InfographicsVQA

I processed the jsonl file downloaded from DUE Benchmark using the code below.For the images, I used images provided by DocDownstream. import json from datasets import Dataset, DatasetDict from tqdm import tqdm from huggingface_hub import login; login(token="YOUR_TOKEN") data = [] jsonl_file = "document.jsonl" with ope

Papers using InfographicsVQA (4)

The Confidence Paradox: Can LLM Know When It's Wrong2025 · 2 citesFocus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding2026Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation2025Enhancing Document VQA Models Via Retrieval-augmented Generation2025