AI.info

Xinghao Chen

Explore Xinghao Chen on AI.info.

• RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs
• VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
• PPE: Positional Preservation Embedding for Token Compression in Multimodal Large Language Models