DRL trains a discriminator on data versus base-model samples in pretrained representation space and uses its logit as reward in KL-regularized RL, cutting guidance-free FID from 9.38 to 2.62 on SiT and similar gains on other backbones.
Calibrating Generative Models to Distributional Constraints
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Generative models frequently suffer miscalibration, wherein statistics of the sampling distribution, such as the fraction of generations in a given class, deviate from desired values. We frame calibration as a constrained optimization problem and seek the closest model in Kullback-Leibler divergence satisfying a calibration constraint. To address the intractability of imposing these constraints exactly, we introduce two surrogate objectives for fine-tuning: (1) the relax loss, which replaces the constraint with a miscalibration penalty, and (2) the reward loss, which converts calibration into a reward fine-tuning problem. We demonstrate that these approaches substantially reduce calibration error across hundreds of simultaneous constraints and models with up to nine billion parameters, spanning applications in protein design, image generation, and language modeling.
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Exploration of pre-generation prediction of human preference metrics (HPM) from noise seeds in diffusion models to improve output quality with negligible added cost.
citing papers explorer
-
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
DRL trains a discriminator on data versus base-model samples in pretrained representation space and uses its logit as reward in KL-regularized RL, cutting guidance-free FID from 9.38 to 2.62 on SiT and similar gains on other backbones.
-
Can We Predict The Human Preference For Text-to-Image Content Prior To Generation And Is It Even Useful To Do So?
Exploration of pre-generation prediction of human preference metrics (HPM) from noise seeds in diffusion models to improve output quality with negligible added cost.