Výsledky vyhledávání - "Liu, Shuhang"

Report

See then Tell: Enhancing Key Information Extraction with Vision Grounding

Autor: Liu, Shuhang, Zhang, Zhenrong, Hu, Pengfei, Ma, Jiefeng, Du, Jun, Wang, Qing, Zhang, Jianshu, Liu, Chenyu

In the digital era, the ability to understand visually rich documents that integrate text, complex layouts, and imagery is critical. Traditional Key Information Extraction (KIE) methods primarily rely on Optical Character Recognition (OCR), which oft

Externí odkaz: http://arxiv.org/abs/2409.19573

Zobrazit plný text záznamu

Report

UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognition

Autor: Zhang, Zhenrong, Liu, Shuhang, Hu, Pengfei, Ma, Jiefeng, Du, Jun, Zhang, Jianshu, Hu, Yu

In the digital era, table structure recognition technology is a critical tool for processing and analyzing large volumes of tabular data. Previous methods primarily focus on visual aspects of table structure recovery but often fail to effectively com

Externí odkaz: http://arxiv.org/abs/2409.13148

Zobrazit plný text záznamu

Report

DocMamba: Efficient Document Pre-training with State Space Model

Autor: Hu, Pengfei, Zhang, Zhenrong, Ma, Jiefeng, Liu, Shuhang, Du, Jun, Zhang, Jianshu

In recent years, visually-rich document understanding has attracted increasing attention. Transformer-based pre-trained models have become the mainstream approach, yielding significant performance gains in this field. However, the self-attention mech

Externí odkaz: http://arxiv.org/abs/2409.11887

Zobrazit plný text záznamu

Report

Momentum Decoding: Open-ended Text Generation As Graph Exploration

Autor: Lan, Tian, Su, Yixuan, Liu, Shuhang, Huang, Heyan, Mao, Xian-Ling

Open-ended text generation with autoregressive language models (LMs) is one of the core tasks in natural language processing. However, maximization-based decoding methods (e.g., greedy/beam search) often lead to the degeneration problem, i.e., the ge

Externí odkaz: http://arxiv.org/abs/2212.02175

Zobrazit plný text záznamu