1. Diversity-Guided MLP Reduction for Efficient Large Vision Transformers (2025)
2. SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models (2025)
Background
Research Interest: Large Vision Model, Multimodal Learning, Large Language Model, Unsupervised Learning, Efficient Inference, Zero/Few-Shot Learning. Position: Associate Professor at School of Computer Science and Engineering, Central South University.
Miscellany
Homepage includes links to Google Scholar, Semantic Scholar, ORCiD, DBLP, and Github.