Xiu Su
Xiu Su is a Full Professor at Central South University, where he serves as a distinguished professor and doctoral supervisor. He holds a PhD from the University of Sydney and has been recognized as a National High-Level Young Talent and Xiaomi Young Scholar. His research spans embodied intelligence, multimodal large models, computer vision, and automated machine learning, with over 40 publications in top-tier venues including TPAMI, CVPR, NeurIPS, and ICML.
“This paper solves one of the most pressing deployment problems in physical AI: VLA models fail at exactly the wrong moments — complex, ambiguous situations — and this framework cuts those failures in half without requiring retraining or sacrificing real-time control speeds.”
Source→“The combination of Chang Xu and Shan You suggests affiliation with a major Chinese AI lab or university. Their focus on plug-and-play inference augmentation without base model modification is a pragmatic, deployment-oriented research direction.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.