pith. sign in

Confidence-aware reward optimiza- tion for fine-tuning text-to-image models

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 2

years

2026 1 2025 1

representative citing papers

Bias at the End of the Score

cs.CV · 2026-04-14 · unverdicted · novelty 6.0

Reward models used as quality scorers in text-to-image generation encode demographic biases that cause reward-guided training to sexualize female subjects, reinforce stereotypes, and reduce diversity.

citing papers explorer

Showing 2 of 2 citing papers.

  • Bias at the End of the Score cs.CV · 2026-04-14 · unverdicted · none · ref 31

    Reward models used as quality scorers in text-to-image generation encode demographic biases that cause reward-guided training to sexualize female subjects, reinforce stereotypes, and reduce diversity.

  • Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps cs.CV · 2025-01-16 · conditional · none · ref 37

    Diffusion models improve generation quality via inference-time search over noise candidates guided by verifiers and algorithms, yielding gains beyond denoising step scaling on class- and text-conditioned benchmarks.