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

TL;DR

Evo-1 is a lightweight vision-language-action model that achieves state-of-the-art performance in robotic tasks while significantly reducing computational costs and maintaining strong generalization without large-scale pretraining.

Contribution

The paper introduces Evo-1, a novel efficient VLA model with a new architecture and training paradigm that preserves semantic alignment and improves deployment efficiency.

Findings

Achieves 12.4% and 6.9% improvements on Meta-World and RoboTwin.

Attains 94.8% on LIBERO benchmark.

Reaches 78% success rate in real-world tests.

Abstract

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.