arXiv Computer Vision
DMA$^2$: Pixel-space Distribution Matching with Adversarial and Anchor Losses
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
1d ago
DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation
arXiv:2610.02188v1 Announce Type: cross Abstract: Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it...
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...
Hugging Face Trending Papers
Jul 7
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing generative and editing approaches reuse these priors by casting dense prediction as target generation: annotations such as depth, normals, alpha mattes, masks, and heatmaps are encoded into an RGB-trained VAE latent space and decoded back as image-like targets.
arXiv AI
Aug 11
RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation
arXiv:2608. 09226v1 Announce Type: cross Abstract: Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression.
Hugging Face Trending Papers
Aug 10
RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation
Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide a natural source of distillation supervision rather than a disposable byproduct of sampling.
arXiv Machine Learning
Jun 9
Optimizing Few-Step Generation with Adaptive Matching Distillation
arXiv:2602. 07345v2 Announce Type: replace-cross Abstract: Distribution Matching Distillation (DMD) is a powerful acceleration paradigm, yet its stability is often compromised in Forbidden Zone, regions where the real teacher provides unreliable guidance while the fake teacher exerts insufficient repulsive force.