AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling

Xudong Xie, Hao Yan, Liang Yin, Yang Liu, Jing Ding, Minghui Liao, Yuliang Liu, Wei Chen, Xiang Bai

IJCV 2026 · Vision-language and multimodal › Visual question answering · approach: Open-domain multimodal QA · 24 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add sparse sampler (ablation)PDF-WuKong · PaperPDF English (ablation)ANLS: 11.1 -> 40.3Improved
add end-to-end joint training of sampler and MLLM (ablation)PDF-WuKong · PaperPDF English (ablation)ANLS: 40.3 -> 42.6Improved
increase training data from 100k to 1M (ablation)PDF-WuKong · PaperPDF English (ablation)ANLS: 38.7 -> 42.6Improved
increase training data from 500k to 1M (ablation)PDF-WuKong · PaperPDF English (ablation)ANLS: 41.6 -> 42.6Improved
add multi-evidence data to single-evidence data at equal scale (ablation)PDF-WuKong · PaperPDF English (ablation)ANLS: 39.2 -> 40.0Improved
increase sampled chunks from top 1 to top 5 (ablation)PDF-WuKong · PaperPDF English (ablation)ANLS: 39.20 -> 42.59Improved
increase sampled chunks from top 5 to top 20 (ablation)PDF-WuKong · PaperPDF English (ablation)ANLS: 42.59 -> 43.42No clear effect
use parsed input instead of page imagesPDF-WuKong · PaperPDF single-evidence subsetANLS: 36.6 -> 41.5Improved
use parsed interleaved text-image input instead of plain text (InternVL2)InternVL2 · PaperPDF English testGPT-Acc: 37.5 -> 54.3Improved
add text RAG (BGE-M3) to IXC2-VLIXC2-VL · PaperPDF English testGPT-Acc: 37.6 -> 48.4Improved
fine-tune BGE-M3 retriever on PaperPDFInternVL2 + BGE-M3 · PaperPDF English testANLS: 29.8 -> 36.4Improved
use PDF-WuKong instead of InternVL2 with parsed inputPDF-WuKong · PaperPDF Chinese testANLS: 28.5 -> 40.9Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy