TABALIGN pairs a diffusion language model planner emitting binary cell masks with a trained attention verifier, raising average accuracy 15.76 points over strong baselines on eight table benchmarks while speeding execution 44.64%.
T a P as: Weakly Supervised Table Parsing via Pre-training
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Centroid averaging across table serializations reduces format-induced embedding variance in retrieval, and a covariance-regularized residual bottleneck adapter further improves robustness for dense retrievers.
TEmBed benchmark shows that the best tabular embedding model depends on the specific task and the representation level (cell, row, column, or table).
An adaptive thresholding mechanism combined with sliding-window reranking retrieves a query-dependent number of tables from large corpora, improving retrieval and downstream text-to-SQL performance on Spider, BIRD, and Spider 2.0.
citing papers explorer
-
From Table to Cell: Attention for Better Reasoning with TABALIGN
TABALIGN pairs a diffusion language model planner emitting binary cell masks with a trained attention verifier, raising average accuracy 15.76 points over strong baselines on eight table benchmarks while speeding execution 44.64%.
-
Improving Robustness of Tabular Retrieval via Representational Stability
Centroid averaging across table serializations reduces format-induced embedding variance in retrieval, and a covariance-regularized residual bottleneck adapter further improves robustness for dense retrievers.
-
Towards Universal Tabular Embeddings: A Benchmark Across Data Tasks
TEmBed benchmark shows that the best tabular embedding model depends on the specific task and the representation level (cell, row, column, or table).
-
Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method
An adaptive thresholding mechanism combined with sliding-window reranking retrieves a query-dependent number of tables from large corpora, improving retrieval and downstream text-to-SQL performance on Spider, BIRD, and Spider 2.0.