Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
AWM-VLA: AlignedWorld Modeling for Efficient and Explainable Vision-Language-Action Policies
An Lanji, Dawei Liu, Jin Li +3
Vision-language-action (VLA) models have become a powerful paradigm for generalist robotic manipulation, yet they are often reactive: the policy maps the current observation direct…
cs.CV2025
SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding
Shuang Cheng, Yuhua Jiang, Zineng Zhou +5
Block-wise discrete diffusion offers an attractive balance between parallel generation and causal dependency modeling, making it a promising backbone for vision-language modeling.…