YUKINO reports state-of-the-art scores on SugarCREPE and Winoground by injecting image-derived pseudo-tokens into captions and comparing yes versus no prompts, a protocol that likely inflates the results.
When and why vision-language models behave like bags-of-words, and what to do about it?,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
REJECT 1roles
method 1polarities
support 1representative citing papers
citing papers explorer
-
A New Method to Capturing Compositional Knowledge in Linguistic Space
YUKINO reports state-of-the-art scores on SugarCREPE and Winoground by injecting image-derived pseudo-tokens into captions and comparing yes versus no prompts, a protocol that likely inflates the results.