Rongrong Ji

Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs

Mingbao Lin, Yu-xin Zhang, Lirui Zhao, 2023, ArXiv.

I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization

Mingbao Lin, Mengzhao Chen, Yunshan Zhong, 2023, ArXiv.

Boosting the Cross-Architecture Generalization of Dataset Distillation through an Empirical Study

Mingbao Lin, Yu-xin Zhang, Fei Chao, 2023, ArXiv.

Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs

Mingbao Lin, Yu-xin Zhang, Lirui Zhao, 2023, ICLR.