Le Yu, Kaishen Wang, Jianlong Xiong, Yue Cao, and Tao He. (2025). "HalluRNN: Mitigating Hallucinations via Recurrent Cross-Layer Reasoning in Large Vision-Language Models." arXiv preprint arXiv:2506.17587, 2025.
Quansong He, Xiangde Min, Kaishen Wang, Tao He. (2025). "FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks." ICML, 2025.
Kaishen Wang, Hengrui Gu, Meijun Gao, Kaixiong Zhou. (2025). "DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language Models." Proceedings of the Thirteenth International Conference on Learning Representations (ICLR), 2025.
Tiejin Chen, Kaishen Wang, and Hua Wei. (2024). "Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language Models." arXiv preprint arXiv:2411.07559, 2024.
Kaishen Wang, Xun Xia, Jian Liu, Zhang Yi, and Tao He. (2024). "Strengthening Layer Interaction via Dynamic Layer Attention." Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI).