Papers by Jifeng Song

1 papers
FigEx: Aligned Extraction of Scientific Figures and Captions (2025.findings-emnlp)

Copied to clipboard

Challenge: FigEx is a vision-language model to extract aligned pairs of subfigures and subcaptions from scientific papers.
Approach: They propose a vision-language model to extract aligned pairs of subfigures and subcaptions from scientific papers.
Outcome: The proposed model improves subfigure detection APb over Grounding DINO by 0.023 and boosts caption separation BLEU over Llama-2-13B by 0.465.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations