Huaibo Huang is the corresponding author.

Accurate identification and organizing of textual content is crucial for the automation of document processing in the field of form understanding. Existing datasets,

Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks.

The code is available in https://github.com/cathyhxh/DIFFER.

Disentangled representation learning (DRL) aims to identify and decompose underlying factors behind observations, thus facilitating data perception and generation.

CPG enables the model to fully capture the intra-category diversity by representing each category with multiple prototypes.