Poster "transformer representations" Papers
2 papers found
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Xiaojun Jia, Sensen Gao, Simeng Qin et al.
NeurIPS 2025posterarXiv:2505.21494
12
citations
Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers
Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai et al.
ICML 2024poster