International Journal of Neural Network, 2026, 5(1); doi: 10.38007/NN.2026.050115.
Qingyao Jia
New York University, Tandon School of Engineering, Brooklyn, 11201, New York, United States
Vision-Language-Action (VLA) foundation models extend robot learning from task-specific policies to open-vocabulary, language-conditioned manipulation, but published benchmark results do not independently validate a new deployment architecture. This evidence-synthesis paper reviews representative VLA systems and datasets from 2023-2026, distinguishes between peer-reviewed evidence, preprints and official technical sources, and re-presents public OpenVLA results with their original evaluation scope. In the published BridgeData V2 WidowX suite, the mean success rates are 18.5% for RT-1-X, 20.0% for Octo, 50.6% for RT-2-X, and 70.6% for OpenVLA; in the Franka-Tabletop adaptation study, pretrained OpenVLA fine-tuned on target data reaches a trial-weighted 67.2% over 99 rollouts. These figures support claims about the cited models only. Based on the above evidence, this paper proposes a semantic slow-loop, action fast-loop and independent runtime-assurance layer, along with embodiment-aware training, edge/local execution roles, staged validation and a non-compensatory evaluation dashboard. The framework is shown as a conceptual engineering guideline for implementation and formal safety analysis of controlled robot validation before the deployment claim can be made.
Vision-language-action model; Intelligent robot; Embodied intelligence; Evidence synthesis; Runtime assurance; Robot manipulation
Qingyao Jia, Application of Multimodal Large Models Combining Vision and Language In Intelligent Robots. International Journal of Neural Network (2026), Vol. 5, Issue 1: 142-155. https://doi.org/10.38007/NN.2026.050115.
[1] Driess D, Xia F, Sajjadi MSM, et al. PaLM-E: An Embodied Multimodal Language Model. Proceedings of the 40th International Conference on Machine Learning, PMLR, 2023, 202: 8469-8488.
[2] Zitkovich B, Yu T, Xu S, et al. RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control. Proceedings of the 7th Conference on Robot Learning, PMLR, 2023, 229: 2165-2183.
[3] Zhang, Y. (2026). Exploration of Enterprise Big Data Microservice Architecture Based on Domain-Driven Design (DDD). Procedia Computer Science, 282, 1994-2003.
[4] Zhang, Z. (2026). Research on Service-oriented Packaging of AI Systems and Data-driven Decision Support for Real-world Business Processes. Engineering Advances, 6(3).
[5] Zhang, Y. (2025, January). Research on the Application and Optimization of Multi Dimensional Data Model Based on Kylin in Enterprise Technology Management. In International Conference on Innovative Computing (pp. 234-241). Singapore: Springer Nature Singapore.
[6] Jingzhi Yin. (2026). Constructing a CMBS Default Risk Sentiment Index Using Financial Text Embeddings and Evaluating Its Predictive Effectiveness. Engineering Advances, 6(1), 50-54.
[7] Fei, W., Xue, W., & Wang, B. (2025). Research on the innovative path of rural education teaching methods from the perspective of PBE and PBL integration. Int. Acad. J. Humanit. Soc. Sci.
[8] Fei, W. (2026). Families Of Chinese Background In Rural Alabama: Education, Immigration, And Identity.
[9] Wendan Xue, Wen Fei. An Analytical Study on the Differences and Determinants of Basic Education Resource Allocation in Rural China and the United States. International Journal of Educational Research and Development, 1(3), 13-17.
[10] Boli Wang, Wen Fei. Innovations and practices in the classroom for rural aesthetic education in the perspective of school integration. International Journal of Educational Research and Development, 3(1), 36-41.
[11] Fei, W., & Qian, J. (2026). Application and Exploration of Reverse Instructional Design in the Teaching of the Primary School Physical Education" Walking and Playing" Unit. Journal of Sociology and Education, 2(2).
[12] Wen Fei, Jianrong Qian. Research on Value Guidance and Practical Pathways for Constructing the Professional Culture of Teachers. International Journal of Educational Research and Development, 2(4), 27-30.
[13] Qian, X. (2026). Intelligent Supply Chain Collaboration Models in Retail Supported by Omnichannel Marketing Data. Advances in Computer and Communication, 7(3).
[14] Su, J. (2026). Android Communication Reliability Enhancement Architecture Based on Multi Link Diversity Transmission.
[15] Liu, S. (2026). Design and Implementation of Retrieval Enhancement Generation Method for Enterprise Knowledge Base.
[16] Su, J. (2026, July). Research on Machine Learning-based Abnormal Traffic Detection and Anti-Interference Methods for Android End-to-End Encrypted Transmission in High-Reliability Application Scenarios. In 2026 5th International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE) (pp. 1-6). IEEE.
[17] Qian, X. (2026, July). Application of the Combination Model of Prophet and LSTM in Multi-Level Inventory Demand Prediction for Retail Supply Chain of CPG-Consumer Packaged Foods. In 2026 5th International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE) (pp. 1-7). IEEE.
[18] Jin, C. (2026). Construction and Empirical Study of Credit Risk Assessment Index System for Small and Micro Enterprises in Commercial Banks.
[19] Jin, C. (2026). Application of Data Mining Technology in Predicting User Churn and Retention Strategies in E-Commerce.
[20] Zhang, Z. (2026). User Behavior Anomaly Identification Integrating Telemetry Data and Its Application in Consumer Finance Risk Control.
[21] Liu, S. (2026). Automatic Generation Method and Implementation of Web Front-End Components Based on Generative AI.
[22] Xin, H. (2026). Research on Distributed Data Pipelines and Event-Driven Architecture for Freight Visibility.
[23] Zhang, Z. (2026). User Behavior Device Reliability Joint Modeling and Intelligent Risk Control Practice In Consumer Technology.
[24] Wang, B. (2025, November). Research on Performance Improvement of Personalized Recommendation System for E-commerce Platform Based on Big Data and Collaborative Filtering Algorithm. In International Conference on Computational Technologies for Research in Data Analytics (pp. 36-46). Cham: Springer Nature Switzerland.
[25] Wang, Z. (2026). Research on Operation Data Analysis and Efficiency Improvement of the New Energy Industry Based on Machine Learning. Procedia Computer Science, 285, 605-612.
[26] Ma, W. (2026). Research on Reliability Enhancement of Cloud Data Platform Driven by Adaptive Sharding and Fault Tolerance Algorithms. Procedia Computer Science, 285, 1020-1029.
[27] Chi, C. (2026, July). Credit Risk Dynamic Pricing Representation Learning Algorithm based on Long-Term SelfSupervised Learning. In 2026 5th International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE) (pp. 1-7). IEEE.
[28] Zhang, Y. (2026). A Framework for Semantic Alignment and Privacy Compliance of Large-Scale Language Models for Cross-Border Data Governance. Procedia Computer Science, 285, 1039-1047.
[29] Sun, L. (2026, July). Low-Latency Optimized Architecture for Distributed Stream Processing Systems for RealTime Bidding Advertising. In 2026 5th International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE) (pp. 1-7). IEEE.
[30] Sun, X. (2026). Research on Online Identification and Alarm Mechanism for Abnormal Power Quality in Data Centers.