PubTabNet
PulseAugur coverage of PubTabNet — every cluster mentioning PubTabNet across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New DELTA and TARQA methods enhance LLM table understanding
Researchers have developed a new approach to table understanding in documents, moving away from image-based vision-language models towards structured textual representations. This method, called DELTA, separates physica…
-
New Geometry-Aware Loss Boosts Table Structure Recognition Accuracy
Researchers have developed a new loss function called Geometry-Aware Pointer (GAP) Loss to improve table structure recognition (TSR) in computer vision. This novel approach addresses a common failure mode where errors o…
-
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…