PaliGemma 2
Google DeepMind — Gemma
rich detail 24 method fields published
Evaluation
extraction of table text content, bounding box coordinates, and table structure in HTML format from document images; fine-tuned on PubTabNet (516k images) and FinTabNet (113k financial tables); assessed with Tree Edit Distance Similarity (TEDS) and Grid Table Similarity (GriTS)
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.
rich detail 24 method fields published