PulseAugur
LIVE 12:22:52
research · [2 sources] ·
0
research

PlotPick uses VLMs to extract data from scientific figures, outperforming dedicated models

A new open-source tool called PlotPick has been developed to extract structured tabular data from scientific figures using vision-language models (VLMs). This tool aims to automate the slow process of manual data digitization for systematic reviews and meta-analyses. Evaluations show that six different VLMs significantly outperform the specialized chart-to-table model DePlot on established benchmarks, particularly on chart types not included in DePlot's training data. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Automates data extraction from scientific figures, potentially accelerating research synthesis and meta-analyses.

RANK_REASON The cluster describes a new open-source tool and research paper detailing its performance on benchmarks.

Read on arXiv cs.CV →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 · Tommy Carstensen ·

    PlotPick: AI-powered batch extraction of numerical data from scientific figures

    arXiv:2605.06021v1 Announce Type: new Abstract: Systematic reviews and meta-analyses frequently require numerical data that authors report only as figures, yet manual digitisation is slow and does not scale. We present PlotPick, an open-source tool that uses vision-language model…

  2. arXiv cs.CV TIER_1 · Tommy Carstensen ·

    PlotPick: AI-powered batch extraction of numerical data from scientific figures

    Systematic reviews and meta-analyses frequently require numerical data that authors report only as figures, yet manual digitisation is slow and does not scale. We present PlotPick, an open-source tool that uses vision-language models (VLMs) to batch-extract structured tabular dat…