Aug 2026· IEEE International Conference on Embedded and Real-Time Computing Systems and Applications· pp. 228-229· 0 citations· 3 references
Abstract
Vision-language-action (VLA) models map language instructions and multi-view observations to robot actions, but dense visual-token processing imposes substantial inference overhead. This paper presents TADP, a training-free dynamic visualtoken pruning framework for efficient VLA inference. TADP estimates task-conditioned visual-token importance after early vision-language interaction, decouples main- and wrist-view budgets, reuses keyframe scores under temporal consistency, and refreshes view-specific caches independently. On LIBERO, TADP achieves a 96.25% average success rate while using only 39% of OpenVLA-OFT FLOPs, corresponding to a 61% FLOP reduction.
Vision-Language-Action (VLA) models enable generalizable robotic control but remain computationally expensive. Token caching provides a training-free, plug-and-play acceleration alternative. However, existing VLA caching does not fully exploit a key inductive bias of VLA models: text-vision synergy, wherein textual sem...
Qian-Er Li, Cheng-Jie Zhang, Jing-Wen Chen et al.· 0 citations
Within this trained-task regime, DEM sits on the observed success--latency--energy frontier and provides a strong, efficient baseline for language-conditioned robot skills.
Xia-Tao Sun, Chen Liang, Zi-Yao Zeng et al.· 2 citations
A neuro-symbolic framework that combines learned VLA control with explicit task graphs and multimodal procedural memory is investigated, which positions structured symbolic reasoning and demonstration-derived visual guidance as complementary mechanisms for reliable long-horizon VLA manipulation.
Vivek Chavan, Ya-Huan Shi, O. Heimann et al.· 0 citations
WA-SpecDec is proposed, a world-aware speculative decoding framework that injects world-model-derived physical scene awareness during the VLA prefill stage, producing shared world-aware prefill states for draft proposal and target verification without changing the relaxed acceptance rule.
The proposed hierarchical long-horizon VLA architecture with an explicit language-memory module improves the success rate and robustness of VLA models on complex long-horizon tasks while providing an interpretable semantic account of the decision process.
A reliable TTT framework for VLA policies (VANE), where candidate updates are isolated from the live policy, evaluated on subsequent observations, and committed only when supported by future evidence, making adaptation selective and reversible.
H. Ji, Guo-Yang Xia, Luo-Yang Sun et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
