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.
Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review
Chef Robotics；RovifyLab；IT Application Research Center, Jeonbuk Regional Branch；Department of Electrical, Computer and Software Engineering（电气与计算机软件工程系）
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
University of Science and Technology of China（中国科学技术大学）；Zhongguancun Academy, Beijing, China（中关村学院）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua University（清华大学）；Eastern Institute of Technology, Ningbo（宁波东部科技研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Nankai University（南开大学）
HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学）；Beijing Academy of Artificial Intelligence (BAAI)（北京人工智能研究院）；CUHK（香港中文大学）
What Matters in Building Vision-Language-Action Models for Generalist Robots
Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；ByteDance Research（字节跳动研究院）；CASIA MAIS-NLPR；Shanghai Jiao Tong University（上海交通大学）；National University of Singapore（新加坡国立大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Beijing University of Posts and Telecommunications（北京邮电大学）
VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Training
Institute of AI (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信）；Lumos Robotics（Lumos机器人）；University of Science and Technology of China（中国科学技术大学）；Northwestern Polytechnical University（西北工业大学）；Shanghai Jiao Tong University（上海交通大学）；East China University of Science and Technology（东华大学）；Harbin Engineering University（哈尔滨工程大学）；Fudan University（复旦大学）
What Makes an Efficient VLA? Navigating Action-Head Design, Scaling, and Latency
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；AI Lab, The Yangtze River Delta（长三角人工智能实验室）；Li Auto Inc.（理想汽车）；School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；University College London（伦敦大学学院）；University of Edinburgh（爱丁堡大学）
CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking
Autel Robotics（大疆创新科技有限公司）；Northeast Normal University（东北师范大学）；Southern University of Science and Technology（南方科技大学）；Peking University（北京大学）；University of Hong Kong（香港大学）
Dexora: Open-source VLA for High-DoF Bimanual Dexterity
Tsinghua University（清华大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；The University of Hong Kong（香港大学）；Shanghai Jiao Tong University（上海交通大学）；ShanghaiTech University（上海科技大学）；Peking University（北京大学）
CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion
Technical University of Munich（慕尼黑技术大学）；TUM School of Computation, Information and Technology（TUM计算、信息与技术学院）；Department of Computer Engineering, Learning Systems and Robotics Lab（计算机工程系、学习系统与机器人实验室）；Munich Institute of Robotics and Machine Intelligence (MIRMI)（慕尼黑机器人与机器智能研究所（MIRMI））；Robotics Institute Germany（德国机器人研究所）；Munich Center for Machine Learning（慕尼黑机器学习中心）
Dept. of Comp. Sci. and Tech., Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint ML Center, Tsinghua University（计算机科学与技术系，人工智能研究院，BNRist中心，THBI实验室，清华-博世联合机器学习中心，清华大学）；Peking University（北京大学）；Horizon Robotics
MolmoAct2: Action Reasoning Models for Real-world Deployment
Allen Institute for AI（艾伦人工智能研究所）；University of Washington（华盛顿大学）；National University of Singapore（新加坡国立大学）；University of Pennsylvania（宾夕法尼亚大学）；Johns Hopkins University（约翰霍普金斯大学）；Amazon（亚马逊公司）；University of Michigan（密歇根大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
