← Search

Hufei Li

2 accepted papers

2026

Rosetta Stone For Unified MLLMs: A Unified Tokenizer to Decipher Understanding and Generation

CVPR 2026

Major state-of-the-art unified tokenizers predominantly adopt pixel reconstruction and feature alignment as pretext tasks, they leave key domains largely unexplored such as architecture, supervised objectives and tasks interaction, potentially resulting in limited performance. We systematically inve

Cited by 0SourceScholar
2024

Boosting Pruned Networks with Linear Over-Parameterization

ICASSP 2024accepted

Structured pruning is a popular technique for reducing the computational cost and memory footprint of neural networks by removing channels. It often leads to a decrease in network accuracy, which can be restored through fine-tuning. However, as the pruning ratio increases, it becomes progressively m…

Cited by 0SourceScholar