6 papers
DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections
Jiwon Park, Seohyun Pyeon, Jinwoo Kim +4
Despite rapid progress in large language models (LLMs), current QA benchmarks still overlook the core challenge of real-world scientific information seeking: synthesizing multimoda…
ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning
Shuo Yang, Soyeon Caren Han, Yihao Ding +2
Large Language Model (LLM) agents are increasingly applied to complex, multi-step tasks that require interaction with diverse external tools across various domains. However, curren…
SynJAC: Synthetic-data-driven Joint-granular Adaptation and Calibration for Domain Specific Scanned Document Key Information Extraction
Yihao Ding, Soyeon Caren Han, Zechuan Li +1
Visually Rich Documents (VRDs), comprising elements such as charts, tables, and paragraphs, convey complex information across diverse domains. However, extracting key information f…
Dirac series of over an Archimedean field
Yihao Ding, Hongfeng Zhang
Motivated by the -cohomology and Dirac cohomology, we determine Dirac series of , and show that the spin lowest -type of any Dirac s…
Deep Learning based Visually Rich Document Content Understanding: A Survey
Yihao Ding, Soyeon Caren Han, Jean Lee +1
Visually Rich Documents (VRDs) play a vital role in domains such as academia, finance, healthcare, and marketing, as they convey information through a combination of text, layout,…
VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding
Yihao Ding, Soyeon Caren Han, Yan Li +1
Visually Rich Document Understanding (VRDU) has emerged as a critical field in document intelligence, enabling automated extraction of key information from complex documents across…