DAM-VLA: A Dynamic Action Model-Based Vision-Language-Action Framework for Robot Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peng, Xiongfeng, Yu, Jiaqian, Li, Dingzhe, Jin, Yixiang, Xu, Lu, Mao, Yamin, Zhang, Chao, Li, Weiming, Jang, Sujin, Lee, Dongwook, Ji, Daehyun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914361423953920
author Peng, Xiongfeng
Yu, Jiaqian
Li, Dingzhe
Jin, Yixiang
Xu, Lu
Mao, Yamin
Zhang, Chao
Li, Weiming
Jang, Sujin
Lee, Dongwook
Ji, Daehyun
author_facet Peng, Xiongfeng
Yu, Jiaqian
Li, Dingzhe
Jin, Yixiang
Xu, Lu
Mao, Yamin
Zhang, Chao
Li, Weiming
Jang, Sujin
Lee, Dongwook
Ji, Daehyun
contents In dynamic environments such as warehouses, hospitals, and homes, robots must seamlessly transition between gross motion and precise manipulations to complete complex tasks. However, current Vision-Language-Action (VLA) frameworks, largely adapted from pre-trained Vision-Language Models (VLMs), often struggle to reconcile general task adaptability with the specialized precision required for intricate manipulation. To address this challenge, we propose DAM-VLA, a dynamic action model-based VLA framework. DAM-VLA integrates VLM reasoning with diffusion-based action models specialized for arm and gripper control. Specifically, it introduces (i) an action routing mechanism, using task-specific visual and linguistic cues to select appropriate action models (e.g., arm movement or gripper manipulation), (ii) a dynamic action model that fuses high-level VLM cognition with low-level visual features to predict actions, and (iii) a dual-scale action weighting mechanism that enables dynamic coordination between the arm-movement and gripper-manipulation models. Across extensive evaluations, DAM-VLA achieves superior success rates compared to state-of-the-art VLA methods in simulated (SIMPLER, FurnitureBench) and real-world settings, showing robust generalization from standard pick-and-place to demanding long-horizon and contact-rich tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00926
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DAM-VLA: A Dynamic Action Model-Based Vision-Language-Action Framework for Robot Manipulation
Peng, Xiongfeng
Yu, Jiaqian
Li, Dingzhe
Jin, Yixiang
Xu, Lu
Mao, Yamin
Zhang, Chao
Li, Weiming
Jang, Sujin
Lee, Dongwook
Ji, Daehyun
Robotics
In dynamic environments such as warehouses, hospitals, and homes, robots must seamlessly transition between gross motion and precise manipulations to complete complex tasks. However, current Vision-Language-Action (VLA) frameworks, largely adapted from pre-trained Vision-Language Models (VLMs), often struggle to reconcile general task adaptability with the specialized precision required for intricate manipulation. To address this challenge, we propose DAM-VLA, a dynamic action model-based VLA framework. DAM-VLA integrates VLM reasoning with diffusion-based action models specialized for arm and gripper control. Specifically, it introduces (i) an action routing mechanism, using task-specific visual and linguistic cues to select appropriate action models (e.g., arm movement or gripper manipulation), (ii) a dynamic action model that fuses high-level VLM cognition with low-level visual features to predict actions, and (iii) a dual-scale action weighting mechanism that enables dynamic coordination between the arm-movement and gripper-manipulation models. Across extensive evaluations, DAM-VLA achieves superior success rates compared to state-of-the-art VLA methods in simulated (SIMPLER, FurnitureBench) and real-world settings, showing robust generalization from standard pick-and-place to demanding long-horizon and contact-rich tasks.
title DAM-VLA: A Dynamic Action Model-Based Vision-Language-Action Framework for Robot Manipulation
topic Robotics
url https://arxiv.org/abs/2603.00926