GeoCode maps 3D shapes to a human-interpretable parameter space, allowing to intuitively edit the recovered 3D shapes from a point cloud or sketch input.

Official code for the paper "PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains".

[EMNLP 2020] Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)

A span-based joint named entity recognition (NER) and relation extraction model.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.