Taiyi Su
Taiyi Su is a researcher affiliated with Midea Group, specifically associated with the Midea AI Research Center (AIRC). His published work spans computer vision topics including zero-shot action recognition, image understanding in poor visibility environments, video object segmentation, and embodied world models. He has co-authored work with colleagues at AIRC and Tongji University on Vision-Language-Action models for robotic garment manipulation tasks.
“DeMaVLA introduces a single Vision-Language-Action (VLA) model capable of folding multiple types of garments (shirts, skirts, pants, towels) from random initial states”
Source→“Taiyi Su... Jian Zhu... Yi Xu... AIRC, Midea Group, Tongji University (Author affiliations)”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.