2 papers
cs.AI2026
TACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification Control
Wei-Jin Huang, Yuan-Ming Li, Kun-Yu Lin +8
Recent text-to-motion models have improved motion quality and instruction following, yet many-step denoising and large model components make deployment slow and memory-intensive. W…
cond-mat.soft2026
Inverse design of a magneto-elastica for shape-morphing
JiaHao Li, Yingchao Zhang, Weicheng Huang +4
Slender magnetic elements provide a versatile platform for programmable shape-morphing under remote magnetic actuation. However, a general and physically interpretable framework fo…