BIMA applies a normalizing-flow-based bijective metric to instruction fine-tuning and reports reduced object hallucination on POPE and CHAIR benchmarks, though key assumptions are unsupported.
The claude 3 model family: Opus, sonnet, haiku
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
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models
BIMA applies a normalizing-flow-based bijective metric to instruction fine-tuning and reports reduced object hallucination on POPE and CHAIR benchmarks, though key assumptions are unsupported.