Shuailong Wang — accepted AI-conference papers

2026

Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs

Shuailong Wang, Xinyu Lyu, Shengming Yuan, Lianli Gao, Jingkuan Song, Heng Tao Shen

ICML 2026poster

Token-Pruning accelerates Vision-Language Models by removing redundant visual tokens, yet its safety implications remain underexplored. In this work, we present the first comprehensive safety evaluation of Token-Pruning mechanism and find that: Most pruning strategies significantly degrade safety as…

Cited by 0 Source ↗Scholar ↗

2025

FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models

Shengming Yuan, Xinyu Lyu, Shuailong Wang, Beitao Chen, Jingkuan Song, Lianli Gao

NeurIPS 2025poster

Multimodal large language models (MLLMs) face an inherent trade-off between faithfulness and creativity, as different tasks require varying degrees of associative reasoning. However, existing methods lack the flexibility to modulate this reasoning strength, limiting MLLMs' adaptability across factua…

Cited by 0 Source ↗code ↗Scholar ↗