Poster "transformer representations" Papers
3 papers found
Conference
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
Xiaojun Jia, Sensen Gao, Simeng Qin et al.
NEURIPS 2025arXiv:2505.21494
18
citations
Constrained Belief Updates Explain Geometric Structures in Transformer Representations
Mateusz Piotrowski, Paul Riechers, Daniel Filan et al.
ICML 2025arXiv:2502.01954
6
citations
Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers
Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai et al.
ICML 2024arXiv:2310.02905
26
citations