Adversarial Flow Models

2025-11-27

AI Summary

This work addresses the inherent trade-offs among generation efficiency, training stability, and mapping interpretability in generative modeling by unifying adversarial generative networks (GANs) and normalizing flows. We propose the Adversarial Flow Model (AFM), which directly learns a deterministic optimal transport map from latent noise space to data space—eliminating stochasticity and iterative refinement, and enabling one-step (1-NFE) end-to-end generation. AFM incorporates a deep repeated architecture and an adversarial training objective to ensure convergence and gradient stability in deep networks. On ImageNet-256, the 1-NFE variant achieves a Fréchet Inception Distance (FID) of 2.38; deeper variants with 56 and 112 layers attain FIDs of 2.08 and 1.94, respectively—surpassing Consistency Models XL/2 and leading multi-step methods. To our knowledge, AFM is the first framework to achieve state-of-the-art performance in single-step generative modeling.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

We present adversarial flow models, a class of generative models that unifies adversarial models and flow models. Our method supports native one-step or multi-step generation and is trained using the adversarial objective. Unlike traditional GANs, where the generator learns an arbitrary transport plan between the noise and the data distributions, our generator learns a deterministic noise-to-data mapping, which is the same optimal transport as in flow-matching models. This significantly stabilizes adversarial training. Also, unlike consistency-based methods, our model directly learns one-step or few-step generation without needing to learn the intermediate timesteps of the probability flow for propagation. This saves model capacity, reduces training iterations, and avoids error accumulation. Under the same 1NFE setting on ImageNet-256px, our B/2 model approaches the performance of consistency-based XL/2 models, while our XL/2 model creates a new best FID of 2.38. We additionally show the possibility of end-to-end training of 56-layer and 112-layer models through depth repetition without any intermediate supervision, and achieve FIDs of 2.08 and 1.94 using a single forward pass, surpassing their 2NFE and 4NFE counterparts.

Problem

• Unifies adversarial and flow models for stable generation
• Enables one-step or few-step generation without intermediate timesteps
• Achieves high performance with reduced training and model capacity

Innovation

• Unifies adversarial and flow models for generative tasks
• Learns deterministic mapping to stabilize adversarial training
• Enables one-step generation without intermediate timestep learning