VLANeXt: Recipes for Building Strong VLA Models

TL;DR

This paper introduces VLANeXt, a unified framework and recipe for building strong Vision-Language-Action models, demonstrating improved performance on benchmarks and real-world tasks.

Contribution

It systematically dissects the VLA design space, distills key findings into a practical recipe, and releases a unified codebase for future research.

Findings

Outperforms state-of-the-art on LIBERO and LIBERO-plus benchmarks.

Provides a unified framework simplifying VLA model development.

Releases an accessible codebase for reproducibility and further exploration.

Abstract

Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, leveraging strong visual and language understanding from Vision-Language Models for general-purpose policy learning. Yet, the current VLA landscape remains fragmented and exploratory. Although many groups have proposed their own VLA models, inconsistencies in training protocols and evaluation settings make it difficult to identify which design choices truly matter. To bring structure to this evolving space, we reexamine the VLA design space under a unified framework and evaluation setup. Starting from a simple VLA baseline similar to RT-2, which is the origin of VLA, we systematically dissect design choices along three dimensions: foundational components, perception essentials, and action modelling perspectives. From this study, we distill 12 key findings that together form a practical recipe for building strong VLA models. The outcome of this exploration is a simple yet effective model, VLANeXt. It outperforms the state-of-the-art methods on the LIBERO and LIBERO-plus benchmarks and demonstrates strong performance in real-world experiments. We release a unified and easy-to-use codebase to reproduce our findings, explore the design space, and develop new VLA variants on top of a shared foundation. The codebase is available at https://github.com/DravenALG/VLANeXt.