The paper introduces continuous adversarial flow models, a continuous-time flow framework trained with an adversarial objective that replaces the fixed mean-squared-error criterion of flow matching. By incorporating a learned discriminator, the method guides training toward a different generalized distribution, yielding samples more closely aligned with the target data distribution. Applied as a post‑training step, it markedly improves ImageNet 256px generation metrics—reducing 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—and also enhances guided generation and text‑to‑image benchmarks.
Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flow matching interpolates noise toward a fixed clean-image endpoint, leaving the spectral evolution to be learned implicitly.
The paper introduces Flow-Based Distribution Matching (FBDM), a non‑adversarial method that learns self‑supervised representations by aligning images to explicit geometric references through spherical conditional velocity regression. By using an ETF‑inspired reference, FBDM allows more reference components than the flow dimension while maintaining geometric separation, and it incorporates an alignment loss to bring augmented views closer together. Experiments on datasets from CIFAR to ImageNet show that FBDM performs nearly as well as adversarial distribution‑matching methods, achieves a 1.48‑ to 1.83‑fold speedup, and offers a theoretical bound on downstream misclassification rates.
Pixel diffusion models generate RGB images directly but tend to miss fine‑scale natural‑image statistics. The authors introduce an adversarial post‑training step that adds an adversarial loss to the model’s output at non‑high‑noise timesteps, without changing the architecture or sampling procedure. This approach improves distribution fidelity, coverage, prompt alignment, and perceptual quality across two pixel backbones, and restores missing high‑frequency spectral power while avoiding memorization or mode dropping.
The paper introduces Flow-Based Distribution Matching (FBDM), a non‑adversarial framework that learns self‑supervised representations using explicit geometric references and spherical conditional velocity regression. FBDM assigns augmented image views to shared target references while limiting reference usage, and employs an alignment loss to bring view representations closer. Experiments on datasets from CIFAR to ImageNet demonstrate that FBDM performs nearly as well as adversarial DM, outperforms existing SSL methods, and achieves a 1.48‑ to 1.83‑fold speedup with minimal GPU memory increase, while a theoretical analysis bounds downstream misclassification rates in terms of the pretraining loss.
arXiv:2608. 14038v1 Announce Type: new Abstract: Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment.
arXiv:2505. 04486v4 Announce Type: replace-cross Abstract: Flow matching models have shown great potential in image generation tasks among probabilistic generative models.
arXiv:2609.35763v3 Announce Type: replace Abstract: Distributional training provides collective supervision for one-step visual generation by matching real and generated features in frozen representa...
arXiv:2509. 24935v3 Announce Type: replace-cross Abstract: Scalability has driven recent advances in generative modeling, yet its principles remain underexplored for adversarial learning.
The paper introduces Priming Models, a two‑stage framework for training one‑step generative models. First, the model is trained on a reconstruction objective such as pixel‑space denoising at a fixed noise level, then it undergoes feature‑space distributional post‑training. This simple reconstruction stage alone is shown to eliminate the difficulty of distributional training, leading to significant improvements in training compute versus generation quality across tasks like class‑conditional image generation, text‑to‑image generation, and world modeling, with a state‑of‑the‑art FID of 1.19 on ImageNet 256×256 using about one‑tenth the compute of previous methods.
The paper introduces SCION, a single-model framework that jointly learns generative and self‑supervised representation tasks without relying on labels or pretrained encoders. SCION uses a pixel‑space encoder conditioned on a flow timestep and a shared embedding, training contrastive and flow‑matching objectives simultaneously with gradient‑norm balancing and stop‑gradient techniques. On ImageNet 256×256, SCION achieves state‑of‑the‑art FID scores (8.92 with JiT‑B and 5.89/3.47 with JiT‑L) surpassing prior class‑unconditional and pretrained‑conditioned methods.
The paper introduces Function Projection for Flow Matching (FP‑FM), an algorithm that conditions generative models directly on samples from a target distribution. FP‑FM learns basis functions spanning velocity fields for training distributions and adapts to new distributions via a simple least‑squares projection, enabling efficient sample generation without additional training at inference time. Variants of the method trade expressivity for computational cost by enriching coefficient calculations, and the approach shows markedly better precision and recall than baselines, especially on unseen distributions.
Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching. Along the way, the underlying techniques have become more complicated and various beliefs about what drives strong empirical performance have taken hold.