VisualCloze is a universal image generation framework based on contextual learning, supporting multiple domain-specific tasks and generalizing to unseen tasks through contextual learning.

Computer VisionDiffusers

Vintix is a multi-task action model achieved through contextual reinforcement learning, demonstrating outstanding performance across multiple benchmarks.

PLLuM is a large language model family specifically designed for Polish and other Slavic/Baltic languages, while incorporating English data for broader generalization. It is built on a high-quality text corpus and optimized through instruction tuning, preference learning, and advanced alignment techniques to generate contextually coherent text and assist with various tasks.

Natural Language ProcessingTransformersOther

PSPNet is a deep learning model for semantic segmentation that uses pyramid pooling modules to capture multi-scale contextual information

Computer VisionSafetensors

A BERT-fine-tuned specialized sentence transformer model for the labor market, capturing labor market structures through contextual learning and relation learning

Natural Language ProcessingTransformers

KRISSBERT is a knowledge-enhanced self-supervised learning model for biomedical entity linking. It trains contextual encoders using unannotated text and domain knowledge to effectively address the diversity and ambiguity of entity names.

Natural Language ProcessingTransformersEnglish