Wang, Kaishen

4 publications

ICLR 2025 DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language Models Kaishen Wang, Hengrui Gu, Meijun Gao, Kaixiong Zhou

ICML 2025 FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks Quansong He, Xiangde Min, Kaishen Wang, Tao He

IJCAI 2024 Strengthening Layer Interaction via Dynamic Layer Attention Kaishen Wang, Xun Xia, Jian Liu, Zhang Yi, Tao He

NeurIPSW 2024 Zer0-Jack: A Memory-Efficient Gradient-Based Jailbreaking Method for Black Box Multi-Modal Large Language Models Tiejin Chen, Kaishen Wang, Hua Wei