pith. sign in

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 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Listener-Rewarded Thinking in VLMs for Image Preferences

cs.CV · 2025-06-28 · unverdicted · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Listener-Rewarded Thinking in VLMs for Image Preferences cs.CV · 2025-06-28 · unverdicted · none · ref 20

    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.