Nullu projects a vision-language model's weights into the null space of a subspace learned from truthful versus hallucinated captions, reducing object hallucinations without extra inference cost.
Dress: Instructing large vision-language models to align and interact with humans via natural lan- guage feedback
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
Nullu projects a vision-language model's weights into the null space of a subspace learned from truthful versus hallucinated captions, reducing object hallucinations without extra inference cost.