VLANeXt: Recipes for Building Strong VLA Models

[2602.18532] VLANeXt Family: A Systematic Study of VLA Models from Core Recipes to Emerging Paradigms Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2602.18532 (cs) [Submitted on 20 Feb 2026 ( v1 ), last revised 7 Oct 2026 (this version, v6)] Title: VLANeXt Family: A Systematic Study of VLA Models from Core Recipes to Emerging Paradigms Authors: Xiao-Ming Wu , Kang Liao , Yihang Luo , Bin Fan , Jian-Jian Jiang , Runze Yang , Zhonghua Wu , Wei-Shi Zheng , Chen Change Loy View PDF HTML (experimental) 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 modeling 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. Beyond identifying the core recipe, we further ask how far these design principles extend to the emerging paradigms in VLAs. We thus expand VLANeXt along several emerging directions, including model scaling, latent-action pretraining, latent predictive representation learning, and world action modeling. These studies give rise to the VLANeXt family, spanning compact and scaled VLA variants, latent-action models, JEPA-style predictive models, and World Action Models. Our results show that the core recipe provides a strong foundation across different model scales and emerging paradigms. Comments: Project Page: this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Robotics (cs.RO) Cite as: arXiv:2602.18532 [cs.CV] (or arXiv:2602.18532v6 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2602.18532 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Xiao-Ming Wu [ view email ] [v1] Fri, 20 Feb 2026 09:26:17 UTC (2,618 KB) [v2] Wed, 20 May 2026 07:29:11 UTC (5,505 KB) [v3] Tue, 25 Aug 2026 08:29:03 UTC (5,508 KB) [v4] Thu, 24 Sep 2026 13:37:39 UTC (4,665 KB) [v5] Fri, 25 Sep 2026 04:02:28 UTC (2,769 KB) [v6] Wed, 7 Oct 2026 09:16:51 UTC (2,768 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CV < prev | next > new | recent | 2026-02 Change to browse by: cs cs.AI cs.RO References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• VLANeXt: Recipes for Building Strong VLA Models#670498
• Replication Data for: Virtual measurements for exterior vibro-acoustic problems using experimental modal models#644658
• Recovering pattern speeds of simulated face-on barred galaxies via Schwarzschild modelling#1142498
• SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe#153002
• Projeto e prototipação de interfaces e redes intrachip não-síncronas em FGPAs#946510