← Search

Dongdong Liu

2 accepted papers

2025

Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout Information

ICLR 2025poster

Recent advancements in document understanding have been dominated by leveraging large language models (LLMs) and multimodal large models. However, enabling LLMs to comprehend complex document layouts and structural information often necessitates intricate network modifications or costly pre-training…

2023

Spatially Covariant Lesion Segmentation

IJCAI 2023poster

Compared to natural images, medical images usually show stronger visual patterns and therefore this adds flexibility and elasticity to resource-limited clinical applications by injecting proper priors into neural networks. In this paper, we propose spatially covariant pixel-aligned classifier (SCP)…

Cited by 9SourcePDFScholar