Gradients with respect to semantics preserving embeddings tell the uncertainty of large language models
ICML
Mingda, Li and Rundong, Lv and Xinyu, Li and Weinan, Zhang and Ting, Liu
ICML
Gradients with respect to semantics preserving embeddings tell the uncertainty of large language models
ICML
Mingda, Li and Rundong, Lv and Xinyu, Li and Weinan, Zhang and Ting, Liu
MRPO: Magnitude-Regularized Policy Optimization via L1 Constraints
ICML
Wei, Han and Yuanxing, Liu and Mingda, Li and Ruiyu, Xiao and Weinan, Zhang and Ting, Liu
MRPO: Magnitude-Regularized Policy Optimization via L1 Constraints
ICML
Wei, Han and Yuanxing, Liu and Mingda, Li and Ruiyu, Xiao and Weinan, Zhang and Ting, Liu