CoExVQA uses a chain-of-explanation to ground DocVQA answers in localized document regions, achieving state-of-the-art explainable performance with a 12% ANLS gain on PFL-DocVQA over prior baselines.
Pix2struct: Screenshot parsing as pretraining for visual language understanding
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MMTR-Bench shows that current MLLMs face significant difficulty reconstructing masked text from visual context, especially at sentence and paragraph lengths.
citing papers explorer
-
Towards Self-Explainable Document Visual Question Answering with Chain-of-Explanation Predictions
CoExVQA uses a chain-of-explanation to ground DocVQA answers in localized document regions, achieving state-of-the-art explainable performance with a 12% ANLS gain on PFL-DocVQA over prior baselines.
-
Can MLLMs "Read" What is Missing?
MMTR-Bench shows that current MLLMs face significant difficulty reconstructing masked text from visual context, especially at sentence and paragraph lengths.