# Multi-task Learning Optimization

RoFormerV2 is an enhanced Transformer model based on rotary position embedding, developed by Zhuiyi Technology, supporting Chinese text processing tasks.

ERNIE 2.0 is a continuous pre-training framework proposed by Baidu, which optimizes pre-training tasks through multi-task learning and surpasses BERT and XLNet in multiple Chinese and English tasks.

ERNIE 2.0 is a continuous pre-training framework proposed by Baidu in 2019, which gradually constructs and optimizes pre-training tasks through continuous multi-task learning. It outperforms BERT and XLNet in multiple tasks.