关注
Mingjian Jiang
Mingjian Jiang
在 stanford.edu 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Calibrating language models via augmented prompt ensembles
M Jiang, Y Ruan, S Huang, S Liao, S Pitis, RB Grosse, J Ba
ICML 2023 Workshop on Deployable Generative AI, 2023
202023
Sentence embedding encoders are easy to steal but hard to defend
A Dziedzic, F Boenisch, M Jiang, H Duan, N Papernot
CISPA; ICLR 2023 Workshop on Trustworthy ML, 2023
72023
Graph-based Uncertainty Metrics for Long-form Language Model Outputs
M Jiang, Y Ruan, P Sattigeri, S Roukos, T Hashimoto
NeurIPS 2024 (Spotlight), 2024
12024
-PO: Generalizing Preference Optimization with -divergence Minimization
J Han, M Jiang, Y Song, J Leskovec, S Ermon, M Xu
arXiv preprint arXiv:2410.21662, 2024
2024
Calibrating Language Models via Augmented Prompt Ensembles. 2023
M Jiang, Y Ruan, S Huang, S Liao, S Pitis, RB Grosse, J Ba
2023
Stealing and Defending Transformer-based Encoders
A Dziedzic, F Boenisch, M Jiang, H Duan, N Papernot
系统目前无法执行此操作,请稍后再试。
文章 1–6