42 citations · 89 across the 6 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.CL2019★ 4 cited
Improving BERT Fine-tuning with Embedding Normalization
Wenxuan Zhou, Junyi Du, Xiang Ren
Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g.…
cs.RO2019★ 42 cited
Environment Probing Interaction Policies
Wenxuan Zhou, Lerrel Pinto, Abhinav Gupta
A key challenge in reinforcement learning (RL) is environment generalization: a policy trained to solve a task in one environment often fails to solve the same task in a slightly d…