LLaDA-VLA：视觉语言扩散动作模型
LLaDA-VLA: Vision Language Diffusion Action Models
AI总结：
本文提出LLaDA-VLA，首个基于预训练扩散视觉语言模型的机器人操作模型，通过局部特殊令牌分类和分层动作解码，在仿真和真实机器人上显著超越现有VLA。
摘要：
自回归视觉语言模型（VLM）的快速发展激发了人们对用于机器人操作的视觉语言动作模型（VLA）的日益浓厚的兴趣。最近，掩码扩散模型作为一种不同于自回归模型的范式，开始在文本生成和多模态应用中展现出具有竞争力的性能，从而推动了一系列基于扩散的视觉语言模型（d-VLM）的发展。然而，利用此类模型进行机器人策略学习在很大程度上仍未得到探索。在这项工作中，我们提出了LLaDA-VLA，这是首个基于预训练d-VLM构建的用于机器人操作的视觉语言扩散动作模型。为了有效地将d-VLM适配到机器人领域，我们引入了两个关键设计：（1）一种局部特殊令牌分类策略，用特殊动作令牌分类取代全词汇分类，降低了适配难度；（2）一种分层动作结构化解码策略，该策略考虑动作内部及动作之间的依赖关系，对动作序列进行分层解码。大量实验表明，LLaDA-VLA在仿真和真实机器人上均显著优于最先进的VLA模型。
英文摘要：
The rapid progress of auto-regressive vision-language models (VLMs) has inspired growing interest in vision-language-action models (VLA) for robotic manipulation. Recently, masked diffusion models, a paradigm distinct from autoregressive models, have begun to demonstrate competitive performance in text generation and multimodal applications, leading to the development of a series of diffusion-based VLMs (d-VLMs). However, leveraging such models for robot policy learning remains largely unexplored. In this work, we present LLaDA-VLA, the first Vision-Language-Diffusion-Action model built upon pretrained d-VLMs for robotic manipulation. To effectively adapt d-VLMs to robotic domain, we introduce two key designs: (1) a localized special-token classification strategy that replaces full-vocabulary classification with special action token classification, reducing adaptation difficulty; (2) a hierarchical action-structured decoding strategy that decodes action sequences hierarchically considering the dependencies within and across actions. Extensive experiments demonstrate that LLaDA-VLA significantly outperforms state-of-the-art VLAs on both simulation and real-world robots.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
