3 papers
cs.CL2026
Self-Ensembling Vision-Language Models for Chart Data Extraction
Thomas Berkane, Qianyi Wang, Maimuna S. Majumder
Charts effectively convey quantitative information, but the underlying data are often locked in image form, hindering reuse and analysis. Manually digitizing charts is time-consumi…
cs.CL2026
EpiCurveBench: Evaluating VLMs on Epidemic Curve Digitization
Thomas Berkane, Maimuna S. Majumder
Chart-to-data extraction with vision-language models (VLMs) is increasingly evaluated on benchmarks that show diminishing headroom (frontier VLMs exceed 89% on ChartQA) and with me…
cs.MA2025
The AI Committee: A Multi-Agent Framework for Automated Validation and Remediation of Web-Sourced Data
Sunith Vallabhaneni, Thomas Berkane, Maimuna Majumder
Many research areas rely on data from the web to gain insights and test their methods. However, collecting comprehensive research datasets often demands manually reviewing many web…