HAF-VLA, HAF-Steer is a latent offline-to-online RL pipeline that leverages flow-matching invertibility and DCT-based dimensionality reduction to restrict RL optimization to a compact noise subspace and train a regularized SAC policy. This avoids updating the large VLA backbone and enables efficient real-world policy refinement. Evaluated on seven real-world humanoid loco-manipulation tasks, HAF surpasses vanilla single-stage VLA baselines and improves whole-body coordination and task performance. Project website: https://grange007.github.io/HAF .