Weight-Tied Adaptive Recursive Vision–Language–Action Transformer for Efficient Multimodal Robotic Control
Journal of Smart Algorithms and Applications (JSAA) · 24.04.2026 · 3 (1) · 36-50
DOI: 10.66279/pk83n728 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Smart Algorithms and Applications (JSAA), online erschienen am 24.04.2026. Verfasst von Howaida Allam und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Vision-Language-Action (VLA) models unify perception, language understanding, and control within a single learning framework, enabling robots to execute manipulation tasks specified through natural language and visual observations. Despite recent progress, many existing VLA systems rely on fixed-depth transformer architectures, resulting in high computational cost and limited adaptability to varying task complexity. We introduce an adaptive recursive VLA architecture that decouples reasoning depth from parameter count through iterative transformer refinement with weight-tied layers. The proposed model processes temporally windowed RGB observations, proprioceptive states, and language instructions using pretrained vision--language encoders and lightweight proprioceptive encoding. Multimodal features are integrated via gated fusion and iteratively refined through recursive transformer iterations, enabling variable-depth reasoning without increasing model size. The refined latent representation conditions structured continuous action prediction, including Cartesian end-effector translation, 6D rotation representation, and gripper actuation. Experimental evaluation on the large-scale DROID robotic manipulation dataset demonstrates substantial improvements over non-recursive baselines. The recursive model achieves a mean squared error (MSE) of 0.020, representing an 82.4\% reduction compared to the baseline (MSE: 0.1137). Prediction accuracy reaches 66.82\% of actions within 0.10 tolerance and 86.15\% within 0.20 tolerance. Position prediction achieves correlations exceeding 0.84-0.96 across all axes, while rotation components show correlations ranging from 0.88 to 0.98. The model maintains computational efficiency with only a 1.5$\times$ inference-time overhead while achieving an 82\% improvement in accuracy. These results validate recursive reasoning as an effective and computationally efficient mechanism for accurate, adaptable multimodal robotic control.
Zitieren
APA
Allam, H., & Khan, I. U. (2026). Weight-Tied Adaptive Recursive Vision–Language–Action Transformer for Efficient Multimodal Robotic Control. Journal of Smart Algorithms and Applications (JSAA), 3(1), 36-50. https://doi.org/10.66279/pk83n728
Vancouver
Allam H, Khan IU. Weight-Tied Adaptive Recursive Vision–Language–Action Transformer for Efficient Multimodal Robotic Control. Journal of Smart Algorithms and Applications (JSAA). 2026;3(1):36-50. doi:10.66279/pk83n728
BibTeX
@article{Allam2026,
author = {Allam, Howaida and Khan, Inam Ullah},
title = {Weight-Tied Adaptive Recursive Vision–Language–Action Transformer for Efficient Multimodal Robotic Control},
journal = {Journal of Smart Algorithms and Applications (JSAA)},
year = {2026},
volume = {3},
number = {1},
pages = {36--50},
doi = {10.66279/pk83n728}
}
EUVIMED