ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2412.07775
267
6
v1v2v3v4v5 (latest)

Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets

10 December 2024
Zhen Liu
Tim Z. Xiao
Weiyang Liu
Yoshua Bengio
Dinghuai Zhang
ArXiv (abs)PDFHTML
Main:10 Pages
31 Figures
Bibliography:6 Pages
1 Tables
Appendix:21 Pages
Abstract

While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetune pretrained diffusion models on some reward functions that are either designed by experts or learned from small-scale datasets. Existing methods for finetuning diffusion models typically suffer from lack of diversity in generated samples, lack of prior preservation, and/or slow convergence in finetuning. Inspired by recent successes in generative flow networks (GFlowNets), a class of probabilistic models that sample with the unnormalized density of a reward function, we propose a novel GFlowNet method dubbed Nabla-GFlowNet (abbreviated as ∇\nabla∇-GFlowNet), the first GFlowNet method that leverages the rich signal in reward gradients, together with an objective called ∇\nabla∇-DB plus its variant residual ∇\nabla∇-DB designed for prior-preserving diffusion alignment. We show that our proposed method achieves fast yet diversity- and prior-preserving alignment of Stable Diffusion, a large-scale text-conditioned image diffusion model, on different realistic reward functions.

View on arXiv
Comments on this paper