The authors introduce SatisDive, a training-free inference-time method for text-to-image diffusion models.
SatisDive method navigates the satisfaction-diversity frontier for text-to-image generation
By imposing a reward floor per image and a diversity cutoff per batch, SatisDive Pareto-dominates FK steering on two base models.
Big Tech
Kevin Zhai · Siva Rajesh Kasa · Soumya Roy · Sumit Negi · Mubarak Shah
University of Central Florida · Amazon
Research Digest··2 min read
Thread:Open-Ended RL Reward Design
The authors formulate text-to-image batch generation as satisficing: each image must meet a reward floor and the batch must meet a diversity cutoff.
Why this paper
From Amazon and University of Central Florida · Part of Open-Ended RL Reward Design, now 3 papers
In one line
Text-to-image generation can satisfy user preferences while maintaining diversity by ensuring each image meets a minimum reward threshold.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§