PDMD: Projected Distribution Matching Distillation for Video Diffusion Models

Modern video diffusion models require tens of denoising evaluations over long spatiotemporal token sequences. Distribution Matching Distillation (DMD) reduces the number of function evaluations (NFE) to just a few. However, DMD samples can degrade during training, exhibiting progressive oversaturation and artifacts. We trace this instability to critic errors, which enter successive student updates and accumulate over time. We introduce Projected Distribution Matching Distillation (PDMD) to filter critic errors. PDMD projects out the component of the DMD update parallel to the student-critic endpoint residual. At a fixed noisy query, we prove that this residual is an unbiased estimate of the critic's endpoint error. Under high-dimensional assumptions, this projection removes a constant fraction of critic error while discarding only a vanishing fraction of ideal DMD signal. Empirically, the projection stabilizes training and improves sample quality where DMD degrades and develops unnatural textures. PDMD requires only a one-line code change to DMD, with no extra loss, network, data, model pass, or multi-stage training. With Wan2.1, PDMD achieves a VBench total score of 83.73 at 4 NFE, surpassing matched DMD by 1.03 points. On MiniMax-H3 joint video-audio generation, PDMD achieves a VideoGen-Eval visual total score of 83.17, 0.41 points above the strongest distilled baseline. PDMD also achieves the best performance on all six audio metrics among the compared 4-NFE models. Qualitative comparisons and user studies favor PDMD over the distilled baselines in visual quality, motion, and audio quality. Code and models are available at https://pdmd2026.github.io/.

2. Document Verification & Archival Data

• Contributing Researchers: Zimo Wang, Junkun Yuan, Angtian Wang, Haotian Yang, Canyu Zhang, Siyuan Yuan, Xingchang Huang, Bo Liu, Yizhi Wang, Yiding Yang, Chongyang Ma, Gordon Guocheng Qian
• Submission Date: September 28, 2026
• Full Preprint Document: Download Official PDF
• Permanent Archive Record: arXiv:2609.35768v1

3. Academic Citation Reference

Standard Reference (APA Format):

Zimo Wang, et al. (2026). PDMD: Projected Distribution Matching Distillation for Video Diffusion Models. arXiv:2609.35768v1. https://arxiv.org/abs/2609.35768v1

Academic Field: Computer Vision | Document Identifier: arXiv:2609.35768v1

BibTeX Entry:

@article{arxiv_2609.35768v1,
  author    = {Zimo Wang and Junkun Yuan and Angtian Wang and Haotian Yang and Canyu Zhang and Siyuan Yuan and Xingchang Huang and Bo Liu and Yizhi Wang and Yiding Yang and Chongyang Ma and Gordon Guocheng Qian},
  title     = {{PDMD: Projected Distribution Matching Distillation for Video Diffusion Models}},
  journal   = {arXiv preprint arXiv:2609.35768v1},
  year      = {2026},
  url       = {https://arxiv.org/abs/2609.35768v1}
}