pith. sign in

Title resolution pending

Percentage of generated images from our fine-tuned model that are better than (win), tied with, or worse than (lose) the compared to original stable diffusion model with rejection sampling in terms of image-text alignment, fidelity · 2022

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.LG 1

years

2023 1

verdicts

UNVERDICTED 1

representative citing papers

Aligning Text-to-Image Models using Human Feedback

cs.LG · 2023-02-23 · unverdicted · novelty 6.0

A three-stage fine-tuning process uses human ratings to train a reward model and then improves text-to-image alignment by maximizing reward-weighted likelihood.

citing papers explorer

Showing 1 of 1 citing paper.

  • Aligning Text-to-Image Models using Human Feedback cs.LG · 2023-02-23 · unverdicted · none · ref 25

    A three-stage fine-tuning process uses human ratings to train a reward model and then improves text-to-image alignment by maximizing reward-weighted likelihood.