FinTabNet
PulseAugur coverage of FinTabNet — every cluster mentioning FinTabNet across labs, papers, and developer communities, ranked by signal.
-
LLM judges unreliable for table recognition regeneration, study finds
A new research paper challenges the reliability of using Large Language Models (LLMs) as judges for evaluating and selecting outputs in closed-loop regeneration tasks, particularly in table recognition. The study found …
-
New active learning method enhances table extraction pipelines
Researchers have adapted an active learning strategy called Uncertainty Herding (UHerding) for cascaded object detection pipelines used in table extraction. This adaptation aims to reduce the costly annotation burden, p…
-
FastTab model uses recursive module and 1D Transformers for table recognition
Researchers have developed FastTab, a novel model for table structure recognition that utilizes a recursive module and 1D Transformers. This approach bypasses traditional autoregressive decoding by focusing on grid-cent…