Pengcheng He

Greedy-Step Off-Policy Reinforcement Learning

Yuhui Wang, Qingyuan Wu, Pengcheng He, 2021 .

ARCH: Efficient Adversarial Regularized Training with Caching pdf

Jianfeng Gao, Simiao Zuo, Pengcheng He, 2021, EMNLP.

DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing pdf

Jianfeng Gao, Pengcheng He, Weizhu Chen, 2021, ArXiv.

Irregular Flight Timetable Recovery Under COVID-19: An Approach Based on Genetic Algorithm

Tianwei Zhou, Ben Niu, Pengcheng He, 2021, DMBD.

Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering

Yelong Shen, Jiawei Han, Jianfeng Gao, 2021, 2101.00294.

Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach

Jianfeng Gao, Simiao Zuo, Pengcheng He, 2021, EMNLP.

Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention pdf

Hao Cheng, Shuohang Wang, Michael Zeng, 2021, ArXiv.