PDCR improves vision-language reasoning by computing separate normalized confidence advantages for perception steps and reasoning steps after unsupervised decomposition.
Calibrated self-rewarding vision language models.Advances in Neural Information Processing Systems, 37:51503–51531, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
PDCR improves vision-language reasoning by computing separate normalized confidence advantages for perception steps and reasoning steps after unsupervised decomposition.