Author

Xiao-Jiang Peng

h-index 5 View on Semantic Scholar

We have 2 of 19 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

ATI-VLA: Action-Centric Predictive Vision-Language-Action Models via Actionable Alignment Then Adaptive Injection

The introduction of ATI-VLA, an Action-Centric Predictive Vision-Language-Action framework via Actionable Alignment Then Adaptive Injection, which aligns predictive observation and action representations by mapping both modalities into a shared discrete latent space via a unified codebook, making predictive observation...

Yi-Jie Zhu, Rui Shao, Jie He et al. · 0 citations

Jul 2026

AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning

AC-VLA is introduced, a plug-and-play Action Compositional learning framework comprising two architecture-agnostic components that achieves a ~28% absolute improvement on compositional OOD tasks while maintaining near-perfect in-distribution performance.

Xiaojiang Peng, Kai Peng, Jie Lu et al. · arXiv.org · 2 citations