Inspire Institute

most citedMultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents

1 citations

researchers with a paper here

A. Descamps-Mandine1 · h 2
Andr'e F. V. Matias1 · h 1
Brigitte Leridon1 · h 1
Chanjun Park1 · h 14
C. Josse1 · h 2
Fabio Finocchi1 · h 4
G. Benas1 · h 0
G. Rousse1 · h 57
Heu-Jeoung Lim1 · h 12
H. R. Vutukuri1 · h 15
Jeongbae Park1 · h 3
Joong Shin1 · h 2

collaborating institutions

Chan Heart Rhythm InstituteUS1 paper
FZU ‒ Institute of Physics of the Academy of Sciences of the Czech RepublicCZ1 paper
InsperBR1 paper
Institut de Chimie Moléculaire et des Matériaux d'OrsayFR1 paper
Institut de minéralogie, de physique des matériaux et de cosmochimieFR1 paper
Institute for Magnetospheric PhysicsUS1 paper
Institut National de Santé PubliqueCI1 paper
International Council on Mining and MetalsGB1 paper
Korea UniversityKR1 paper
Laboratoire de Physique et d’Étude des MatériauxFR1 paper
Matériaux Ingénierie et ScienceFR1 paper
Soongsil UniversityKR1 paper

Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026★ 1 cited

MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents

Joongmin Shin, Chanjun Park, Jeongbae Park +2

RAG-based QA has emerged as a powerful method for processing long industrial documents. However, conventional text chunking approaches often neglect complex and long industrial doc…