# 连续对抗流模型

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-04-13 08:00
- AIHOT 链接：https://aihot.virxact.com/items/cmnygovrm003gsl13uw4ae9xc
- 原文链接：https://arxiv.org/abs/2604.11521

## AI 摘要

研究团队提出连续对抗流模型，通过引入学习判别器替代固定的均方误差准则，对现有 flow matching 模型进行后训练优化。在 ImageNet 256px 生成任务中，该方法将 latent-space SiT 的无引导 FID 从 8.26 降至 3.63，pixel-space JiT 从 7.17 降至 3.57；有引导生成下 SiT 的 FID 从 2.06 优化至 1.53。该方法在文生图任务的 GenEval 和 DPG 基准测试上也取得显著性能提升。

## 正文

We propose continuous adversarial flow models, a type of continuous-time flow model trained with an adversarial objective. Unlike flow matching, which uses a fixed mean-squared-error criterion, our approach introduces a learned discriminator to guide training. This change in objective induces a different generalized distribution, which empirically produces samples that are better aligned with the target data distribution. Our method is primarily proposed for post-training existing flow-matching models, although it can also train models from scratch. On the ImageNet 256px generation task, our post-training substantially improves the guidance-free FID of latent-space SiT from 8.26 to 3.63 and of pixel-space JiT from 7.17 to 3.57. It also improves guided generation, reducing FID from 2.06 to 1.53 for SiT and from 1.86 to 1.80 for JiT. We further evaluate our approach on text-to-image generation, where it achieves improved results on both the GenEval and DPG benchmarks.