2 papers
cs.RO2026
Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models
Houze Xu, Jizhong Li, Ziyi Ye
Vision-language-action (VLA) models provide a unified paradigm for connecting visual perception, language understanding, and robotic control. However, existing VLA models still fac…
cs.CV2026
LowAux-RDNet: Low-Pass Residual Supervision with Scene-Balanced Real-World Training for Single-Image Reflection Removal
Jizhong Li
Single-image reflection removal aims to recover a clean transmission layer from one image captured through glass. We study an explicit decomposition pipeline built on RDNet and int…