3 papers
cs.LG2026
Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL
Timo Klein, Thomas Lang, Andrii Shkabrii +3
Scaling self-supervised contrastive reinforcement learning (CRL) to 1000-layer Euclidean neural networks has enabled state-of-the-art goal-reaching performance, yet wall-clock time…
cs.RO2026
ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency
Wenda Yu, Tianshi Wang, Fengling Li +3
Vision-language-action (VLA) policies achieve strong performance in robotic manipulation but remain vulnerable to runtime disturbances that break the temporal alignment among visua…
cs.RO2026
AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
Wenda Yu, Tianshi Wang, Fengling Li +2
Vision-Language-Action (VLA) models have demonstrated strong performance in robotic manipulation, yet their closed-loop deployment is hindered by the high latency and compute cost…