Humanoid Loco-Manipulation With Discrete VLA Model

arXiv:2609.35709 · cs.RO · Submitted 2026-09-28 · Read on arXiv

cs.RO

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/NVlabs/GR00T-WholeBodyControl

Project page: https://horizonrobotics.github.io/gail/Holo-M/ABSTRACT

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Action Space — 11× in this paper · explained in 1 episode
• Benchmark — 10× in this paper · explained in 2 episodes
• Humanoid Everyday — 10× in this paper
• Tokenization — 10× in this paper · explained in 2 episodes
• Action Groups — 9× in this paper · explained in 1 episode
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Adaptation — 5× in this paper · explained in 1 episode
• Decode — 5× in this paper · explained in 2 episodes
• VLA Models — 5× in this paper · explained in 3 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Generalization — 2× in this paper · explained in 13 episodes
• Action Decoder — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes

Sources

• SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation
• G0.5: One Autoregressive Stream for Robot Reasoning and Action
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization
• HoloMotion-1 Technical Report
• Qwen3-VL Technical Report
• World Action Models are Zero-shot Policies

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies