ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Models

Computer Science > Robotics [Submitted on 26 Mar 2026] ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Models Yiru Wang, Anqing Jiang, Shuo Wang, Yuwen Heng, Zichong Gu, Hao Sun The integration of Vision-Language-Action (VLA) models into autonomous driving systems offers a unified framework for interpreting complex scenes and executing control commands. However, the necessity to incorporate historical multi-view frames for accurate temporal reasoning imposes a severe computational burden, primarily driven by the quadratic complexity of self-attention mechanisms in Large Language Models (LLMs). To alleviate this bottleneck, we propose ETA-VLA, an Efficient Token Adaptation framework for VLA models. ETA-VLA processes the past n frames of multi-view images and introduces a novel Intra-LLM Sparse Aggregator (ILSA). Drawing inspiration from human driver attention allocation, ILSA dynamically identifies and prunes redundant visual tokens guided by textual queries and temporal consistency. Specifically, we utilize a text-guided scoring mechanism alongside a diversity-preserving sparsification strategy to select a sparse subset of critical tokens, ensuring comprehensive awareness of the driving scene. Extensive experiments on the NAVSIM v2 demonstrate that ETA-VLA achieves driving performance comparable to state-of-the-art baselines while reducing computational FLOPs by approximately 32\%. Notably, our method prunes 85% of visual tokens and reduces inference FLOPs by 61\%, but still retaining 94% of the original accuracy on the NAVSIM v2 benchmark. Subjects: Robotics (cs.RO); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.25766 [cs.RO]   (or arXiv:2603.25766v1 [cs.RO] for this version)   https://doi.org/10.48550/arXiv.2603.25766 Focus to learn more Submission history From: Yiru Wang [view email] [v1] Thu, 26 Mar 2026 06:53:42 UTC (650 KB) Access Paper: HTML (experimental) view license Current browse context: cs.RO < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.AI References & Citations NASA ADS 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 Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)