MuDoC combines document layout analysis, DPR and CLIP retrieval, and GPT-4o to answer PDF questions with interleaved source text and figures, plus clickable provenance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MuDoC: An Interactive Multimodal Document-grounded Conversational AI System
MuDoC combines document layout analysis, DPR and CLIP retrieval, and GPT-4o to answer PDF questions with interleaved source text and figures, plus clickable provenance.