Showing cs.ROShow all
2 papers · 1 filter
cs.RO2026
-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills
Siyao Xiao, Yuhong Zhang, Zhifang Liu +9
Current Vision-Language-Action (VLA) models predominantly rely on end-to-end fine-tuning. While effective, this paradigm compromises the inherent generalization capabilities of Vis…
cs.RO2026
TinyIO: Lightweight Reparameterized Inertial Odometry
Shanshan Zhang, Siyue Wang, Mengzi Chen +4
Inertial odometry (IO) is a widely used approach for localization on mobile devices; however, obtaining a lightweight IO model that also achieves high accuracy remains challenging.…