Author

Richang Hong

h-index 4 View on Semantic Scholar

We have 1 of 14 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Visual Token Compression Enhances Robustness of MLLMs

This paper shows for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), mitigating vulnerabilities such as jailbreak attacks and hallucinations, and maintains strong results on general datasets like MME.

Shishen Gu, Jie-Quan Cui, Wen-Bo Hu et al. · arXiv.org · 2 citations