FAV aligns few-step generative models by amortizing SVGD updates from reward-tilted sampling into generator parameters via fixed-point regression, requiring only sample access, and shows outperformance on robotics tasks plus scaling on image generators.
org/abs/2404.03673
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.
citing papers explorer
-
Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference
FAV aligns few-step generative models by amortizing SVGD updates from reward-tilted sampling into generator parameters via fixed-point regression, requiring only sample access, and shows outperformance on robotics tasks plus scaling on image generators.
-
Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
A reinforcement-learning agent that picks high-error trajectory segments during consistency distillation improves few-step text-to-image generation on FLUX and SDXL.