2 papers
cs.CV2026
SM4RT: Learning Structured Motion Geometry for 4D Reconstruction
Shing Ho J. Lin, Wenzhao Zheng, Dong Zhuo +3
Geometry Foundation Models (GFMs) have substantially advanced monocular 3D reconstruction, yet extending this capability to 4D dynamic understanding remains a fundamental challenge…
cs.LG2025
Lipschitz Constant Meets Condition Number: Learning Robust and Compact Deep Neural Networks
Yangqi Feng, Shing-Ho J. Lin, Baoyuan Gao +1
Recent research has revealed that high compression of Deep Neural Networks (DNNs), e.g., massive pruning of the weight matrix of a DNN, leads to a severe drop in accuracy and susce…