A multi-response discriminative reward model scores N candidates in one pass via concatenation and cross-entropy, achieving SOTA on multimodal benchmarks and improving RL policies over single-response baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
A multi-response discriminative reward model scores N candidates in one pass via concatenation and cross-entropy, achieving SOTA on multimodal benchmarks and improving RL policies over single-response baselines.