Universal Pose Pretraining for Generalizable Vision-Language-Action Policies

arXiv:2602.19710 · cs.CV, cs.LG, cs.RO · Submitted 2026-02-23 · Read on arXiv

cs.CV, cs.LG, cs.RO

Submitted: 2026-02-23

Updated: 2026-09-27

Comments: Accepted to Robotics: Science and Systems (RSS) 2026. Project website: https://hetolin.github.io/PoseVLA

Journal ref: Robotics: Science and Systems, 2026

Code: https://github.com/QwenLM/Qwen3-VL

Project page: https://hetolin.github.io/PoseVLA

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

Terminology

• Grounding — 37× in this paper · explained in 3 episodes
• Benchmark — 22× in this paper · explained in 2 episodes
• Alignment — 21× in this paper · explained in 1 episode
• Ablation — 14× in this paper · explained in 1 episode
• Generalization — 12× in this paper · explained in 13 episodes
• Tokenization — 8× in this paper · explained in 2 episodes
• Ablation study — 7× in this paper · explained in 1 episode
• Robustness — 6× in this paper · explained in 5 episodes
• Action Space — 5× in this paper · explained in 1 episode
• Embeddings — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Vision-Language Model — 4× in this paper
• Decoupling — 3× in this paper · explained in 2 episodes
• Flow Matching — 3× in this paper · explained in 8 episodes
• Quantization — 3× in this paper · explained in 12 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Data Heterogeneity — 2× in this paper · explained in 3 episodes
• Existing Vision-Language-Action — 2× in this paper
• Fidelity — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Latent Representation — 2× in this paper · explained in 2 episodes
• Latent Representations — 2× in this paper · explained in 3 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Trace — 2× in this paper · explained in 2 episodes
• VLA Models — 2× in this paper · explained in 3 episodes
• Vision-Language-Action (VLA) Models — 2× in this paper · explained in 2 episodes
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Visual Spatial Tuning — 2× in this paper
• 6D Object Pose Estimation — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Action Flow — 1× in this paper · explained in 1 episode
• Adaptive Reasoning — 1× in this paper · explained in 2 episodes
• Alignment Pre-training — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decoupled Learning — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Granularity Mismatch — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• International Conference on Robotics and Automation — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Point Clouds — 1× in this paper · explained in 2 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Vision-Language Model (VLM) — 1× in this paper · explained in 3 episodes
• Visual Question Answering — 1× in this paper
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Qwen2.5-VL Technical Report
• PaliGemma: A versatile 3B VLM for transfer
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• WorldVLA: Towards Autoregressive Action World Model
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• Training Strategies for Efficient Embodied Reasoning
• Language-Image Models with 3D Understanding
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• VLA-0: Building State-of-the-Art VLAs with Zero Modification
• Seed1.5-VL Technical Report
• Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
• OpenVLA: An Open-Source Vision-Language-Action Model
• MolmoAct: Action Reasoning Models that can Reason in Space
• Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
• Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
• OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning
• Flow Matching for Generative Modeling
• HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
• Rectified Flow: A Marginal Preserving Approach to Optimal Transport

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models