As another crazy year on planet earth draws to a close, it's time to reflect on some of the standout moments of 2025. And so, without further ado and in no particular order, we present SARAH VINE'S ...
TRivia is a novel self-supervised fine-tuning framework of vision-language models for table recognition. This repository contains the TRivia-3B, an advanced table recognition VLMs trained from Qwen2.5 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback