arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.04555cs.ROcs.CV
收藏

Evo-1:轻量级视觉-语言-动作模型,保持语义对齐

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

School of AI, Shanghai Jiao Tong University(上海交通大学人工智能学院);EvoMind Tech(EvoMind科技);IAAR-Shanghai(IAAR-上海);SII;Carnegie Mellon University(卡内基梅隆大学);University of Cambridge(剑桥大学);Nanyang Technological University(南洋理工大学)

Tao Lin, Yilei Zhong, Yuxin Du, Jingjing Zhang, Jiting Liu, Yinxinyu Chen, Encheng Gu, Ziyan Liu, Hongyi Cai, Yanwen Zou, Lixing Zou, Zhaoye Zhou, Gen Li, Bo Zhao

AI总结:

Evo-1是一种轻量级的视觉-语言-动作模型,通过减少计算并保持语义对齐,实现了高效的部署和强大的性能。

摘要:

视觉-语言-动作(VLA)模型已经发展成为一种强大的框架,能够统一感知、语言和控制,使机器人能够通过多模态理解执行多样化任务。然而,当前的VLA模型通常包含大量参数,并依赖大量机器人数据预训练,导致训练过程中的计算成本高,以及在实时推理中的部署性有限。此外,大多数训练范式往往退化了视觉-语言主干的感知表示,导致过拟合和对下游任务的泛化能力差。在本工作中,我们提出了Evo-1,一种轻量级的VLA模型,通过减少计算并提高部署效率,同时在不预训练机器人数据的情况下保持强大的性能。Evo-1基于原生的多模态视觉-语言模型(VLM),结合了一种新的交叉调制扩散变压器以及优化的整合模块,共同形成一个有效的架构。我们进一步引入了两阶段训练范式,逐步对齐动作与感知,保留VLM的表示。值得注意的是,仅拥有0.77亿参数的Evo-1在Meta-World和RoboTwin套件上取得了最先进的结果,分别超过了先前最佳模型12.4%和6.9%,并在LIBERO上也取得了94.8%的竞争力结果。在现实世界评估中,Evo-1在高推理频率和低内存开销下达到了78%的成功率,优于所有基线方法。我们发布了代码、数据和模型权重,以促进未来对轻量级和高效VLA模型的研究。

英文摘要:

Vision-Language-Action (VLA) models have emerged as a powerful framework that unifies perception, language, and control, enabling robots to perform diverse tasks through multimodal understanding. However, current VLA models typically contain massive parameters and rely heavily on large-scale robot data pretraining, leading to high computational costs during training, as well as limited deployability for real-time inference. Moreover, most training paradigms often degrade the perceptual representations of the vision-language backbone, resulting in overfitting and poor generalization to downstream tasks. In this work, we present Evo-1, a lightweight VLA model that reduces computation and improves deployment efficiency, while maintaining strong performance without pretraining on robot data. Evo-1 builds on a native multimodal Vision-Language model (VLM), incorporating a novel cross-modulated diffusion transformer along with an optimized integration module, together forming an effective architecture. We further introduce a two-stage training paradigm that progressively aligns action with perception, preserving the representations of the VLM. Notably, with only 0.77 billion parameters, Evo-1 achieves state-of-the-art results on the Meta-World and RoboTwin suite, surpassing the previous best models by 12.4% and 6.9%, respectively, and also attains a competitive result of 94.8% on LIBERO. In real-world evaluations, Evo-1 attains a 78% success rate with high inference frequency and low memory overhead, outperforming all baseline methods. We release code, data, and model weights to facilitate future research on lightweight and efficient VLA models.

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。

↑