HittER: Hierarchical Transformers for Knowledge Graph Embeddings [Code]
HittER generates embeddings for large-scale knowledge graphs and performs link prediction using a hierarchical Transformer model. It appeared in EMNLP 2021.
Protein sequence models
Codebase for generative modeling of protein sequence and structure, including code for CNNs and GNNs and custom data handling code.
CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
This repo contains the data and source code for baseline models in the NeurIPS 2021 benchmark paper for Constrained Language Understanding Evaluation Standard (CLUES) under MIT License.
Fourier Feature Networks and Neural Volume Rendering
Fourier Feature Networks are an exciting new development in Computer Vision, and their use for modeling radiance fields has produced a range of impressive results at the meeting point of Computer Vision and Computer Graphics.…