Abstract: The fast expansion of deep learning models has led to an increasing need for well-annotated datasets, while traditional manual annotation cannot meet this requirement. Current research on ...

Add short notes to any text without creating a full page. Select a word or sentence, attach an annotation, and reveal it with a click or hover. Perfect for TTRPG notes, study material, manuscripts, or ...

InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders InterPLM is a toolkit for extracting, analyzing, and visualizing interpretable features from protein ...

Abstract: Large-scale pre-trained vision-language models (e.g., CLIP) have shown incredible generalization performance in downstream tasks such as video-text retrieval (VTR). Traditional approaches ...