PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations

Hugging Face Daily Papers Papers
vision-language-action robotics world-model physical-dynamics manipulation simulation-benchmarks

Summary

PDRVLA 是一篇机器人操作研究论文，提出在视觉-语言-动作（VLA）模型中加入轻量级物理动力学模块，通过世界模型监督预测未来视觉特征，从而在不引入在线视频生成延迟的情况下提升机器人动作生成性能，并在 LIBERO、RoboTwin 2.0 等仿真基准上取得领先成功率。

Vision--Language--Action (VLA) models generate robot actions from visual observations and language instructions, but their understanding of physical dynamics remains limited. Video world models can capture scene dynamics, yet generating future videos introduces high latency into the control loop. We introduce PDRVLA, whose lightweight Physical Dynamics Module extracts physical tokens from vision--language features to condition action generation without online video generation. The module learns through direct prediction of future RGB, depth, and optical-flow features, with auxiliary supervision through a frozen pretrained video world model. Training relies entirely on publicly available data, expanded through human-to-robot synthesis, subtask annotation, and embodied chain-of-thought (ECoT) annotation. Across four simulation benchmarks, PDRVLA achieves success rates of 99.3% on LIBERO, 89.9% on LIBERO-Plus, 93.6% on RoboTwin~2.0, and 81.5% on SimplerEnv. Ablations show improved future prediction with world-model supervision and evaluate how subtask conditioning, future object-pose supervision, and ECoT training affect action success.
Original Article
View Cached Full Text

Cached at: 10/28/26, 09:26 AM

Paper page - PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations

Source: https://huggingface.co/papers/2610.37381

Abstract

PDRVLA improves robot action generation by integrating a lightweight physical dynamics module that predicts future visual features with world-model supervision, avoiding online video generation latency.

Vision--Language--Action (VLA) models generate robot actions from visual observations and language instructions, but their understanding of physical dynamics remains limited.Video world modelscan capture scene dynamics, yet generating future videos introduces high latency into the control loop. We introduce PDRVLA, whose lightweightPhysical Dynamics Moduleextractsphysical tokensfrom vision--language features to condition action generation without online video generation. The module learns through direct prediction of future RGB, depth, andoptical-flow features, with auxiliary supervision through a frozen pretrained video world model. Training relies entirely on publicly available data, expanded throughhuman-to-robot synthesis,subtask annotation, andembodied chain-of-thought(ECoT) annotation. Across four simulation benchmarks, PDRVLA achieves success rates of 99.3% on LIBERO, 89.9% on LIBERO-Plus, 93.6% on RoboTwin~2.0, and 81.5% on SimplerEnv. Ablations show improved future prediction with world-model supervision and evaluate how subtask conditioning, future object-pose supervision, and ECoT training affect action success.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2610\.37381

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.37381 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.37381 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.37381 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

MotionVLA: Vision-Language-Action Model for Humanoid Motion

Hugging Face Daily Papers

Proposes MotionVLA, a vision-language-action model for humanoid motion generation using a dual-stream frequency tokenizer that separately encodes pose and physical dynamics, achieving better diversity and consistency.