Yating Wu @yatingwu.bsky.social · 07/05/2026[3/4] Do VLMs actually ground in the figure? Fine-tuning Qwen3.5-9B on MQUD makes generated questions more grounded in the figure and more specific to the paper’s scientific content. 100
Yating Wu @yatingwu.bsky.social · 07/05/2026[2/4] These questions often require reasoning across the figure and paper text: Why does this curve shift? What comparison is scientifically meaningful? What claim is this figure supporting? 🔍 100
Yating Wu @yatingwu.bsky.social · 07/05/2026What does a scientific figure make you wonder? 📊 We introduce MQUD: multimodal Questions Under Discussion for scientific figures. With 1,250 author-annotated questions over 245 figures from 56 papers, MQUD asks what scientific question a figure raises in context. 141