Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment
Yang Chen, Xiaowei Xu, Shuai Wang, Chenhui Zhu, Ruxue Wen, Xubin Li, Tiezheng Ge, Limin Wang
Abstract
Normalizing Flows (NFs) are a class of generative models distinguished by a mathematically invertible architecture, where the forward pass transforms data into a latent space for density estimation, and the reverse pass generates new samples from this space. This characteristic creates an intrinsic synergy between representation learning and data generation. However, the generative quality of standard NFs is limited by poor semantic representations from log-likelihood optimization. To remedy this, we propose a novel alignment strategy that creatively leverages the invertibility of NFs: instead of regularizing the forward pass, we align the intermediate features of the generative (reverse) pass with representations from a powerful vision foundation model, demonstrating superior effectiveness over naive alignment. We also introduce a novel training-free, test-time optimization algorithm for classification, which provides a more intrinsic evaluation of the NF
BibTeX
@inproceedings{aaai2026_flowingbackwards,
title = {Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment},
author = {Yang Chen and Xiaowei Xu and Shuai Wang and Chenhui Zhu and Ruxue Wen and Xubin Li and Tiezheng Ge and Limin Wang},
booktitle = {AAAI 2026},
year = {2026}
}