arXiv AI
DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
2d ago
Enhancing Autoregressive Video Generation via Representation Adversarial Distillation
arXiv:2609.40037v1 Announce Type: new Abstract: Few-step autoregressive video generation enables efficient streaming synthesis, but errors introduced in early temporal blocks are reused as context an...
arXiv Machine Learning
Jul 23
SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
arXiv:2605. 30116v2 Announce Type: replace-cross Abstract: Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models.
arXiv Computer Vision
3d ago
DMA$^2$: Pixel-space Distribution Matching with Adversarial and Anchor Losses
arXiv:2609.38156v1 Announce Type: new Abstract: Distribution matching distillation (DMD) provides a general framework for few-step diffusion generation, but its modern text-to-image instantiations ha...
arXiv Machine Learning
Jun 30
Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
arXiv:2606. 29287v1 Announce Type: new Abstract: Diffusion and continuous-flow generative models achieve high-quality generation, and their deterministic sampling can be formulated as solving learned ODE dynamics.
arXiv AI
5d ago
Persistent Negatives for Adversarial Black-Box On-Policy Distillation
The paper introduces Persistent Negative Adversarial Distillation, a method that improves black-box on-policy distillation by maintaining a live pool of historical teacher–student comparisons to stabilize the discriminator’s negative distribution. By anchoring the discriminator with these persistent negatives, the approach reduces reward-estimation error and yields smoother, higher-performing student policies across multiple benchmarks. The study demonstrates that the choice of negative samples is a critical design factor in effective black-box distillation.
arXiv Machine Learning
1d ago
Visualizing Distribution Coverage in Generative Diffusion Models
arXiv:2609.38853v1 Announce Type: new Abstract: Diffusion distillation is widely adopted to accelerate sampling, and the resulting few-step models are broadly believed to match or even surpass their...