An inference-time visual perturbation, optimized with zeroth-order gradients and CLIP text similarity, modestly reduces object hallucination across 8 LVMs on POPE, BEAF, and CHAIR.
Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
An inference-time visual perturbation, optimized with zeroth-order gradients and CLIP text similarity, modestly reduces object hallucination across 8 LVMs on POPE, BEAF, and CHAIR.