← Search

Dong Shen

2 accepted papers

2025

Libra-Merging: Importance-redundancy and Pruning-merging Trade-off for Acceleration Plug-in in Large Vision-Language Model

CVPR 2025poster

Large Vision-Language Models (LVLMs) have achieved significant progress in recent years. However, the expensive inference cost limits the realistic deployment of LVLMs. Some works find that visual tokens are redundant and compress tokens to reduce the inference cost. These works identify important n…

2025

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model

ICLR 2025poster

The Mixture-of-Experts (MoE) has gained increasing attention in studying Large Vision-Language Models (LVLMs). It uses a sparse model to replace the dense model, achieving comparable performance while activating fewer parameters during inference, thus significantly reducing the inference cost. Exist…