2 papers
cs.RO2026
CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors
Dachong Li, ZhuangZhuang Chen, Jin Zhang +1
Vision--Language--Action (VLA) models often use intermediate representations to connect multimodal inputs with continuous control, yet spatial guidance is often injected implicitly…
cs.CV2025
Small Convolutional Kernel with Large Kernel Effect
Dachong Li, Li Li, Zhuangzhuang Chen +1
Large kernels make standard convolutional neural networks (CNNs) great again over transformer architectures in various vision tasks. Nonetheless, recent studies meticulously design…