Context-to-Cue Direct Preference Optimization (CcDPO) reduces multi-image hallucinations in 7B multimodal LLMs by training on perturbed full-sequence captions and region-focused visual prompts, improving average multi-image benchmark scores by about 4.6 points on LLaVA-OV.
Vipergpt: Visual inference via python execution for reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs
Context-to-Cue Direct Preference Optimization (CcDPO) reduces multi-image hallucinations in 7B multimodal LLMs by training on perturbed full-sequence captions and region-focused visual prompts, improving average multi-image benchmark scores by about 4.6 points on LLaVA-OV.