Filtering post-training data to visually grounded questions improves VLM video understanding performance by up to 6.2 points using 69% of the data.
Gemini-1.5-Pro achieves less than 15% accuracy in the text-only setup
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Watch Before You Answer: Learning from Visually Grounded Post-Training
Filtering post-training data to visually grounded questions improves VLM video understanding performance by up to 6.2 points using 69% of the data.