Handling extremely large documents for question answering is challenging: chunk-based embedding methods often lose track of important global context, while full-context transformers can be ...

Abstract: Segmenting unknown domains using a model trained in the source domain still faces challenges. Although some approaches tried to resolve the problem through various data generation and ...

Abstract: Despite the unprecedented success of text-to-image diffusion models, controlling the number of depicted objects using text is surprisingly hard. This is important for various applications ...