HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model

arXiv:2605.31234 · cs.RO · Submitted 2026-05-29 · Read on arXiv

cs.RO

Submitted: 2026-05-29

Updated: 2026-10-09

Code: https://github.com/anonymity35/HARP-VLA

Terminology

• Alignment — 64× in this paper · explained in 1 episode
• Action Space — 9× in this paper · explained in 1 episode
• Benchmark — 9× in this paper · explained in 2 episodes
• Adaptation — 8× in this paper · explained in 1 episode
• Embeddings — 6× in this paper · explained in 2 episodes
• Representation Learning — 5× in this paper · explained in 2 episodes
• Abstraction — 4× in this paper · explained in 1 episode
• Dynamic Time Warping — 4× in this paper
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Dynamic Time Warping (DTW) — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Vision-Language-Action (VLA) Models — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• HARP Latent Action Model — 2× in this paper
• Action Flow — 1× in this paper · explained in 1 episode
• Cross-Embodiment Transfer — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• VLA Models — 1× in this paper · explained in 3 episodes

Sources

• Latent Action Pretraining from Videos
• UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
• UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
• MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training
• DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation
• OpenVLA: An Open-Source Vision-Language-Action Model
• RT-1: Robotics Transformer for Real-World Control at Scale
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
• Octo: An Open-Source Generalist Robot Policy
• RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches
• Flow as the Cross-Domain Manipulation Interface
• Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow
• RoVi-Aug: Robot and Viewpoint Augmentation for Cross-Embodiment Robot Learning
• OpenEgo: A Large-Scale Multimodal Egocentric Dataset for Dexterous Manipulation
• RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot
• Human2Robot: Learning Robot Actions from Paired Human-Robot Videos
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
• Learning Generalizable Robot Policy with Human Demonstration Video as a Prompt

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