Listener-augmented GRPO uses an independent frozen VLM to provide dense confidence scores on reasoning traces, yielding 67.4% accuracy on ImageReward, up to +6% OOD gains on 1.2M-vote human data, and fewer reasoning contradictions.
OpenAI o1: Learning to reason with reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Listener-Rewarded Thinking in VLMs for Image Preferences
Listener-augmented GRPO uses an independent frozen VLM to provide dense confidence scores on reasoning traces, yielding 67.4% accuracy on ImageReward, up to +6% OOD gains on 1.2M-vote human data, and fewer reasoning contradictions.