BalancedDPO applies majority-vote consensus from multiple preference scorers and dynamic reference model updates within DPO to achieve multi-metric alignment for text-to-image diffusion models, reporting improved win rates on Pick-a-Pic, PartiPrompt, and HPD datasets across SD 1.5, 2.1, and SDXL.
Beyond one-preference-fits-all alignment: Multi-objective direct prefer- ence optimization
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
-
BalancedDPO: Adaptive Multi-Metric Alignment
BalancedDPO applies majority-vote consensus from multiple preference scorers and dynamic reference model updates within DPO to achieve multi-metric alignment for text-to-image diffusion models, reporting improved win rates on Pick-a-Pic, PartiPrompt, and HPD datasets across SD 1.5, 2.1, and SDXL.