Hello there, I’m Ziyu

Illustration of combining vision and language modalities šŸ‘ØšŸ»ā€šŸ’» Currently I’m a 4th year Ph.D student at University of South Carolina under Prof. Song Wang.

šŸ”¬ My research centers on enhancing the capabilities of foundation models for both 2D and 3D vision tasks, with a focus on bridging the gap between theoretical advances and practical applications.

šŸ“š My current work explores innovative approaches in multi-modal pretraining and parameter-efficient tuning techniques, developing methods that have successfully transitioned from research prototypes to production environments, as well as generative models & 3D reconstruction.

šŸ“½ļø I am also interested in assisting others on their path in the world of Deep/Machine Learning and academia.